Method and system for planning, predicting and monitoring treatment of lung disease

Abstract

The present disclosure provides methods for planning, predictively modeling, and monitoring treatments for lung disease. In some embodiments, a method for planning treatment of a patient having a lung disease includes receiving patient data including computed tomography (CT) data of a lung of the patient. The method may include generating a set of lung metrics by inputting the patient data into a first machine learning algorithm. The method may also include predicting a response of the patient to treatment of the lung disease by inputting the set of lung metrics into a second machine learning algorithm. The method may further include evaluating whether the patient is a candidate for the treatment of the pulmonary disease based on the predicted response. The method may further include evaluating whether the patient is benefited after treatment and whether additional treatment is needed.

Description

[0001] Cross Reference to Related Applications

[0002] This application claims priority benefit of U.S. Patent Application No. 63 / 477,623, filed December 29, 2023, the entirety of which is incorporated herein by reference. TECHNICAL FIELD

[0003] The present technology relates generally to treatment planning, and in particular to methods and systems for planning, predicting, and monitoring treatment of lung disease. BACKGROUND

[0004] Chronic obstructive pulmonary disease (COPD) is a disease in which lung function is impaired. Symptoms of COPD include cough, wheezing, shortness of breath, and chest tightness. Smoking is the leading cause of COPD, but long-term exposure to other lung irritants (e.g., air pollution, chemical fumes, dust) can also cause or contribute to COPD. In most cases, COPD is a progressive disease that worsens over the course of years. Thus, many people have COPD without realizing its progression. COPD is currently a leading cause of death and disability in the United States. Severe COPD can prevent patients from performing even basic activities, such as walking, climbing stairs, or bathing. Unfortunately, there is no known cure for COPD. Nor is there a known medical technology that can reverse the lung damage associated with COPD. Conventional methods of treating COPD are associated with severe complications, have limited effectiveness, are suitable for only a small fraction of COPD patients, and / or have other significant drawbacks. Given the prevalence of this disease and the inadequacy of conventional treatments, there is a great need for innovation in this area. SUMMARY

[0005] For example, in accordance with various aspects described below, aspects of the present technology are illustrated with reference to Figures 1 to 28 For convenience, various examples of aspects of the present technology are described as numbered examples (1, 2, 3, etc.). These are provided as examples only, and are not limiting of the present technology.

[0006] Example 1. A method for planning treatment of a patient having a lung disease, the method comprising:

[0007] receiving patient data, the patient data including computed tomography (CT) data of a lung of the patient;

[0008] producing a set of lung metrics by inputting the patient data into a first machine learning algorithm, wherein the set of lung metrics is representative of a state of the lung of the patient;

[0009] predicting a response of the patient to a treatment for the lung disease by inputting the set of lung metrics into a second machine learning algorithm; and

[0010] evaluating whether the patient is a candidate for the treatment for the lung disease based on the predicted response.

[0011] Example 2. The method of example 1, wherein the patient data comprises one or more of: questionnaire information, medical record information, magnetic resonance imaging (MRI) data, single photon emission computed tomography (SPECT) data, bronchoscopy data, ventilation perfusion data, pulmonary function test data, chest radiography data, fluoroscopy data, photographs, or sensor data.

[0012] Example 3. The method of example 1 or 2, wherein the CT data comprises expiratory CT data.

[0013] Example 4. The method of example 3, wherein the CT data comprises inspiratory CT data.

[0014] Example 5. The method of any one of examples 1-4, wherein the patient data comprises data obtained at a plurality of different time points.

[0015] Example 6. The method of any one of examples 1-5, wherein the set of lung metrics is related to whether the patient has at least one of chronic obstructive pulmonary disease (COPD), severe emphysema, or severe emphysema with hyperinflation.

[0016] Example 7. The method of any one of examples 1-6, wherein the set of lung metrics characterizes one or more lung parameters comprising one or more of: forced expiratory volume in 1 second, forced vital capacity, vital capacity, inspiratory capacity, inspiratory capacity / total lung capacity ratio, functional residual capacity, total lung capacity, carbon monoxide diffusing capacity, residual volume, residual volume / total lung capacity ratio, closed space volume, lung lobe and / or lung segment tissue destruction, lung lobe and / or lung segment air trapping, lung lobe and / or lung segment fissure status, lung lobe and / or lung segment fissure completeness, lung lobe and / or lung segment ventilation, lung function, lung lobe and / or lung segment emphysema homogeneity / heterogeneity, emphysema type, location of diseased portion of lung, lung lobe volume, lung segment volume, lung segment location, diaphragm shape, tissue density, opacity, proximity of diseased portion to anatomical structures, proximity of diseased portion to other medical devices, bronchial slice lumen diameter, airflow mapping, collapsed airways, airway pressure, airway compliance, pleural pressure, airway diameter and wall thickness, airway wall deformation, vascular perfusion, parenchymal density, lung bullae, information localizing disease in the lung, obstruction score, mucus score, or degree of epithelialization.

[0017] Example 8. The method of any one of examples 1-7, wherein the set of lung metrics comprises at least one disease score characterizing a severity of a lung disease in the patient.

[0018] Example 9. The method of example 8, wherein the at least one disease score is a predictor of patient response to the treatment of the lung disease.

[0019] Example 10. The method of example 8 or 9, wherein the set of lung metrics comprises a plurality of disease scores, each disease score corresponding to a respective lobe, segment, or subsegment region of the lung of the patient.

[0020] Example 11. The method of example 8 or 9, wherein the set of lung metrics comprises a single disease score based on a plurality of local disease scores, each local disease score corresponding to a respective lobe, segment, or subsegment region of the lung of the patient.

[0021] Example 12. The method of example 11, wherein the single disease score is an average of the plurality of local disease scores.

[0022] Example 13. The method of any one of examples 8-12, wherein the at least one disease score is indicative of a degree of at least one of air trapping or hyperinflation in the lung of the patient.

[0023] Example 14. The method of any one of examples 7-13, wherein the set of lung metrics characterizes a change in at least one of the one or more lung parameters over a plurality of time points.

[0024] Example 15. The method of example 14, wherein the plurality of time points comprises two or more of: prior to intrabronchial implant treatment, after intrabronchial implant treatment, prior to bronchodilator administration, after bronchodilator administration, prior to exercise, or during exercise.

[0025] Example 16. The method of any one of examples 1-15, wherein the predicted response comprises a prediction of one or more of: forced expiratory volume in one second, forced vital capacity, vital capacity, inspiratory capacity, inspiratory capacity / total lung capacity ratio, functional residual capacity, total lung capacity, carbon monoxide diffusing capacity, residual volume, residual volume / total lung capacity ratio, lung segment volume, mMRC score, SGRQ score or subgroups thereof, CAT score or subgroups thereof, 6-minute walk test result, cycle ergometry result, cardiopulmonary exercise test (CPET) result, patient health metric, patient exercise metric, patient visit metric, number of implant removals required, time to re-intervention, treatment durability, quality of life score, body mass index, comorbidities, dosing regimen, length of hospital stay, healthcare utilization or cost.

[0026] Example 17. The method of any one of examples 1-16, wherein the treatment comprises airway treatment of COPD.

[0027] Example 18. The method of example 17, wherein the airway treatment comprises pharmacological treatment.

[0028] Example 19. The method of example 17 or 18, wherein the airway treatment comprises interventional treatment.

[0029] Example 20. The method of example 19, wherein the interventional treatment comprises one or more of: vapor therapy, administration of a sealant, transbronchial fenestration, placement of an endobronchial coil, placement of an endobronchial valve, or placement of a minimal endobronchial augmentation implant.

[0030] Example 21. The method of example 20, wherein the interventional treatment comprises the placement of the minimal endobronchial augmentation implant.

[0031] Example 22. The method of any one of examples 1-21, further comprising generating a plan for the treatment if the patient is a candidate for the treatment of the lung disease.

[0032] Example 23. The method of example 22, wherein the plan is generated by inputting one or more of the predicted response or the set of lung metrics into a third machine learning algorithm.

[0033] Example 24. The method of example 22 or 23, wherein the treatment comprises placement of at least one minimal endobronchial augmentation implant, and the plan comprises one or more of: implant placement location, number of implants, implant size, implant type, path to target location, or local treatment solution.

[0034] Example 25. The method of example 24, wherein the implant placement location is based at least in part on one or more of: location of dynamic airway collapse determined from expiratory CT data, severity of disease in a peripheral zone of the lung, location of the patient’s pleural wall, or location of lobar, segmental, and / or subsegmental airways.

[0035] Example 26. The method of any one of examples 1-25, further comprising generating a report comprising a summary of one or more of: at least a portion of the set of lung metrics, the predicted response, an assessment of whether the patient is a candidate for the treatment, or the generated plan for the treatment.

[0036] Example 27. The method of any of examples 1-26, further comprising updating one or more of the first machine learning algorithm or the second machine learning algorithm based on historical or repository patient data.

[0037] Example 28. The method of example 27, wherein the historical or repository patient data comprises data for patients with GOLD IIIC COPD, data for patients with GOLD IV COPD, or a combination thereof.

[0038] Example 29. The method of example 27 or 28, wherein the historical or repository patient data comprises data for patients treated with one or more of: a minimal bronchial endoluminal augmentation implant, a bronchial valve, a bronchial coil, or a vapor therapy.

[0039] Example 30. The method of any of examples 27-29, wherein the historical or repository patient data comprises data from the patient at an earlier time point.

[0040] Example 31. A system comprising:

[0041] a processor; and

[0042] a memory operatively coupled to the processor and storing instructions that, when executed by the processor, cause the computing system to perform operations comprising the method of any of examples 1-30.

[0043] Example 32. A non-transitory computer-readable storage medium comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations comprising the method of any of examples 1-30.

[0044] Example 33. A method for assessing treatment outcomes for a patient, the method comprising:

[0045] receiving patient data comprising computed tomography (CT) data of a lung of the patient after placement of a bronchial implant in the lung of the patient;

[0046] generating a set of state metrics by inputting the patient data into a first machine learning algorithm, wherein the set of state metrics comprises:

[0047] a set of lung metrics representing a state of the lung of the patient after the placement of the bronchial implant, and

[0048] a set of implant metrics representing a state of the bronchial implant after placement in the lung;

[0049] determining a response of the patient to the endobronchial implant by inputting the set of state metrics into a second machine learning algorithm; and

[0050] predicting an outcome of the patient after the placement of the endobronchial implant by inputting one or more of the set of state metrics or the determined response into a third machine learning algorithm.

[0051] Example 34. The method of Example 33, wherein the patient data comprises one or more of: questionnaire information, medical record information, magnetic resonance imaging (MRI) data, single photon emission computed tomography (SPECT) data, bronchoscopy data, ventilation perfusion data, pulmonary function test data, chest radiography data, fluoroscopy data, photographs, or sensor data.

[0052] Example 35. The method of Example 33 or 34, wherein the CT data comprises expiratory CT data.

[0053] Example 36. The method of any one of Examples 33-35, wherein the CT data comprises inspiratory CT data.

[0054] Example 37. The method of any one of Examples 33-36, wherein the patient data comprises data obtained at a plurality of different time points.

[0055] Example 38. The method of any one of Examples 33-37, wherein the set of lung metrics characterizes one or more lung parameters characterizing any of: forced expiratory volume in 1 second, forced vital capacity, vital capacity, inspiratory capacity, inspiratory capacity / total lung capacity ratio, functional residual capacity, total lung capacity, carbon monoxide diffusing capacity, residual volume, residual volume / total lung capacity ratio, closed space volume, lung lobe and / or segment tissue destruction, lung lobe and / or segment air trapping, lung lobe and / or segment fissure status, lung lobe and / or segment fissure completeness, lung lobe and / or segment ventilation, lung function, lung lobe and / or segment emphysema homogeneity / heterogeneity, emphysema type, location of diseased portion of the lung, lung lobe volume, lung segment volume, lung segment location, diaphragm shape, tissue density, opacity, proximity of diseased portion to anatomical structures, proximity of diseased portion to other medical devices, bronchial slice lumen inner diameter, airflow mapping, collapsed airways, airway pressure, airway compliance, pleural pressure, airway diameter and wall thickness, airway wall deformation, vascular perfusion, parenchymal density, lung bullae, information localizing disease in the lung, obstruction score, mucus score, degree of epithelialization, granulation tissue, implant-induced airway deformation, or airway tissue invagination into the lumen of the implant.

[0056] Example 39. The method of any of Examples 33-38, wherein the set of lung metrics comprises a disease score characterizing a severity of a lung disease in the patient.

[0057] Example 40. The method of Example 38 or 39, wherein the set of lung metrics characterizes a change in at least one of the one or more lung parameters over a plurality of time points.

[0058] Example 41. The method of Example 40, wherein the plurality of time points comprises two or more of: prior to intrabronchial implant treatment, after intrabronchial implant treatment, prior to bronchodilator administration, after bronchodilator administration, prior to exercise, or during exercise.

[0059] Example 42. The method of any of Examples 33-41, wherein the intrabronchial implant comprises a minimal intrabronchial augmentation implant.

[0060] Example 43. The method of any of Examples 33-42, wherein the set of implant metrics characterizes one or more of: implant location, distance between distal end of the implant and pleura, implant length, implant diameter at any one or more locations along the length of the implant, implant cross-sectional profile at any one or more locations along the length of the implant, implant integrity, pitch of rings of the implant, angle of implant ring profile relative to longitudinal axis of the implant, implant location relative to one or more additional implants, movement of the implant between inhalation and exhalation, obstruction of the implant, or implant migration.

[0061] Example 44. The method of any of Examples 33-43, further comprising generating and displaying a virtual bronchoscopy depicting a model of one or more of at least a portion of the lung metrics or at least a portion of the implant metrics.

[0062] Example 45. The method of any of Examples 33-44, wherein the determined response comprises a determination of one or more of: 1-second forced expiratory volume, forced vital capacity, vital capacity, inspiratory capacity, inspiratory capacity / total lung capacity ratio, functional residual capacity, total lung capacity, carbon monoxide diffusing capacity, residual volume, residual volume / total lung capacity ratio, lung segment volume, mMRC score, SGRQ score or subgroups thereof, CAT score or subgroups thereof, 6-minute walk test result, cycle ergometry result, cardiopulmonary exercise test (CPET) result, patient health metric, patient exercise metric, patient visit metric, number of implant removals required, time to re-intervention, treatment durability, quality of life score, body mass index, comorbidities, dosing regimen, length of hospital stay, healthcare utilization or cost.

[0063] Example 46. The method of any of examples 33-45, wherein the predicted outcome comprises a prediction of a postoperative issue following the placement of the endobronchial implant.

[0064] Example 47. The method of example 46, wherein the postoperative issue comprises one or more of: excessive mucus, excessive granulation tissue, excessive fibrosis, implant collapse, implant failure, implant migration, implant sputum, inadequate lung function, pneumothorax, infection, pneumonia, or hospitalization.

[0065] Example 48. The method of example 46 or 47, further comprising determining an intervention to address the postoperative issue.

[0066] Example 49. The method of example 48, wherein the determined intervention comprises one or more of: a clean bronchoscopy, retrieval or removal of the endobronchial implant, repositioning the endobronchial implant, replacement of the endobronchial implant, dilation of the endobronchial implant, placement of an additional endobronchial implant, or consultation with a healthcare professional.

[0067] Example 50. The method of any of examples 33-49, further comprising generating a report comprising a summary of one or more of: at least a portion of the lung metrics, at least a portion of the implant metrics, the determined response of the patient to the endobronchial implant, the predicted outcome of the patient following the placement of the endobronchial implant, or the determined intervention to address a postoperative issue.

[0068] Example 51. The method of any of examples 33-50, further comprising updating one or more of the first machine learning algorithm, the second machine learning algorithm, or the third machine learning algorithm based on historical or repository patient data.

[0069] Example 52. The method of example 51, wherein the historical or repository patient data comprises data of patients with GOLD IIIC COPD, data of patients with GOLD IV COPD, or a combination thereof.

[0070] Example 53. The method of example 51 or 52, wherein the historical or repository patient data comprises data of patients treated with one or more of: a minimal endobronchial augmentation implant, an endobronchial valve, an endobronchial coil, or vapor therapy.

[0071] Example 54. The method of any of examples 51-53, wherein the historical or repository patient data comprises data of the patient from an earlier time point.

[0072] Example 55. The method of any of examples 33-54, further comprising comparing the set of lung metrics to a second set of lung metrics determined from one or more of: image data of the lung prior to the placement of the endobronchial implant, image data of the lung at an earlier time point after the placement of the endobronchial implant, image data of the lung after placement of another endobronchial implant at a location different from the location of the endobronchial implant, or image data from other patients with COPD.

[0073] Example 56. A system comprising:

[0074] a processor; and

[0075] a memory operatively coupled to the processor and storing instructions that, when executed by the processor, cause the computing system to perform operations comprising the method of any of examples 33-55.

[0076] Example 57. A non-transitory computer-readable storage medium comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations comprising the method of any of examples 33-55.

[0077] Example 58. A method for assessing a patient having or suspected of having a lung disease, the method comprising:

[0078] receiving patient data including computed tomography (CT) data of a lung of the patient; and

[0079] generating a lung disease score for a region of interest of the lung by inputting the patient data into a machine learning algorithm, wherein the lung disease score characterizes a severity of a lung disease in the region of interest of the lung of the patient, wherein the region of interest is a lung segment region or a subsegment region of the lung.

[0080] Example 59. The method of example 58, wherein the machine learning algorithm assesses voxel densities in the CT data associated with the region of interest of the lung of the patient.

[0081] Example 60. The method of example 58 or 59, wherein the lung disease score is based on a plurality of local disease scores, each local disease score corresponding to a respective lobe, segment, or subsegment region of the lung of the patient.

[0082] Example 61. The method of example 60, wherein the lung disease score is an average of the plurality of local disease scores.

[0083] Example 62. The method of Example 58 or 59, wherein the lung disease score is a first lung disease score, wherein the method further comprises generating a plurality of lung disease scores including the first lung disease score, wherein each of the plurality of lung disease scores corresponds to a respective lobe, segment, or subsegment region of the lung of the patient.

[0084] Example 63. The method of any one of Examples 58-62, wherein the lung disease score is indicative of a degree of at least one of air trapping or hyperinflation in the lung of the patient.

[0085] Example 64. The method of any one of Examples 58-63, wherein the CT data comprises expiratory CT data.

[0086] Example 65. The method of any one of Examples 58-64, wherein the CT data comprises inspiratory CT data.

[0087] Example 66. The method of any one of Examples 58-65, wherein the CT data is generated prior to administration of a treatment to the patient to treat the lung disease.

[0088] Example 67. The method of any one of Examples 58-65, wherein the CT data is generated after administration of a treatment to the patient to treat the lung disease.

[0089] Example 68. The method of Example 66 or 67, wherein the treatment comprises placement of an endobronchial implant.

[0090] Example 69. A system comprising:

[0091] a processor; and

[0092] a memory operatively coupled to the processor and storing instructions that, when executed by the processor, cause the computing system to perform operations comprising the method of any one of Examples 58-68.

[0093] Example 70. A computed tomography (CT) scanner comprising:

[0094] a processor; and

[0095] a memory operatively coupled to the processor and storing instructions that, when executed by the processor, cause the CT scanner to perform operations comprising the method of any one of Examples 58-68.

[0096] Example 71. A non-transitory computer-readable storage medium comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations comprising the method of any of examples 58-68.

[0097] Example 72. A method for normalizing quantitative computed tomography (CT) results for a patient, the method comprising:

[0098] receiving first CT data for the patient, wherein the first CT data is generated under a predetermined imaging condition; and

[0099] transforming the first CT data to second CT data by applying at least one correction factor associated with the predetermined imaging condition to the first CT data.

[0100] Example 73. The method of example 72, wherein the at least one correction factor maps a voxel density in the first CT data to a normalized voxel density.

[0101] Example 74. The method of example 72 or 73, wherein the at least one correction factor compensates for a voxel density in the first CT data affected by one or more of: tube current, tube potential, pitch.

[0102] Example 75. The method of any of examples 72-74, wherein the at least one correction factor compensates for a voxel density in the first CT data affected by at least one of: slice thickness or slice spacing.

[0103] Example 76. The method of any of examples 72-75, wherein the at least one correction factor compensates for a voxel density in the first CT data affected by a reconstruction algorithm used to determine sharpness or smoothness of an image in an axial plane.

[0104] Example 77. The method of any of examples 72-76, wherein the first CT data is obtained from a CT scan provider having a provider-specific machine learning algorithm for reconstructing CT images from CT data, wherein the at least one correction factor compensates for a voxel density in the first CT data affected by the provider-specific machine learning algorithm.

[0105] Example 78. The method of any of examples 72-77, wherein the at least one correction factor compensates for a voxel density in the first CT data affected by administration of a contrast agent in the patient prior to generation of the first CT data.

[0106] Example 79. The method of any of examples 72-78, wherein the second CT data is normalized with respect to CT scan parameters.

[0107] Example 80. The method of any one of Examples 72 to 79, wherein the first CT data is obtained during a preoperative phase prior to placement of an endobronchial implant in the patient.

[0108] Example 81. A method according to any one of Examples 72 to 80, further comprising generating a set of lung metrics associated with the patient based on the second CT data.

[0109] Example 82. A method according to any one of Examples 72 to 79, wherein the first CT data is obtained during a perioperative phase during placement of an endobronchial implant in the patient.

[0110] Example 83. The method of any one of Examples 72 to 79, wherein the first CT data is obtained during a postoperative period after placement of an endobronchial implant in the patient.

[0111] Example 84. The method of Example 82 or 83, further comprising generating at least one of a set of lung measurements or a set of implant measurements associated with the patient based on the second CT data.

[0112] Example 85. A system comprising:

[0113] processor; and

[0114] A memory operably coupled to the processor and storing instructions that, when executed by the processor, cause a computing system to perform operations including the method according to any one of Examples 72-84.

[0115] Example 86. A computed tomography (CT) scanner comprising:

[0116] processor; and

[0117] A memory operably coupled to the processor and storing instructions that, when executed by the processor, cause the CT scanner to perform operations including the method according to any one of Examples 72 to 84.

[0118] Example 87. A non-transitory computer-readable storage medium comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations including the method of any of Examples 72-84.

[0119] Example 88. A method for planning treatment for a patient suffering from a lung disease, the method comprising:

[0120] receiving patient data, the patient data including computed tomography (CT) data of a lung of the patient;

[0121] generating a set of lung metrics by inputting the patient data into a first machine learning algorithm, wherein the set of lung metrics is representative of a state of the lung of the patient;

[0122] identifying, based at least in part on the generated lung metrics, a potential target region in the lung for treating the lung disease.

[0123] Example 89. The method of Example 88, wherein the patient data comprises one or more of: questionnaire information, medical record information, magnetic resonance imaging (MRI) data, single photon emission computed tomography (SPECT) data, bronchoscopy data, ventilation perfusion data, pulmonary function test data, chest radiography data, fluoroscopy data, photographs, or sensor data.

[0124] Example 90. The method of Example 88 or 89, wherein the CT data comprises expiratory CT data.

[0125] Example 91. The method of any one of Examples 88-90, wherein the CT data comprises inspiratory CT data.

[0126] Example 92. The method of any one of Examples 88-91, wherein the patient data comprises data obtained at a plurality of different time points.

[0127] Example 93. The method of any one of Examples 88-92, wherein the set of lung metrics is related to whether the patient has at least one of: chronic obstructive pulmonary disease (COPD), severe emphysema, or severe emphysema with hyperinflation.

[0128] Example 94. The method of any of examples 88-93, wherein the set of lung metrics characterizes one or more lung parameters comprising one or more of: forced expiratory volume in 1 second, forced vital capacity, vital capacity, inspiratory capacity, inspiratory capacity / total lung capacity ratio, functional residual capacity, total lung capacity, carbon monoxide diffusing capacity, residual volume, residual volume / total lung capacity ratio, closed space volume, lung lobe and / or lung segment tissue destruction, lung lobe and / or lung segment air trapping, lung lobe and / or lung segment fissure status, lung lobe and / or lung segment fissure completeness, lung lobe and / or lung segment ventilation, lung function, lung lobe and / or lung segment emphysema homogeneity / heterogeneity, emphysema type, location of diseased portion of lung, lung lobe volume, lung segment volume, lung segment location, diaphragm shape, tissue density, opacity, proximity of diseased portion to anatomical structures, proximity of diseased portion to other medical devices, bronchial slice lumen inner diameter, airflow mapping, collapsed airways, airway pressure, airway compliance, pleural pressure, airway diameter and wall thickness, airway wall deformation, blood vessel perfusion, parenchymal density, lung bullae, information localizing disease in the lung, obstruction score, mucus score, or degree of epithelization.

[0129] Example 95. The method of any of examples 88-94, wherein the set of lung metrics comprises at least one disease score characterizing a severity of a lung disease in the patient.

[0130] Example 96. The method of example 95, wherein the at least one disease score is a predictor of patient response to the treatment of the lung disease.

[0131] Example 97. The method of example 95 or 96, wherein the set of lung metrics comprises a plurality of disease scores, each disease score corresponding to a respective lobe, segment, or subsegment region of the lung of the patient.

[0132] Example 98. The method of example 95 or 96, wherein the set of lung metrics comprises a single disease score based on a plurality of local disease scores, each local disease score corresponding to a respective lobe, segment, or subsegment region of the lung of the patient.

[0133] Example 99. The method of example 98, wherein the single disease score is an average of the plurality of local disease scores.

[0134] Example 100. The method of any of examples 95-99, wherein the at least one disease score is indicative of a degree of at least one of air trapping or overinflation in the lung of the patient.

[0135] Example 101. The method of any of examples 94-100, wherein the set of lung metrics characterizes a change in at least one of the one or more lung parameters over a plurality of time points.

[0136] Example 102. The method of example 101, wherein the plurality of time points comprises two or more of: prior to intrabronchial implant treatment, after intrabronchial implant treatment, prior to bronchodilator administration, after bronchodilator administration, prior to exercise, or during exercise.

[0137] Example 103. The method of any of examples 88-102, wherein the treatment comprises airway treatment for COPD.

[0138] Example 104. The method of example 103, wherein the airway treatment comprises pharmacological treatment.

[0139] Example 105. The method of example 103 or 104, wherein the airway treatment comprises interventional treatment.

[0140] Example 106. The method of example 105, wherein the interventional treatment comprises one or more of: vapor therapy, administration of a sealant, transbronchial fenestration, placement of an intrabronchial coil, placement of an intrabronchial valve, or placement of a minimal intrabronchial augmentation implant.

[0141] Example 107. The method of example 106, wherein the interventional treatment comprises the placement of the minimal intrabronchial augmentation implant.

[0142] Example 108. The method of any of examples 88-107, further comprising generating a plan for the treatment.

[0143] Example 109. The method of example 108, wherein the plan is generated by inputting the set of lung metrics into a second machine learning algorithm.

[0144] Example 110. The method of example 108 or 109, wherein the treatment comprises placement of at least one minimal intrabronchial augmentation implant, and the plan comprises one or more of: implant placement location, number of implants, implant size, implant type, path to target location, or local treatment solution.

[0145] Example 111. The method of example 110, wherein the implant placement location is based at least in part on one or more of: location of dynamic airway collapse determined from expiratory CT data, severity of disease in a peripheral zone of the lung, location of the patient’s pleural wall, or location of lobar, segmental, and / or subsegmental airways.

[0146] Example 112. A system comprising:

[0147] a processor; and

[0148] a memory, operatively coupled to the processor, storing instructions that, when executed by the processor, cause the computing system to perform operations comprising the method of any of examples 88-111.

[0149] Example 113. A computed tomography (CT) scanner comprising:

[0150] a processor; and

[0151] a memory, operatively coupled to the processor, storing instructions that, when executed by the processor, cause the CT scanner to perform operations comprising the method of any of examples 88-111.

[0152] Example 114. A non-transitory computer-readable storage medium comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations comprising the method of any of examples 88-111. BRIEF DESCRIPTION OF DRAWINGS

[0153] Many aspects of the disclosure can be better understood with reference to the following figures. The components in the figures are not necessarily to scale. Instead, emphasis is placed on enabling a clear disclosure of the principles of the present disclosure.

[0154] Figure 1 is a schematic illustration of a subject’s bronchial tree within the thoracic cavity of a human subject.

[0155] Figure 2 is a schematic illustration of a bronchial tree of an isolated human subject.

[0156] Figure 3 is a zoomed-in view of the terminal portion of the bronchial tree shown in Figure 2

[0157] Figure 4 is a table showing examples of the dimensions and generation numbers of different portions of a bronchial tree of a human subject.

[0158] Figure 5 is a graph showing lung volumes during normal lung function.

[0159] Figure 6 is a table showing airway wall composition at different portions of a bronchial tree of a human subject.

[0160] Figure 7 ​is an anatomical illustration of the composition of the airway wall at different parts of the bronchial tree of a human subject.

[0161] Figure 8 is an anatomical illustration showing narrowing of small airways in emphysematous lung tissue.

[0162] Figure 9 is an anatomical illustration showing damage to alveolar walls in emphysematous lung tissue.

[0163] Figure 10 is an anatomical illustration showing normal airway patency during expiration in healthy lung tissue.

[0164] Figure 11 is an anatomical illustration showing airway collapse during expiration in emphysematous lung tissue.

[0165] Figure 12 is an anatomical illustration showing a normal acinus.

[0166] Figure 13 is an anatomical illustration showing acinar centri lobular emphysema.

[0167] Figure 14 is an anatomical illustration showing panacinar emphysema.

[0168] Figure 15 is an anatomical illustration showing paraseptal emphysema.

[0169] Figure 16 is a side view of an implant according to at least some embodiments of the present technology.

[0170] Figure 17 is a schematic end view of the implant shown in Figure 16

[0171] Figure 18 is a side view of a portion of an implant within an airway according to at least some embodiments of the present technology.

[0172] Figure 19 is a block diagram providing an overview of a workflow for selecting a patient for treatment and planning and monitoring a treatment procedure according to embodiments of the present technology.

[0173] Figure 20 is a flow diagram illustrating a method for planning a treatment of a patient according to embodiments of the present technology.

[0174] Figure 21 is a flow diagram illustrating a method for assessing a treatment outcome of a patient according to embodiments of the present technology.

[0175] Figure 22 is a flow diagram illustrating a method for updating a treatment plan of a patient according to embodiments of the present technology. Figure 20 and​21 a flowchart of a method of a software algorithm.

[0176] Figure 23A and 24 B is a flowchart illustrating an example of generating various lung metrics based on an inhale CT scan and an exhale CT scan, respectively.

[0177] Figure 24 is a flowchart illustrating an example of assessing treatment effectiveness and / or efficacy based on CT scans.

[0178] Figure 25A is an anatomical illustration showing coronal views of lung fissures in the right lung and the left lung. Figure 25B is an anatomical illustration showing sagittal views of lung fissures in the right lung. Figure 25C is an anatomical illustration showing sagittal views of lung fissures in the left lung.

[0179] Figure 26 is a flowchart illustrating a method for normalizing quantitative CT results.

[0180] Figure 27 is a flowchart illustrating a method for assessing a patient having or suspected of having a lung disease.

[0181] Figure 28 is a flowchart illustrating a method for planning a treatment of a patient having a lung disease. DETAILED DESCRIPTION

[0182] The present technology relates to methods for planning, predicting, and / or monitoring a course of treatment of a patient having a lung disease, such as COPD. In some embodiments, for example, a method for planning a treatment of a patient includes receiving patient data including computed tomography (CT) data of a lung of the patient. The method can include generating a set of lung metrics by inputting the patient data into a first machine learning algorithm. The method can include predicting a response of the patient to a treatment of the lung disease (e.g., a treatment using an endobronchial implant) by inputting the set of lung metrics into a second machine learning algorithm. The method can further include assessing whether the patient is a candidate for the treatment of the lung disease based on the predicted response.

[0183] As another example, a method for assessing treatment outcomes for a patient includes receiving patient data including CT data of a lung of a patient after placement of an endobronchial implant in the lung of the patient. The method can include generating a set of state metrics (e.g., lung metrics, implant metrics) by inputting the patient data into a first machine learning algorithm. The method can also include determining a response of the patient to the endobronchial implant by inputting the set of state metrics into a second machine learning algorithm. The method can further include predicting an outcome of the patient after the placement of the endobronchial implant by inputting the set of state metrics and / or the determined response into a third machine learning algorithm.

[0184] The present technology can provide a number of advantages for treating patients with lung disease. For example, the methods described herein can be used to diagnose and treat patients at earlier stages of disease (e.g., Stage 2 COPD), which can improve treatment efficacy and result in better outcomes. Additionally, the methods herein can provide patients with personalized, evidence-based treatment recommendations that are more likely to result in successful outcomes. The methods herein can also improve planning of treatment procedures, which can reduce procedure time, improve patient safety, and result in improved outcomes. Furthermore, the methods of the present technology can monitor patients post-procedure to predict problems before they occur, thereby reducing the frequency of additional hospitalizations and visits after a treatment procedure.

[0185] Embodiments of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings, in which like reference numerals can be used to refer to like elements throughout the several figures, and where the implementations can be shown by examples which do not limit the scope of use of the present technology. Example implementations are provided herein for illustrative purposes only and merely to facilitate recognition of various potential implementations.

[0186] The headings provided herein are merely for convenience and do not interpret the scope or meaning of the claimed technology. Embodiments under any one heading can be used in combination with embodiments under any other heading.

[0187] I. Anatomy and Physiology

[0188] In normal breathing, the act of inhaling draws air into the lungs via the nose or mouth and the trachea. Within each lung, the inhaled air enters a branching network of progressively narrower airways called bronchi, and then into the narrowest airways called bronchioles. Bronchioles terminate in bundles of tiny round structures called alveoli. Small blood vessels called capillaries pass through the walls of the alveoli. When inhaled air reaches the alveoli, oxygen passes from the alveoli into the blood in the capillaries. At the same time, carbon dioxide moves in the opposite direction, i.e., from the blood in the capillaries into the alveoli. This process is called gas exchange. In healthy lungs, the airways and alveoli have elasticity and distensibility to accommodate air inhalation. When inhaling, the alveoli fill with air like small balloons. When exhaling, the alveoli contract. This expansion of the alveoli is an important part of efficient gas exchange. Alveoli that expand freely exchange more gas than alveoli that are inhibited from expanding.

[0189] Figure 1 is a schematic illustration of a bronchial tree of a human subject within the subject's thoracic cavity. As shown in Figure 1 , the bronchial tree includes a trachea T that extends down from the nose and mouth and divides into a left main bronchus LMB and a right main bronchus RMB. Each of the left and right main bronchi branches to form lobar bronchi LB, segmental bronchi SB, and subsegmental bronchi SSB, which have successively smaller diameters and shorter lengths as they extend distally. Figure 2 is a schematic illustration of an isolated bronchial tree. As shown in Figure 2 , the subsegmental bronchi continue to branch to form bronchioles BO, conducting bronchioles CBO, and terminal bronchioles TBO, which are the smallest airways that do not contain alveoli. The terminal bronchioles branch into respiratory bronchioles RBO, which are divided into alveolar ducts AD. Figure 3 is a magnified view of the terminal portion of a bronchial tree. As shown in Figure 3 , the alveolar ducts terminate in blind outpouchings that include two or more small clusters of alveoli A, called alveolar sacs AS. Various individual alveoli can also be disposed along the length of the respiratory bronchioles.

[0190] The bronchi and bronchioles are conducting airways that transport air to and from the alveoli. They do not participate in gas exchange. Rather, gas exchange occurs in the alveoli, which are located distal to the conducting airways, starting at the respiratory bronchioles. Depending on the degree of branching proximal to the airway, various airways of the bronchial tree are commonly referred to as "generations." For example, the trachea is referred to as "Generation 0," each level of bronchi including the left and right main bronchi are referred to as "Generation 1," the lobar bronchi are referred to as "Generation 2," and the segmental bronchi are referred to as "Generation 3." Furthermore, any of the airways extending from the trachea to the terminal bronchioles are commonly referred to as "conducting airways." Figure 4Table of examples indicating the size and number of different parts of the bronchial tree.

[0191] The respiratory bronchioles, alveoli, and alveolar sacs receive air via more proximal parts of the bronchial tree and participate in gas exchange to oxygenate blood delivered to the lungs from the heart via the pulmonary artery, branching blood vessels, and capillaries. A thin, semi-permeable membrane separates the deoxygenated blood in the capillaries from the oxygen-rich air in the alveoli. Capillaries wrap around and extend between alveoli. Oxygen in the air diffuses through the membrane into the blood. Carbon dioxide in the blood diffuses through the membrane into the air in the alveoli. New, oxygen-rich blood then flows from the alveolar capillaries to the heart through branching blood vessels of the pulmonary venous system. The heart pumps the oxygen-rich blood to the rest of the body. When the diaphragm and intercostal muscles relax and the lungs and chest wall elastically return to their normal, relaxed state, deoxygenated air in the lungs is exhaled. In this way, air flows through branching bronchioles, segmental bronchi, lobar bronchi, main bronchi, and trachea, and is eventually expelled through the mouth and nose.

[0192] Figure 5 is a graph showing lung volumes during normal lung function. About one-tenth of total lung capacity is used at rest. More volume is used as needed (e.g., during exercise). The tidal volume (TV) is the volume of air inhaled and exhaled during unconscious breathing. The extra volume of air that can be exhaled with maximum effort after a normal inspiration is the inspiratory reserve volume (IRV). The extra volume of air that can be forced out after a normal expiration is the expiratory reserve volume (ERV). The total volume of air that can be exhaled after a maximum inspiration is the vital capacity (VC). The VC is equal to the sum of the TV, IRV, and ERV. The residual volume (RV) is the volume of air remaining in the lungs after maximum expiration. The lungs can never be completely emptied. The total lung capacity (TLC) is the sum of the VC and RV. Assessment of lung function can be used to determine whether a patient is eligible for treatment, and to assess the effectiveness of treatment.

[0193] Figure 6 is a table showing the composition of the airway wall at different parts of the bronchial tree. Figure 7 is an anatomical illustration of the composition of the airway wall at different parts of the bronchial tree. As Figure 6 and 7As shown in the middle, the walls of bronchi, bronchioles, alveolar ducts, and alveoli contain epithelium, connective tissue, goblet cells, mucous glands, club cells, smooth muscle, elastic fibers, and hyaline cartilage, with nerves, blood vessels, and inflammatory cells interspersed throughout. Most of the epithelium (from the nose to the bronchi) is covered in ciliated pseudostratified columnar epithelium, often referred to as the respiratory epithelium. The cilia on these epithelia beat in one direction, moving mucus and foreign objects (such as dust and bacteria) from more distal airways to more proximal airways, and ultimately to the throat, where the mucus and / or foreign objects are cleared by swallowing or by coughing. Moving down the bronchioles, the shape of the cells is more cuboidal, but there are still cilia.

[0194] The proportions and properties of the various components of the airway wall vary depending on the location within the bronchial tree. For example, mucous glands are abundant in the trachea and main bronchi, but are absent starting from the bronchioles (e.g., at about the 10th generation). In the trachea, the cartilage appears as C-shaped rings of hyaline cartilage, while in the bronchi, the cartilage is in the form of scattered plates. As branching continues through the bronchial tree, the amount of hyaline cartilage in the wall decreases until it disappears in the bronchioles. Smooth muscle begins in the trachea, where it is joined with the C-shaped rings of cartilage. It extends down the bronchi and bronchioles and completely surrounds the bronchi and bronchioles. The bronchi and bronchioles are composed of elastic tissue, rather than hard cartilage. As the cartilage decreases, the amount of smooth muscle increases. The mucosa also undergoes a transition from ciliated pseudostratified columnar epithelium to simple cuboidal epithelium to simple squamous epithelium.

[0195] Figures 25A to 25Cis an anatomical illustration of the fissures of the right and left lung. The right horizontal fissure separates the right upper lobe (RUL) and the right middle lobe (RML). The right oblique fissure divides the right middle lobe (RML) and the right lower lobe (RLL), and posteriorly separates the RUL and RLL. The left oblique fissure separates the left upper lobe (LUL) and the left lower lobe (LLL). In normal healthy tissue, the lung fissures are double-layered invaginations of the pleura of the lung and exit between the different lobes. Additionally, there are segmental fissures (not shown) that separate 18 segments across the five lobes (RUL, RML, RLL, LUL, LLL). However, the appearance of the lung fissures can vary from patient to patient, and can be incomplete or even absent and / or deformed (in terms of location, shape, etc.) due to disease such as COPD. The completeness or completeness degree of the lung fissures indicates how well the lobes are separated. For example, an incomplete lung fissure can indicate that air from one lobe can flow into another lobe (e.g., collateral ventilation). CT imaging can be used to visualize certain features of the lung fissures, but different CT protocols can result in different appearances of the lung fissures. One or more various algorithms can be used to automatically identify and / or characterize the lung fissures in CT imaging, such as lung fissure segmentation algorithms (e.g., algorithms to perform implicit surface fitting on surface shaped structures of the lung volume, trained machine learning algorithms such as supervised lung fissure enhancement filters, algorithms to perform adaptive lung fissure scanning and wavelet transform, etc.) and / or algorithms based on anatomical knowledge (e.g., fuzzy inference systems to search for lung fissures based at least in part on spine image intensity and smoothness, etc.) and / or other suitable algorithms for lung fissure characterization.

[0196] II. Pulmonary Disease

[0197] COPD is a major public health problem. Over 1 million patients in the United States alone have severe emphysema and severe overinflation. The vast majority of these patients do not have access to currently available treatments. The unmet clinical need globally, including in countries with high prevalence of respiratory disease due to smoking, is many times that of the United States.

[0198] In lung tissue affected by COPD, less air flows through the airways for various reasons. The airways and / or alveoli can be relatively inelastic, the walls between alveoli can be damaged or destroyed, the walls of the airways can be thick or inflamed, and / or the airways can produce excess mucus, leading to mucus buildup and airway blockage. In a typical case of COPD, the disease does not equally affect all airways and alveoli in the lung. The lung can have some regions that are significantly more affected than others. In severe cases, airways and alveoli that are not suitable for efficient gas exchange can occupy 20% to 30% or more of the total volume of the lung.

[0199] The effects of COPD are typically most apparent when the patient exercises or engages in other physical activity that would cause a healthy person to breathe hard. Patients with COPD can not be able to breathe hard because the diseased portion of the patient's lungs retains air, resulting in an inability to fully exhale. This in turn inhibits the subsequent expansion of healthy lung tissue. Thus, during exercise or other physical activity, the lungs of a COPD patient can work in a state of dynamic hyperinflation, which impairs respiratory mechanics and increases the work of breathing. The hyperinflation of the lungs can also impede cardiac filling, cause dyspnea, and / or reduce the patient's exercise performance. These and / or other deleterious effects of COPD can result in a range of symptoms that ultimately impair the patient's quality of life and increase the risk of severe disability and death.

[0200] The term COPD encompasses both chronic bronchitis and emphysema. About 25% of COPD patients have emphysema. About 40% of these emphysema patients have severe emphysema. Moreover, it is common for COPD patients to have symptoms of both chronic bronchitis and emphysema. In chronic bronchitis, the inner walls of the airways become inflamed, usually as a result of persistent irritation. This inflammation can cause the inner walls of the airways to thicken and produce thick, sticky mucus that can coat and eventually block the airways. In contrast, emphysema is primarily a pathological diagnosis that involves the abnormal permanent enlargement of airspaces distal to the terminal bronchioles. In emphysema lung tissue, the small airways and / or alveoli have typically lost their structural integrity and / or their ability to maintain their optimal shape. For example, damage or destruction to the alveolar walls can result in fewer but larger alveoli. This can severely impair normal gas exchange. Within the lung, the foci or "diseased" areas of emphysema lung tissue, which are characterized by a lack of discernible alveolar walls, can be referred to as lung bullae. These relatively inelastic dead space sacs are typically greater than 1 cm in diameter and contribute little to gas exchange. Lung bullae tend to retain air and thus create hyperinflated lung sections that limit the ability of healthy lung tissue to fully expand upon inhalation. Thus, in patients with emphysema, the diseased lung tissue not only no longer contributes significantly to respiratory function, it also impairs the function of healthy lung tissue.

[0201] Figure 8 is an anatomical illustration showing narrowing of small airways in emphysema lung tissue. Figure 9 is an anatomical illustration showing damage to alveolar walls in emphysema lung tissue. Figure 10 is an anatomical illustration showing patency of airways during exhalation in a normal lung. Figure 11 is an anatomical illustration showing collapse of airways during exhalation in emphysema lung tissue. COPD, and emphysema in particular, is characterized by irreversible destruction of alveolar walls, which contain elastic fibers that maintain a radially outward traction on small airways and can be used for inspiration and exhalation. As Figures 8 to 11As shown in the middle, when these elastic fibers are damaged, the small airways are no longer pulled radially outward and collapse, especially during exhalation. In addition, emphysema destroys the alveolar walls. As shown in the bottom left, Figure 9 This results in a larger air space and a reduction in the surface area available for gas exchange, as shown in the bottom right. Thus, the lung is unable to exchange gases at a satisfactory rate, which results in a reduction in oxygenated blood. In addition, the large air spaces of the diseased lung, combined with airway collapse, result in overinflation of the lung (air trapping) and an inability to fully exhale. Furthermore, the overinflated lung exerts a constant pressure on the chest wall, diaphragm, and surrounding structures, which can result in shortness of breath and can prevent the patient from walking short distances or performing daily tasks. Patients with advanced emphysema have a very low quality of life and life expectancy, with less than half surviving for five years.

[0202] There are three types of emphysema: centriacinar, panacinar, and paraseptal. Figure 12 This is an anatomic illustration showing a normal acinus. Figure 13 This is an anatomic illustration showing centriacinar emphysema, which involves destruction of the alveoli and airways in the central acinus, including the respiratory bronchioles and alveolar ducts. Figure 14 This is an anatomic illustration showing panacinar emphysema, which is characterized by destruction of the tissue of the alveoli, alveolar ducts, and respiratory bronchioles. This results in a fairly uniform enlargement of the air spaces throughout the acinus and produces uniformly distributed emphysematous changes across the acinus and sublobular lobule. Figure 15 This is an anatomic illustration showing paraseptal emphysema, which is characterized by enlargement of the air spaces around the acinus, primarily due to destruction of the alveoli and alveolar ducts. The distribution of paraseptal emphysema is usually limited, and it most commonly occurs along the posterior surface of the upper lung. It is often coexistent with other forms of emphysema.

[0203] Emphysema can also be characterized as heterogeneous or homogeneous. Generally, heterogeneous emphysema in a lung (right or left) is characterized by a relative difference in the amount of emphysematous destruction above a threshold value in any two or more regions (e.g., lung lobes, lung segments), while homogeneous emphysema in a lung is characterized by a relative difference in the amount of emphysematous destruction below a threshold value in any two or more regions (e.g., lung lobes, lung segments). In some patients, both the right and left lung can be heterogeneous or homogeneous, or one lung can be heterogeneous while the other lung can be homogeneous.

[0204] COPD can be treated with medication. Therapeutic regimens of bronchodilators, B2 agonists, muscarinic agonists, corticosteroids, or combinations thereof can provide short-term relief of symptoms of COPD. Non-pharmacological management solutions can also be used, such as home oxygen therapy, non-invasive positive pressure ventilation, and pulmonary rehabilitation. Another treatment option for patients with severe emphysema is lung volume reduction surgery (LVRS). This surgery involves removing the less functional portions of the lung, often up to 20-25% of the lung volume, thereby reducing the overall size of the lung and leaving more volume within the chest cavity for the relatively healthy lung tissue to expand. The remaining lung tissue after LVRS has an enhanced capacity for efficient gas exchange due to the greater volume available for expansion.

[0205] There are also procedures that reduce lung volume without surgically removing diseased lung tissue. Examples include using coils or clips to grab and physically compact the diseased lung tissue. These procedures can reduce the overall volume of the lung, with effects similar to LVRS. Another device-based treatment for COPD involves placing one-way stent valves in the airways proximal to emphysematous tissue. These valves allow air to flow out but not in to the overinflated portions of the lung. While not conventionally used to treat COPD, stents are sometimes used in the lumens of central airways (e.g., trachea, main bronchus, lobar bronchus, and / or segmental bronchus) to temporarily improve patency of these airways. For example, stents can be used to temporarily improve patency in central airways affected by a benign or malignant obstruction.

[0206] Steam / vapor therapy, such as bronchoscopic thermal vapor ablation (BTVA), is yet another COPD treatment option. BTVA involves introducing heated water vapor into diseased lung tissue. This creates a thermal reaction, resulting in an initial local inflammatory response, followed by permanent fibrosis and atelectasis. Similar to thermal treatments like BTVA, there are also biochemical treatments that involve injecting a glue or sealant into diseased lung tissue. Both thermal and biochemical procedures can accelerate remodeling, resulting in a reduction of tissue and air volume at the targeted region of the overinflated lung.

[0207] Some other known COPD treatments involve bypassing obstructed airways. For example, a puncture through the chest wall into an outer portion of the lung can be used to create a direct communication (i.e., a bypass tract) between the diseased, alveoli, and the outside of the body. If no other steps are taken, these bypass tracts will typically close through normal healing or through the formation of granulation tissue. Thus, placing a tubular prosthesis in the bypass tract can temporarily extend the efficacy.

[0208] III. Endobronchial Implant

[0209] In some embodiments, the present technology provides for endobronchial placement of an implant to establish or improve airway patency (also referred to herein as "endobronchial implant therapy"). The implant can incorporate features designed to minimize or reduce foreign body reactions, such as minimal surface area coverage (or at least significantly reduced surface area coverage compared to other types of implants), open helical structure, and / or high contrast between outward radial force and flexibility along the longitudinal axis. Such endobronchial implants can also be referred to herein as minimal airway augmentation implants or minimal endobronchial augmentation implants. Minimal endobronchial augmentation implants can be advantageous compared to other types of endobronchial implants (e.g., valves, airway stents) whose therapeutic effectiveness can be compromised due to foreign body reactions (e.g., granulomatous reactions, mucus impaction, airway constriction).

[0210] The implant can be placed at a treatment site that includes a previously collapsed airway, such as a previously collapsed distal airway. Deployment of the implant can release air trapped in an overinflated portion of the lung and / or reduce or prevent subsequent air from being trapped in this portion of the lung. In at least some cases, the treatment site where the implant is deployed includes a generation 4 or higher / deeper airway, such as (from distal to proximal) respiratory bronchioles, terminal bronchioles, conducting bronchioles, bronchiolar or subsegmental bronchi, and then extending proximally to more central, larger airways (e.g., generation 6 or more proximal / deeper), such as (from distal to proximal) subsegmental bronchi, lobar bronchi, pulmonary bronchi, and main bronchi. A single implant can create a continuous path from distal to proximal to reliably create a passageway for trapped air. In alternative embodiments, multiple discrete implants can be used instead of a single longer implant. Multiple discrete implants can be placed in bronchial airways that have collapsed or are at risk of collapsing. Use of multiple discrete implants in select locations in the bronchial tree can have the advantage of using less material, reducing contact stress and foreign body reactions, and allowing greater flexibility and customization of treatment. For example, while a single implant embodiment can extend from a higher generation airway distally to a lower generation airway proximally, a system of multiple discrete implants can allow for placement of implants in multiple airways of the same generation.

[0211] The devices, systems, and methods described herein can be applied to different bronchopulmonary segments in order to release trapped air from regions of the lung in the safest and most effective manner possible. For example, treatment of the left lung can involve one or more of the following segments: upper lobe (upper segments: apical-posterior segment, anterior segment; lingual segments: superior segment, inferior segment); lower lobe: superior segment, anteromedial basal segment, lateral basal segment. Treatment of the right lung can involve one or more of the following segments: upper lobe: apical segment, anterior segment, posterior segment; middle lobe: medial segment, lateral segment; lower lobe: superior segment, anterobasal segment, lateral basal segment. Treatment described herein can involve placement of a single implant in a single lung (right or left), placement of a single implant in each lung, or placement of multiple implants in each lung. Treatment within a particular lung can involve placement of an implant in a particular lobe of the lung (e.g., the upper lobe) and a particular segment within this lobe, or it can involve placement of at least one implant in multiple lobes, segments within a lobe, or subsegments within a segment. A clinical operator (e.g., a pulmonologist or a surgeon) can determine which parts of the lung to treat, with the aid of imaging (e.g., CT, ultrasound, x-ray radiography, or bronchoscopy), to assess the presence and pathology of disease and its effect on lung function and airflow dynamics.

[0212] Figure 16 and 17 Examples of a minimally bronchoscopic enhanced implant configured for placement in an airway lumen of an expandable device 100 are described. In particular, Figure 16 is a side view of the expandable device 100 in an expanded, unconstrained state, and Figure 17 is an end view of the device 100. As Figure 16 shown in FIG. 1A, the device 100 can include a generally tubular structure configured to be positioned within an airway lumen. For example, the device 100 can be configured to be implanted in an airway lumen such that the device 100 maintains a minimum desired diameter lumen in the airway. The device 100 has a first end 100a, a second end 100b opposite the first end 100a, and a central longitudinal axis LI extending between the first and second ends 100a, 100b. As used herein, the term "longitudinal" can refer to a direction along an axis that extends through a lumen of the device in a tubular configuration, the term "circumferential" can refer to a direction along an axis that is orthogonal to the longitudinal axis and extends around a circumference of the device in a tubular configuration, and the term "radial" can refer to a direction along an axis that is orthogonal to the longitudinal axis and extends toward or away from the longitudinal axis.

[0213] The device 100 may include an elongated member 102 wrapped around a longitudinal axis L1 of the device 100. In some embodiments, the elongated member 102 is heat-set into a novel three-dimensional (3D) configuration such that the elongated member 102 is configured to self-expand to a predetermined configuration. In some embodiments, the elongated member 102 is not heat-set and / or configured to self-expand. For example, the elongated member 102 is balloon expandable. In some embodiments, the elongated member 102 is balloon expandable and self-expandable. The elongated member 102 has a first end 102a and a second end 102b opposite the first end 102a along the longitudinal axis L2 of the elongated member 102. The elongated member 102 may include a wire, a coil, a tube, a filament, a single interwoven filament, a plurality of braided filaments, a laser-cut sheet, a laser-cut tube, a thin film formed via a deposition process, and other suitable elongation structures and / or methods, such as cold working, bending, EDM, chemical etching, water jetting, etc. The elongated member 102 may be made of, for example, Nitinol, stainless steel, cobalt chromium alloy (e.g., 35N The elongated member 102 may be formed of a material such as MP35N (Fort Wayne Metals, Fort Wayne, Indiana), Elgiloy, a magnesium alloy, tungsten, tantalum, platinum, rhodium, palladium, gold, silver, or combinations thereof, or one or more polymers, or a combination of polymers and metals. In some embodiments, the elongated member 102 may comprise one or more drawn fill tube ("DFT") wires comprising an inner material surrounded by a different outer material. For example, the inner material may be a radiopaque material, and the outer material may be a superelastic material.

[0214] although Figure 16 The device 100 shown in FIG. 1 includes a single elongated member 102, but the device 100 may include any number of elongated members 102. A single elongated member (e.g., a single wire-expandable device) may be easier to remove and / or reposition because the operator can grasp one end of the elongated member and pull it through the working channel of the scope. The elongated member will straighten in either a balloon-expandable or self-expanding form.

[0215] refer to Figure 16 The elongated member 102 may be wound around the longitudinal axis L1 of the device 100 into a series of windings or loops 104, four of which are Figure 16The rings 104 are shown and individually labeled 104a-104d. Each of the rings 104 can extend around a longitudinal axis LI of the device 100 between a first end 106 and a second end 108. In some embodiments, the rings 104 are connected end-to-end such that, for example, the second end 108 of the first ring 104a is the first end 106 of the second ring 104b. The second end 108 can be disposed about 360 degrees from the first end 106 around the longitudinal axis LI of the device 100. That is, the first and second ends 106, 108 can be disposed at substantially equal circumferential positions relative to the longitudinal axis LI of the device 100. In some embodiments, the device 100 has a circular cross-sectional shape. In other embodiments, the device 100 can have other suitable cross-sectional shapes (e.g., oval, square, triangular, polygonal, irregular, etc.). The cross-sectional shape of the device 100 can be substantially the same or vary along the length of the device 100 and / or from ring to ring.

[0216] The expanded cross-sectional dimension of the device 100 can be substantially constant, or vary along the length of the device 100 and / or from ring to ring. For example, as discussed herein, the device 100 can have varying cross-sectional dimensions along its length to accommodate different portions of the airway. For example, the device 100 can have a first cross-sectional dimension along a first portion configured to be positioned in a more distal portion of the airway (e.g., such as in the terminal bronchioles and / or emphysematous regions that are destroyed and / or collapsed), and a second cross-sectional dimension along a second portion configured to be positioned more proximally (e.g., in a primary bronchus and / or another portion that is not collapsed). For example, the second portion can be configured to be positioned in a portion of the airway that is less emphysematous than the collapsed distal portion and / or has cartilage (preferably rings of cartilage rather than plates) in the airway wall, which can occur at the lobar (2ndgeneration) or segmental (3rdgeneration) level.

[0217] In some embodiments, the expanded cross-sectional dimension of the device 100 in an unconstrained (e.g., removed from constraint by a catheter or airway), expanded state is oversized relative to the diameter of the original airway lumen. For example, the expanded, unconstrained cross-sectional dimension of the device 100 can be at least 1.5X the initial (un-collapsed) diameter of the airway lumen in which it is intended to be positioned. In some embodiments, the device 100 has an expanded cross-sectional dimension that is about 1.5X to 6X, 2X to 5X, or 2X to 3X the diameter of the original airway lumen. Without being limited by theory, it is believed that expanding the airway lumen to the largest diameter possible without tearing the airway wall will provide the greatest improvement in lung function (e.g., as measured by flow out, FEV, etc.).

[0218] As Figure 16, as the elongated member 102 is wrapped about the longitudinal axis L1 of the device 100, the elongated member 102 may undulate along its longitudinal axis L2, forming a plurality of alternating peaks 110 (closer to the second end 100b of the device 100) and valleys 112 (closer to the first end 100a of the device 100). At least some of the valleys 112 may be located at different positions along the longitudinal axis L1 of the device 100 than at least some of the peaks 110. Additionally or alternatively, at least some of the valleys 112 may be located at different longitudinal positions than at least some other of the valleys 112, and / or at least some of the peaks 110 may be located at different longitudinal positions than at least some other of the peaks 110.

[0219] As an example, the three peaks 110 and four valleys 112 of the first ring 104a have been individually labeled as peaks 110a-110c and valleys 112a-d. Figure 16 and 17 , for a first loop 104a in a winding direction W, the elongate member 102 extends from a first end 106 of the elongate member 102 (which includes a first valley 112a of the first loop 104a) along a first longitudinal direction toward a second end 100b of the device 100. The elongate member 102 may then extend from the first peak 110a to a second valley 112b along a second longitudinal direction opposite the first longitudinal direction, from the second valley 112b to the second peak 110b along the first longitudinal direction, from the second peak 110b to a third valley 112c along the second longitudinal direction, from the third valley 112c to the third peak 110c along the first longitudinal direction, and from the third peak 110c to a fourth valley 112d (which is also the second end 108 of the first loop 104a) along the second longitudinal direction. Thus, when traveling in the winding direction W about a given loop 104, the loop 104 does not consistently advance from the first end 100a of the device 100 to the second end 100b of the device 100 (or vice versa), but rather undulates such that along certain portions of its length the loop 104 gradually becomes closer to the first end 100a of the device 100, and along other portions of its length the loop gradually becomes closer to the second end 100b of the device 100.

[0220] Although the first and second ends 106, 108 of one of the rings 104 may be generally circumferentially aligned, the first and second ends 106, 108 are longitudinally offset. The first peak 110a may be closer to the second end 100b of the device 100 than the first valley 112a. The second valley 112b may be closer to the first end 100a of the device 100 than the first peak 110a and / or the first valley 112a. The second peak 110b may be closer to the second end 100b of the device 100 than the second valley 112b, the first peak 110a, and / or the first valley 112a. The third valley 112c may be closer to the first end 100a of the device 100 than the second peak 110b and / or closer to the second end 100b of the device 100 than the first valley 112a and / or the second valley 112b. In some embodiments, the third valley 112c may be generally longitudinally aligned with the first peak 110a. The third peak 110c may be closer to the second end 100b of the device 100 than the third valley 112c, the second peak 110b, the second valley 112b, the first peak 110a, and / or the first valley 112a. The fourth valley 112d may be closer to the first end 100a of the device 100 than the third peak 110c and / or closer to the second end 100b of the device 100 than the third valley 112c, the second valley 112b, the first peak 110a, and / or the first valley 112a. In some embodiments, the fourth valley 112d may be substantially longitudinally aligned with the second peak 110b.

[0221] although Figure 16 and 17 The device 100 is shown as including four rings 104, each having four peaks 110 and four valleys 112, but in some embodiments, one or more of the rings 104 has more or fewer peaks 110 and / or more or fewer valleys 112. For example, in some embodiments, one or more of the rings 104 has one, two, three, four, five, six, seven, eight, etc. peaks 110 per ring 104 and one, two, three, four, five, six, seven, eight, etc. valleys 112 per ring 104. The rings 104 can have the same or different numbers of peaks 110, and the rings 104 can have the same or different numbers of valleys 112. In a given ring 104, the circumferential distance (e.g., angular separation) between adjacent ones of the peaks 110 and valleys 112 can be uniform or non-uniform. In some embodiments, adjacent ones of the peaks 110 and valleys 112 may be spaced apart by about 90 degrees, about 120 degrees, about 150 degrees, about 180 degrees, about 210 degrees, about 240 degrees, about 270 degrees, about 300 degrees, and / or about 330 degrees around the circumference of the device 100. Additionally, the amplitude of the peaks 110 may be the same or different along a given ring 104 and / or between rings 104, and the amplitude of the valleys 112 may be the same or different along a given ring 104 and / or between rings 104. Furthermore, the peaks 110 and valleys 112 may have the same or different amplitudes.

[0222] As shown in Figure 16 A portion of elongated member 102 between adjacent peaks 110 and valleys 112 can be linear, curved, or both. Two sets of adjacent portions of elongated member 102 between adjacent peaks 110 and valleys 112 can form V-shaped and / or U-shaped structures. At least some of valleys 112 can be concave toward second end 100b of device 100, and / or at least some of peaks 110 can be concave toward first end 100a of device 100.

[0223] In some embodiments, elongated member 102 can extend around the circumference of device 100 and / or along longitudinal axis LI of device 100 without extending substantially away from or toward longitudinal axis LI, as shown, for example, in Figure 18 Further, in some embodiments, device 200 can include elongated member 202 that undulates radially with respect to longitudinal axis LI of device 200. As shown, for example, in Figure 16 elongated member 202 can form peaks 204 and / or valleys 204 that are located closer to longitudinal axis LI than the intermediate portions of elongated member 202 between peaks 204 and valleys 204. The apex of each “V” can be curved radially inward toward the center of the lumen, such that only the longitudinally extending portions of elongated member 202 contact the bronchial wall. This configuration can prevent the stent from obstructing the flow of mucus along the wall of the bronchus.

[0224] The radial expansion mechanism allows for easy design and delivery of expandable devices 200 by both self-expansion and balloon expansion. The zig-zag pattern of the devices disclosed herein, including the example shown in Methods for Patient Selection, Treatment Planning, and Monitoring is configured to conform to airways of different diameters by a single design, while conventional coils are fixed diameter. This is particularly advantageous for achieving gradual airway enlargement over time. The expandable devices store expansion potential in the implant design, which is realized via the curved beams, and establishes elastic potential. When the geometry is designed in this way, the expandable devices in balloon-expandable form also have the unique potential to form coils by expanding the zig-zags all the way to straight lines.

[0225] In some embodiments, the devices described herein include at least one material configured to facilitate visualization, such as a radiopaque material. The material can be the same material used to form the device, or can be incorporated into the device via doping, coating, attachment of a separate component (e.g., a radiopaque marker) into the material, or the like.

[0226] Additional examples of devices suitable for use in the present technology are described in International Application No. PCT / US2022 / 073962, the entire disclosure of which is incorporated herein by reference.

[0227] IV. Figure 19

[0228] Figure 19 19 is a block diagram that provides a general overview of a workflow 1900 for selecting a patient for treatment and planning and monitoring the course of treatment according to an embodiment of the present technology. For example, the course of treatment may be a process of treating a patient with a lung disease (e.g., COPD) by placing one or more implantable devices into one or both lungs of the patient. The device may be any embodiment of the endobronchial implant described herein, such as a minimal endobronchial augmentation implant.

[0229] like Figure 19 , workflow 1900 can be divided into a preoperative stage 1902, a perioperative stage 1904, and a postoperative stage 1906. In some embodiments, preoperative stage 1902 occurs before the patient has been diagnosed with a lung disease. Alternatively, preoperative stage 1902 can occur after the patient has been diagnosed with a lung disease, but before the patient has received treatment for the lung disease (e.g., endobronchial implant therapy and / or other treatments).

[0230] The preoperative stage 1902 may involve determining whether the patient is a candidate for treatment of a lung disease (block 1908). For example, the treatment may be or include airway treatment for COPD. Airway treatment may include medication (e.g., bronchodilators), interventional therapy (e.g., implantable and / or non-implantable procedures), or a combination thereof. In some embodiments, interventional therapy includes vapor therapy (e.g., BTVA), application of sealants, transbronchial fenestration (e.g., airway bypass stent), and / or endobronchial implant therapy (e.g., placement of an endobronchial coil, placement of an endobronchial valve, and / or placement of a minimal endobronchial augmentation implant).

[0231] The process of block 1908 (also referred to herein as "patient selection") may involve analyzing patient data (e.g., CT data and / or other image data, medical records, questionnaires, other diagnostics) to assess the patient's current status. For example, the patient selection process may determine whether the patient has or is at risk for developing a lung disease, and optionally determine a disease profile (e.g., type, location, severity). Optionally, patient data obtained over time may be used to track disease progression. The patient selection process may also involve assessing whether the patient is a good candidate for a particular treatment for the lung disease, e.g., the predicted likelihood of achieving a successful treatment outcome with the treatment.

[0232] In some embodiments, the patient selection process involves analyzing patient data and predicting the degree of response based on factors such as homogeneity / heterogeneity of emphysema and / or collateral ventilation, location of diseased portions (e.g., tissue destruction, air trapping), proximity to anatomical structures (e.g., pleura, heart, nodules), proximity to other medical devices, proper bronchial pathway to target, alveolar collapse, diaphragm movement (where air flows in response to breathing and / or flow patterns), and / or calculated measures of lung volume and / or health (e.g., RV, TLC, RV / TLC ratio). Optionally, the patient selection process can involve screening patient data for exclusion characteristics, such as tumors, lesions, giant bullae, central airway collapse, etc.

[0233] In some embodiments, the patient selection process involves predicting patient outcomes by comparing a patient's disease profile to aggregated normalized data of other patients. This method can be used to predict how a patient's quality of life can decline over time (e.g., create a trend line) compared to bronchial implant treatment with minimal endobronchial augmentation implants, and / or how a patient can respond to different treatments (e.g., medication; interventions such as valves, coils, steam, hydrogel, thermal ablation, non-thermal ablation; surgery).

[0234] In some embodiments, the patient selection process of block 1908 is implemented at least in part by a patient engagement utility. The patient engagement utility can be a software module that administers automated questionnaires related to symptoms and / or quality of life measures. Based on the patient's answers, the patient engagement utility can order imaging (e.g., CT, X-ray, magnetic resonance imaging (MRI), single photon emission computed tomography (SPECT), bronchoscopy) and / or testing (spirometry, arterial blood gas). Based on the image data and / or test results, the patient engagement utility can generate an interactive patient report that provides a COPD "risk" assessment (e.g., X% likelihood that the patient has COPD) and a referral to a pulmonologist. Based on the patient's provisional disease profile, the patient report can also include information about available treatments and predictions of potential efficacy. For example, the patient report can provide layperson-understandable, personalized, evidence-based recommendations (e.g., if the patient receives treatment, their quality of life can be restored by X%, they will be able to walk two flights of stairs instead of one flight of stairs), which can facilitate patient-driven market development.

[0235] Optionally, patient engagement with the utility program can send referral cases to pulmonologists along with detailed physician reports with data, analysis, and risk assessment generated for the patient. The physician report can include preliminary diagnosis, recommendations for additional and / or confirmatory testing, and / or predictive analysis related to disease progression, responsiveness to medical and / or pharmacological treatment, interventional treatment, surgery, etc. Optionally, the physician report can also include referral to an interventionalist if appropriate.

[0236] If the patient is determined to be a good candidate for treatment, the preoperative stage 1902 can generate a plan for the patient's course of treatment (block 1910). The process of block 1910 (also referred to herein as a "procedure plan") can involve determining parameters for the treatment plan. For example, parameters for endobronchial implant treatment (e.g., using minimal endobronchial augmentation implants) can include the number of implants, implant size (e.g., length, outer diameter), implant geometry, other implant characteristics (e.g., flexibility, material, design features), placement location (e.g., which airway(s), lung segment, subsegment, lung lobe, etc. to place the implant in), placement path, and / or other treatment solutions (e.g., drugs, surgery, other medical devices) that can be used in combination with endobronchial implant treatment. The selection of implant configuration can be based on factors such as the outer diameter, wall thickness, lumen inner diameter, proximity to anatomical structures, and / or airway generation of the target airway. The treatment plan can also include information such as the airway in which to place the implant, how to predict the area of the lung to which the implant will supply air, airway wall structure and size, how to predict airway wall structure and size to interface with the implant, proximity to structures, airway mechanical strength (e.g., radius, wall thickness), and / or tissue type (e.g., fat, muscle, connective tissue - which can imply implant characteristics). In some embodiments, the procedure planning process is part of a software tool used by the interventionalist.

[0237] In some embodiments, the procedure planning process involves modeling the patient's lung, for example, before and after implant placement. For example, a 3D model of the bronchial tree can optionally be generated from CT data and / or other image data. In some embodiments, the CT data can identify the most diseased lung lobe (and / or lung segment, subsegment, etc.) and help identify incomplete lung fissures, but can be limited in identifying the exact airways most impacted due to resolution, and thus can be combined with higher resolution imaging modalities such as MRI to allow assessment of specific airways. Furthermore, it can not be necessary to determine precise airway targets, as any open airway that creates a connected shortcut with integrity from a peripheral airway to a proximal airway can be sufficient to release trapped air, especially if collateral ventilation further facilitates air movement through the parenchyma.

[0238] The 3D models can be used to model various treatment options and associated outcomes (e.g., placement of a valve at a target location produces X% increase in FEVi, while placement of a minimally bronchial endoluminal augmentation implant produces Y% increase in FEVi). The modeling results can be used to select an appropriate treatment type, target locations (e.g., target airways, lung segments, and / or lung lobes) for implant placement, and / or sequence of target locations. Modeling techniques (e.g., computational fluid dynamics, AI-based methods) can also be used to identify optimal target airways and / or predict optimal implant plans based on factors such as predicted effectiveness of removing trapped air, zones with trapped air, presence or proximity of incomplete lung fissures, safety from iatrogenic damage (e.g., to pleura, blood vessels, organs), safety from implant fatigue, safety and effectiveness from risk of friction with adjacent implants, minimizing number of implants (e.g., for safety purposes, ease of use, reducing procedure time), minimizing amount of foreign bodies (e.g., for safety purposes), minimizing number of bends, minimizing risk of implant rejection or migration (e.g., due to coughing), and / or minimizing procedure time. Modeling can also be used to predict how the lung can perform in bronchial endoluminal implant treatment. For example, modeling can be used to predict which lung segments will have reduced air trapping and thus contribute less to residual volume, and / or which lung segments can contribute more to improved lung function, compared to baseline (e.g., pre-treatment) measurements. Lung segments with less disease and proximal or adjacent to lung segments with large air trapping are expected to be able to expand significantly compared to baseline, and thus can contribute most to improved lung function. Additionally, modeling can be used to predict risk of pneumothorax. Analysis of inspiratory and expiratory CT can be able to detect presence and location of adhesions that are at risk of tearing from the pleural wall after treatment. This perforation and pneumothorax risk analysis associated with predictive modeling can inform location and sequence of treatment.

[0239] The perioperative phase 1904 can occur during a treatment procedure, immediately before the procedure (e.g., when preparing for the procedure), and / or immediately after the procedure (e.g., when assessing immediate results of the procedure). The perioperative phase 1904 can involve using data generated during the preoperative phase 1902 to assist an interventional therapist in performing a treatment procedure. For example, a 3D model of patient anatomy generated during the preoperative phase 1902 can be integrated with perioperative visualization (e.g., fluoroscopy, bronchoscopy) and navigation techniques (e.g., robotic navigation and delivery systems) to enhance delivery and calibration of bronchial endoluminal implants into proper locations in the lung.

[0240] In some embodiments, the perioperative phase 1904 involves modifying and / or reinforcing the treatment plan during the procedure by assessing the results of previous steps in the plan and providing recommendations for subsequent steps. For example, real-time data characterizing the patient’s response to previously placed implants can be used to demonstrate the success of the procedure, assess whether the procedure should continue as planned, and / or determine whether modifications should be made (e.g., repositioning of implants, removal of implants, placement of additional implants, administration of other therapies). Real-time data can include, for example, image data, AI analysis, physician input, pressure and / or flow measurements, physiological metrics (e.g., O2 saturation, respiratory metrics), etc. Optionally, real-time data can be generated by the ventilator or other device that checks for correlations between data (e.g., O2 saturation and airflow), and uses such data as a measure of success. This approach can improve efficacy and reduce procedure time.

[0241] The postoperative phase 1906 can occur after the treatment procedure, e.g., at least 24 hours, 48 hours, 1 week, 2 weeks, 3 weeks, 4 weeks, 1 month, 2 months, 3 months, 6 months, or 1 year after the procedure. In some embodiments, the postoperative phase 1906 involves assessing the patient’s treatment outcome at one or more time points after the procedure (e.g., at a single time point after treatment, or repeatedly, e.g., periodically or intermittently, after treatment) (block 1912). The process of block 1912 (also referred to herein as “outcome assessment”) can involve analyzing patient data (e.g., CT data and / or other image data, medical records, questionnaires, other diagnostics) to assess the patient’s response to the treatment, e.g., whether the patient’s condition is improving, stable, or worsening over time. For example, postoperative lung function metrics can be compared to preoperative lung function metrics, e.g., airway patency, lung / lung lobe / lung segment volumes in inspiration and expiration, RV, TLC, RV / TLC ratio, flow through the target airway, and / or flow through adjacent airways. Optionally, the status of the patient’s lungs can be assessed by determining a set of lung metrics from patient data (e.g., CT data of the lungs), and then comparing the set of lung metrics to a second set of lung metrics determined from other types of data, e.g., image data of the same lungs before treatment (e.g., baseline CT images obtained before placement of the endobronchial implant), image data of the same lungs at an earlier time point after treatment (e.g., comparison of 6-month follow-up and 12-month follow-up CT images after placement of the endobronchial implant), image data of the same lungs after placement of another endobronchial implant at a different location than the current endobronchial implant, and / or a database of lung images of patients with COPD. The outcome assessment process can also involve assessing the status of the endobronchial implant over time, e.g., whether the implant is still positioned at the target location and functioning as intended, whether the implant has migrated, whether the implant has collapsed or otherwise failed, etc.

[0242] In some embodiments, the process of block 1912 can include transforming some or all of the patient data into a "virtual bronchoscopy" with which a user can interact. For example, a 3D model of the lung, including the airways and the implanted implants, can be reconstructed from post-operative imaging of the lung, e.g., follow-up CT imaging. In some embodiments, developing the virtual bronchoscopy can include obtaining CT slice images of at least a portion of the lung in which an endobronchial implant is placed, reconstructing a 3D model of the lung based on the CT slice images, and segmenting the 3D model to distinguish various structures in the lung, including cardio-pulmonary structures (e.g., 3D airway structures and / or pulmonary vasculature) and the placed endobronchial implant. Additionally or alternatively, the CT slice images can be segmented to distinguish structures in the lung prior to 3D model construction. For example, such segmentation can be based at least in part on density differences between different cardio-pulmonary features and the endobronchial implant itself, as represented as different voxel densities in the CT images.

[0243] The 3D model can be displayed on a suitable display (e.g., on a computing device) and / or can be navigated by a user in a virtual bronchoscopy interaction. For example, the 3D model can be displayed on a monitor and / or a wearable device (e.g., glasses, a headset, goggles, etc.). In some embodiments, the 3D model can additionally or alternatively be displayed in an augmented reality (AR) and / or virtual reality (VR) environment. Suitable user interface devices (e.g., a mouse, a joystick, a handheld controller, a button, a scroll wheel or ball, etc.) can be utilized to navigate the 3D model.

[0244] In some embodiments, the display of the 3D model can include highlighting or other emphasis of one or more implant features. For example, an implant can be visually indicated with an outline of the implant itself (e.g., a colored line or thicker line). As another example, one or more individual implant features can additionally or alternatively be visually indicated with markers associated with the relevant implant feature (e.g., markers corresponding to the proximal and distal ends of an endobronchial implant, an outline of a cross-sectional profile of an endobronchial implant at one or more locations along an airway in which the endobronchial implant is placed). In some embodiments, the implant outline and / or markers associated with individual implant features can be toggled on and / or off for display, e.g., to enable clearer visualization of certain features in the 3D model.

[0245] Virtual bronchoscopy can provide more detailed information about the lung, airways, and / or implants than can be visually observed during non-virtual bronchoscopy or existing virtual bronchoscopy techniques. For example, in many instances, placed implants can be configured to blend into the contours of the airway and minimize the induction of a foreign body reaction, thus the implants can not be readily visible on the tissue surface during non-virtual bronchoscopy. In contrast, as described above, virtual bronchoscopy according to the present technology that allows navigation of a reconstructed 3D model of the lung, airways, and / or placed implants can allow visualization and investigation of the airways, placed implants, implant-airway tissue interactions, and the entire lung, even beyond the surface of the airway. In particular, visualization of placed implants relative to their surroundings can aid in assessing treatment outcomes for post-operative patients. In some embodiments, assessment of treatment outcomes using virtual bronchoscopy can be performed manually (e.g., by a user operating and navigating the virtual bronchoscopy) and / or with software algorithms (e.g., trained machine learning algorithms, such as those described herein).

[0246] In some embodiments, the outcome assessment process of block 1912 involves predicting future outcomes for the patient, such as predicted disease progression, treatment efficacy, implant status, etc. For example, the outcome assessment process can predict whether any post-operative problems are likely to arise, such as physiological problems (e.g., excess mucus, granulation tissue, and / or fibrosis) as well as implant problems (e.g., collapse, migration, and / or other failure). If any problems are predicted to arise, then the post-operative stage 1906 can generate a recommendation for an intervention to prevent, mitigate, or otherwise address such problems (block 1914). The process of block 1914, also referred to herein as an “intervention recommendation,” can generate a recommendation for an additional treatment procedure, such as a cleanout bronchoscopy, implant removal, implant replacement, placement of additional implants, consultation with a healthcare professional, etc.

[0247] In some embodiments, patient data is collected during the post-operative stage 1906 using home-use devices, such as home spirometers and / or wearable devices (e.g., smart watches with sensors for blood oxygen level, heart rate, activity (e.g., steps), altitude, location, and / or sleep; wearable stethoscopes that analyze lung sounds to detect early signs of disease exacerbation). Data generated from such devices can be used to track the patient over an extended period of time (e.g., weeks, months), and can allow for remote monitoring, reducing the frequency of office visits. Optionally, if the data indicates that there is a potential health problem (e.g., the patient’s condition suddenly worsens), the patient can be instructed to come in for a follow-up visit.

[0248] Figure 20Any of the processes (e.g., patient selection processes, surgical planning processes, outcome assessment processes, and / or intervention recommendation processes) described herein can be performed using one or more software algorithms (e.g., rule-based algorithms, machine learning algorithms, or a combination thereof). Examples of machine learning algorithms that can be used include: regression algorithms (e.g., ordinary least squares regression, linear regression, logistic regression, stepwise regression, multivariate adaptive regression splines, locally estimated scatterplot smoothing), example-based algorithms (e.g., k-nearest neighbors, learning vector quantization, self-organizing maps, locally weighted learning), regularization algorithms (e.g., ridge regression, least absolute shrinkage and selection operator, elastic net, least-angle regression), decision tree algorithms (e.g., iterative dichotomiser 3 (ID3), C4.5, C5.0, classification and regression tree, chi-squared automatic interaction detection, decision stump, M5), Bayesian algorithms (e.g., Naive Bayes, Gaussian Naive Bayes, Multinomial Naive Bayes, Average One-Dependence Estimator, Bayesian Belief Network, Bayesian Network, Hidden Markov Model, Conditional Random Fields), clustering algorithms (e.g., k-means, single-linkage clustering, k-medians, expectation maximization, hierarchical clustering, fuzzy clustering, density-based spatial clustering of applications with noise (DBSCAN), order-based points to identify clustering structure (OPTICS), non-negative matrix factorization (NMF), Latent Dirichlet Allocation (LDA), Gaussian Mixture Model (GMM)), association rule learning algorithms (e.g., a priori algorithm, Equivalence Class Transformation (Eclat) algorithm, frequent pattern (FP)-growth), artificial neural network algorithms (e.g., perceptron, neural network, backpropagation, Hopfield network, autoencoder, Boltzmann machine, restricted Boltzmann machine, spiking neural network, radial basis function network), deep learning algorithms (e.g., deep Boltzmann machine, deep belief network, convolutional neural network, stacked autoencoder), dimensionality reduction algorithms (e.g., principal component analysis (PCA), independent component analysis (ICA), principal component regression (PCR), partial least squares regression (PLSR), Sammon mapping, multidimensional scaling, projection pursuit, linear discriminant analysis, hybrid discriminant analysis, quadratic discriminant analysis, flexible discriminant analysis), ensemble algorithms (e.g., boosting, bootstrapped aggregation, AdaBoost, bagging, gradient boosting machine, gradient boosting regression trees, random forest), or suitable combinations thereof. The machine learning algorithms described herein can be trained using any suitable technique, including supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, or suitable combinations thereof.

[0249] In some embodiments, the software algorithms described herein include at least one computer vision algorithm, which can or can not be a machine learning algorithm (e.g., a deep learning algorithm, such as a convolutional neural network). The computer vision algorithm can receive image data as input, and can produce output data characterizing one or more objects present in the image data. For example, the computer vision algorithm can receive CT data of one or both lungs of a patient, and can identify objects in the lungs, such as anatomical structures, healthy tissue, diseased tissue, implanted devices (e.g., endobronchial implants), etc.

[0250] Figure 19 is a flowchart illustrating a method 2000 for planning treatment of a patient according to embodiments of the present technology. The method 2000 can be performed as part of the preoperative phase 1902 of the workflow 1900 of Figure 20 The method 2000 can involve receiving patient data, such as questionnaire information, medical record information, image data, pulmonary function test (PFT) data, and / or data from other diagnostic techniques. The method 2000 can implement one or more software algorithms that use the patient data to determine whether the patient is a candidate for endobronchial implant treatment (and / or other treatments for lung disease), and optionally assist in planning such treatment.

[0251] The questionnaire information can include the patient’s responses to one or more questionnaires, which can be administered by the patient engagement utility as described above. The medical record information can include information from the patient’s electronic health record, such as the patient’s name, date of birth, demographic information, height, weight, medical history, family medication history, symptoms, comorbidities, diagnoses, medications, test results, prior treatments and outcomes, etc. The questionnaire information and / or medical record information can provide any of the following information: whether the patient coughs, whether the patient is a smoker, whether the patient finds it difficult to breathe, whether the patient is able to take deep breaths, whether the patient is able to perform typical activities (e.g., walk, shower), whether the patient is worsening, whether the patient has a lot of mucus, whether the patient has a lung infection, and / or the patient’s current and / or past dosing regimen.

[0252] The image data can include data produced by any suitable imaging modality, such as CT, X-ray (e.g., chest radiography, fluoroscopy), MRI (e.g., 3 He MRI, 129Xe MRI), SPECT, bronchoscopy, ultrasound, ventilation perfusion scan data, photographs (e.g., from multiple external cameras to map the surface topography of the chest), etc. For example, CT data can include inhale CT data (e.g., obtained at the end of full inhalation) and / or exhale CT data (e.g., obtained at the end of forced exhalation). In some embodiments, image data can be generated after administration of a contrast agent to the patient (e.g., via intrapleural injection, inhalation, etc.), where the contrast agent can help provide contrast enhancement in CT imaging. For example, for lung CT, suitable contrast agents include iodinated compounds (e.g., derivatives of diatrizoic acid), barium, radiolabeled albumin to track blood flow in the lungs, and labeled gas (e.g., Xenon-133) for tracking ventilation in the lungs. CT data can include a series of 2D cross-sectional images of the patient’s anatomy, where each image has a specified slice thickness and is spaced apart by a particular slice interval (e.g., 10 mm intervals). For example, the 2D cross-sectional images can have a slice thickness of at least 3 mm (e.g., in a range from 3 mm to 10 mm), or can have a slice thickness of less than 3 mm (e.g., in a range from 1 mm to 2 mm (e.g., 1 mm)). In some embodiments, the 2D cross-sectional images can be combined to generate a 3D volumetric CT model of the imaged lung tissue.

[0253] PFT data can include any data characterizing the function of the patient’s lungs, such as spirometry data, plethysmography data, exercise test results (e.g., 6-minute walk distance test), etc. PFT data can include measured values for any of the following: tidal volume, minute ventilation, VC, functional residual capacity, residual volume (RV), total lung capacity (TLC), RV / TLC ratio, forced vital capacity (FVC), forced expiratory volume (FEV) (e.g., FEV in one second (FEV1)), forced expiratory flow, peak expiratory flow, closing volume (CV), inspiratory capacity (IC), IC / TLC ratio, and / or carbon monoxide diffusing capacity.

[0254] Other data from other diagnostic techniques can include data from one or more sensors configured to monitor the status of the patient, which can include implanted sensors, non-invasive sensors, wearable sensors, or suitable combinations thereof. Examples of suitable sensors for use in the present techniques include, but are not limited to, impedance sensors, pressure sensors, flow sensors, and wearable stethoscopes. As another example, bronchoscopy can be used to automatically collect information at specific locations in the lungs, such as information about flow, pressure, granulation tissue, fibrosis, mucus, epithelization, and / or obstruction.

[0255] Any of the patient data types described herein can be obtained at multiple points in time, e.g., two, three, four, five, 10, 20, 50, or more points in time. For example, patient data can be obtained at multiple points in time spanning multiple seconds, minutes, hours, days, weeks, months, and / or years. In some embodiments, patient data is obtained at two or more of the following points in time: before treatment (e.g., before placement of an endobronchial implant, before administration of a bronchodilator), after treatment (e.g., after placement of an endobronchial implant, after administration of a bronchodilator), before exercise, during exercise, after exercise, and / or during different phases of a breathing cycle (e.g., inhalation, exhalation). However, in other embodiments, some or all of the patient data can be obtained at a single point in time.

[0256] As Figure 27As shown in FIG. 1, patient data can be provided to a first software algorithm. The first software algorithm can be a first machine learning algorithm that has been trained (e.g., via supervised learning) to synthesize the patient data to calculate metrics that characterize lung properties and / or the disease state of the patient. In some embodiments, the first software algorithm can additionally or alternatively include other suitable automated processes. The output of the first software algorithm can be a set of lung metrics that represent the state of one or both lungs of the patient. For example, the lung metrics can characterize any of the following lung parameters: FEV (e.g., FEVi), FVC, VC, IC, IC / TLC ratio, functional residual capacity, TLC, carbon monoxide diffusing capacity, RV, RV / TLC ratio, CV, lung lobe and / or segment tissue destruction, lung lobe and / or segment air trapping, lung lobe and / or segment fissure status, lung lobe and / or segment fissure completeness, lung lobe and / or segment ventilation, lung function (e.g., zone assessment), disease phenotype (e.g., homogeneity / heterogeneity of lobar and / or segment emphysema, type of emphysema (e.g., acinar centric emphysema, panacinar emphysema, or paraseptal emphysema), location of diseased portion of lung), lung lobe volume, lung segment volume, lung segment location, septal shape, tissue density, opacity, proximity of diseased portion to anatomical structures (e.g., pleura, heart, nodule), proximity of diseased portion to other medical devices, bronchial slice lumen diameter, airflow mapping, collapsed airways, airway pressure, airway compliance, pleural pressure, airway diameter and wall thickness, airway wall deformation, blood vessel perfusion, parenchymal density, lung bullae, information localizing disease in the lung (e.g., at the segment and / or subsegment level), obstruction score, mucus score, and / or degree of epithelization. The lung metrics can characterize any of the above lung parameters at a single point in time and / or can characterize changes in any of the above lung parameters over multiple points in time (e.g., before bronchial endoluminal implant treatment, after bronchial endoluminal implant treatment, before bronchial dilator administration, after bronchial dilator administration, before or during exercise). The lung metrics can be correlated with whether the patient has a lung disease, such as COPD. Optionally, the lung metrics can be used to generate a risk assessment for a lung disease (e.g., a percentage likelihood that the patient has COPD).

[0257] Additionally or alternatively, the lung metrics can be used to generate a disease "score" that characterizes the severity of the lung disease and / or represents a predictor of the patient's response to treatment for the lung disease. For example, the disease score can represent the extent of emphysematous destruction, the extent of overinflation, and / or the extent of air trapping in one or more regions of the lung. In some embodiments, the lung metrics can include one or more disease scores, with each disease score corresponding to a respective region of the lung (e.g., a particular lung, a particular lobe, a particular segment, a particular subsegment). In some embodiments, the lung metrics can include a single disease score that is based at least in part on a plurality of "local" disease scores, each corresponding to a respective region of the lung (e.g., a particular lung, a particular lobe, a particular segment, a particular subsegment). For example, the single disease score can be an average of the plurality of local disease scores, or any suitable calculation based on the plurality of local disease scores. Figure 23A is a flowchart illustrating a method 2700 for assessing a patient using such a disease score lung metric, including receiving patient data including CT data of a lung of the patient (block 2710), and generating a lung disease score for a region of interest of the lung by inputting the patient data into a machine learning algorithm (block 2720).

[0258] In some embodiments, as described above, the lung metrics generated by the first software algorithm can include a disease phenotype. For example, the distribution of disease scores can be used to characterize the homogeneity or heterogeneity of emphysema. In some embodiments, for example, a difference in disease scores in a contralateral lung region (e.g., in different lobes, segments, and / or subsegments in a particular lung) that is below a threshold difference value can correspond to a characterization of homogenous emphysema of the lung, while a difference in disease scores in a contralateral lung region (e.g., in different lobes, segments, and / or subsegments in a particular lung) that is above a threshold difference value can correspond to a characterization of heterogeneous emphysema of the lung. In some embodiments, the threshold difference value for characterizing emphysema homogeneity / heterogeneity can be in a range from about 10% to about 25%, from about 10% to about 20%, or from about 10% to about 15%. Additionally or alternatively, in some embodiments, the distribution of disease scores across a lung or lung region (e.g., across different lobes and / or different segments and / or different subsegments) can be used to determine the type of emphysema. In particular, such lung metrics regarding emphysematous tissue destruction at the segment and / or subsegment level can advantageously provide more insight into the patient's disease and lung anatomy at a finer level than analysis performed only at the lobar level.

[0259] Additionally or alternatively, in some embodiments as described above, the lung metrics generated by the first software algorithm can include a characterization of lobar and / or segmental fissure status and / or completeness, and / or lobar and / or segmental collateral ventilation. In particular, such lung metrics regarding lung fissure status, lung fissure completeness, and / or ventilation at the segment level can advantageously provide more insight into the patient's disease and lung anatomy at a finer level than analysis performed only at the lobar level.

[0260] In some embodiments, the lung metrics generated by the first software algorithm can be based at least in part on patterns of voxel density from one or more 3D models of patient tissue generated from inspiratory and / or expiratory CT scans. Generally, voxel density is directly proportional to the attenuation of an X-ray beam by tissue, which generally corresponds to the physical density of the tissue and other substances (e.g., air) being imaged. Voxel density can be expressed in Hounsfield Units (HU), which indicate the amount of X-ray attenuation occurring in the tissue corresponding to a particular voxel along the Hounsfield scale. In some embodiments, the first software algorithm can include evaluating voxel density across one or more lung regions relative to one or more voxel density thresholds to characterize emphysema occurring at the lobar and / or segmental level, air trapping at the lobar and / or segmental level, lobar and / or segmental lung volume, perfusion volume at the lobar and / or segmental level, and / or airway size (e.g., intraluminal diameter of the segmental airway along the length of the airway pathway, airway wall thickness, etc.). The first software algorithm can incorporate different voxel density thresholds associated with different types of CT scans and / or different lung metrics. In some embodiments, the first software algorithm can output lung metrics based on analysis of both inspiratory and expiratory CT scans. In some embodiments, the first software algorithm can output lung metrics based on expiratory CT scans but not inspiratory CT scans. In some embodiments, the first software algorithm can output lung metrics based on inspiratory CT scans but not expiratory CT scans. Additionally or alternatively, the first software algorithm can include other suitable quantitative CT (QCT) techniques, such as those described in further detail herein.

[0261] For example, as shown in Figure 23B The first software algorithm can incorporate one or more voxel density thresholds associated with inspiratory CT scans. In some embodiments where the CT images from inspiratory CT scans have a slice thickness of about 3 mm or greater (e.g., between 3 mm and 10 mm), emphysema can be quantified or otherwise characterized by assessing lung voxels on the inspiratory CT scans having an attenuation below -910 HU (e.g., the percentage of lung voxels below this threshold, the integral of density values for all voxels below this threshold, and / or other density-based calculations). Quantification of emphysema can characterize the emphysema disease state at the lobar level (2ndgeneration) and / or the segmental level (3rdgeneration) and / or the subsegmental level (4+thgeneration). Additionally or alternatively, this -910 HU threshold can be used to characterize lobar lung volume and / or segmental lung volume. As described in further detail below, such lung metrics can be analyzed by additional software algorithms to predict optimized treatment for particular lobes and / or segments of the lung.

[0262] As shown in Figure 23BAs further shown in FIG, in some embodiments where the CT image from the inspiratory CT scan has a slice thickness of less than 3 mm (e.g., 1 mm), emphysema can be quantified or otherwise characterized by assessing lung voxels on the inspiratory CT scan with an attenuation below -950 HU (e.g., the percentage of lung voxels below this threshold, the integration of the density values ​​of all voxels below this threshold, and / or other density-based calculations). Quantification of emphysema can characterize emphysematous disease states at the lobar and / or segmental levels. Additionally or alternatively, this -950 HU threshold can be used to characterize lobar and / or segmental lung volumes, and / or perfusion deficits at the lobar and / or segmental levels.

[0263] As another example, Figure 20 As shown in FIG, a first software algorithm may incorporate one or more voxel density thresholds associated with an expiratory CT scan. In some embodiments, air trapping may be quantified or otherwise characterized by assessing lung voxels on the expiratory CT scan with an attenuation below -856 HU (e.g., the percentage of lung voxels below this threshold, the integral of the density values ​​of all voxels below this threshold, and / or other density-based calculations). Additionally or alternatively, in some embodiments, the first software algorithm may include generating lung metrics characterizing one or more lung anatomical features (e.g., measurements of the airways within the lungs) from image data from the expiratory CT scan. For example, the first software algorithm may generate lung metrics from the expiratory CT scan that include geometric, physical, and / or mechanical properties of the airways, such as airway compliance, pleural pressure, airway diameter and wall thickness, and / or airway wall deformation. Such properties may be measured, in particular, at the segmental level, which (compared to such information determined only at the lobar level) may provide greater insight into the patient's condition for use in determining the patient's treatment candidacy, treatment plan, and the like. Additionally or alternatively, the first software algorithm may generate lung metrics from the expiratory CT scan, including characterization of lobar and / or segmental lung volumes, and / or identification of collapsed airways (and the severity of their collapse, such as airway diameter) that may facilitate disease states (e.g., hyperinflation and respiratory compromise).

[0264] It should be understood that the density thresholds described above for analyzing CT scans are merely examples, and other suitable thresholds may be used in addition or alternatively to evaluate voxel density data and generate suitable lung metrics. For example, the density threshold for an inspiratory CT scan may be a value ranging from -910 HU to -990 HU, or ranging from -950 HU to -990 HU, or ranging from -970 HU to -990 HU (e.g., -950 HU, -960 HU, -970 HU, -980 HU, or -990 HU).

[0265] The lung metrics generated by the first software algorithm can be provided to a second software algorithm. The second software algorithm can be a second machine learning algorithm that has been trained (e.g., via supervised learning) to analyze the lung metrics to determine whether the patient is a candidate for one or more treatments for lung disease. In some embodiments, the second software algorithm can additionally or alternatively include other suitable automated processes. For example, if the patient receives a treatment, the output of the second software algorithm can be a likelihood of success. The treatment can be an airway treatment for COPD, such as a pharmacological treatment (e.g., a bronchodilator), an interventional treatment (e.g., vapor therapy, administration of a sealant, transbronchial fenestration, placement of an endobronchial coil, placement of an endobronchial valve, or placement of a minimal endobronchial augmentation implant), or a combination thereof.

[0266] In some embodiments, the output of the second software algorithm is a predicted response of the patient to a treatment. The predicted response can include a prediction of any of the following: FEV (e.g., FEVi), FVC, VC, IC, IC / TLC, functional residual capacity, TLC, carbon monoxide diffusing capacity, RV / TLC, RV, lung segment volume, mMRC score, SGRQ score (or score of a subset of SGRQ questions), CAT score (or score of a subset of CAT questions), 6-minute walk test result, cycle ergometry result, cardiopulmonary exercise test (CPET) result, patient health metric (e.g., heart rate, blood pressure, body mass index), patient exercise metric (e.g., number of steps taken), patient visit metric, quality of life metric (e.g., breathlessness), number of implant removals required, time to re-intervention, treatment durability, comorbidities, dosing regimen, length of hospital stay, healthcare utilization, and / or cost; and / or a change (e.g., increase or decrease) in any of the above. Optionally, the predicted response can include a comparison of the response to endobronchial implant therapy with a minimal endobronchial augmentation implant to other treatment processes (e.g., pharmacological treatment, interventional treatment (e.g., valve, coil, vapor, hydrogel, thermal ablation, non-thermal ablation), surgical treatment, etc.).

[0267] If the patient is predicted to have a good response to treatment (e.g., to endobronchial implant treatment with minimal endobronchial augmentation implants), the method 2000 can include generating a treatment plan for the patient using a third software algorithm. The third software algorithm can be a third machine learning algorithm that has been trained (e.g., via supervised learning) to analyze lung metrics and / or predicted responses to predict optimal placement of one or more endobronchial implants to treat the patient’s lung disease. In some embodiments, the third software algorithm can additionally or alternatively include other suitable automated processes. The output of the third software algorithm can be a treatment plan. In embodiments where the treatment includes endobronchial implant treatment, the treatment plan can include any of the following information: implant placement locations, number of implants, implant size, implant type, implant geometry, paths to target locations for implant placement, and / or local treatment solutions. For example, the implant placement locations can be based at least in part on locations of dynamic airway collapse observed in or otherwise determined from the expiratory CT data, severity of lung disease in the peripheral lung, locations of pleural walls, and / or locations of lobar, segmental, and / or subsegmental airways.

[0268] For example, in some embodiments, the third software algorithm can help select one or more lobes and / or one or more airway segments and / or subsegments for implant placement locations based on lung metrics (e.g., lung metrics provided by the first software algorithm). For example, in identifying suitable implant placement locations, the third software algorithm can target lobes with higher amounts of emphysematous destruction (e.g., higher disease scores) and with larger lobar volumes. Additionally or alternatively, the third software algorithm can target airway segments with higher amounts of emphysematous destruction (e.g., higher disease scores) and with larger segment volumes.

[0269] Additionally or alternatively, in some embodiments, a third software algorithm may analyze lung metrics associated with one or more fissures in the lung (e.g., lobar and / or segmental fissures) to generate a treatment plan for the patient. The analyzed lung metrics may include, for example, identification of the location, shape, and / or integrity of fissures between lobes and / or between segments within a lobe. In some embodiments, to optimize placement of minimal endobronchial augmentation implants, it may be advantageous to place the implant at a target location where the fissures are incomplete. Without being bound by any particular theory, it is believed that incomplete fissures allow for greater airflow communication between adjacent segments and / or adjacent lobes, thereby allowing trapped air to be released from more segments (and / or lobes) with fewer endobronchial augmentation implants. Therefore, the third software algorithm may be configured to identify endobronchial augmentation implant placement locations proximal to one or more incomplete lobar and / or segmental fissures. Conversely, for some interventional procedures (e.g., placement of a one-way stent valve, which allows air to flow out but not into an overinflated portion of the lung), it may be advantageous to place the implant at a target location where the fissures are intact.

[0270] Method 2000 can be modified in many different ways. For example, Figure 28 Any of the software algorithms described in the can be combined with each other, subdivided into separate algorithms, and / or omitted entirely. Figure 21 , method 2800 may be similar to method 2000, except that method 2800 omits at least a second software algorithm (e.g., predicting a patient's response to treatment). For example, method 2800 may include receiving patient data comprising CT data of a patient's lungs (block 2810), generating a set of lung metrics by inputting the patient data into a first machine learning algorithm (block 2820), identifying potential target regions in the lungs for treatment of a lung disease based at least in part on the generated lung metrics (block 2830), and generating a treatment plan for the lung disease (block 2840). In some embodiments, blocks 2830 and 2840 may incorporate or be similar to one or more aspects of a third software algorithm. In some embodiments, the first and second software algorithms are combined with or replaced by a single software algorithm that predicts a patient's response directly from the patient data. Optionally, the third software algorithm may generate a treatment plan directly from the patient data, without requiring the lung metrics and / or predicted response generated by the first and second software algorithms, respectively.

[0271] In some embodiments, any of the outputs of the first, second, and / or third software algorithms in the method 2000 can be provided to a user in a patient report. For example, the report can include any one or more of the lung metrics generated by the first software algorithm, the patient's response predicted by the second software algorithm, and / or the treatment plan generated by the third software algorithm. The report can include a written summary or description of any of such outputs of the software algorithms of the method 2000, annotated charts, annotated images, and / or other media (e.g., videos). For example, the report can include an anatomical illustration of at least a portion of the lung and / or an image (e.g., a CT image) of at least a portion of the lung annotated with suitable information. For example, suitable annotation information can include airway measurements (e.g., lumen diameter, wall thickness, etc.) along one or more slices of an airway, disease scores for selected regions (e.g., lobes, segments, and / or subsegments of the lung), lobes, portions of the lung having disease scores that exceed a predetermined threshold, and / or proposed implant placement locations. In some embodiments, such annotations can be descriptive (e.g., with text or numbers) and / or otherwise visualized, such as with color coding or line thickness (e.g., thicker lines to emphasize airway walls in lung segments or subsegments of interest). For example, the illustration or image of the lung can include a map or other visualization of airways in the lung and identification (e.g., with color coding or line thickness) of lobes or segments of the lung having disease scores that exceed a predetermined threshold. As another example, the illustration or image of the lung can include a map or other visualization of airways in the lung and identification (e.g., with an outline of an implant, with color or line thickness to highlight airway walls in targeted airway segments, etc.) of one or more proposed implant placement locations. In some embodiments, the report can be transmitted to a patient medical record (e.g., an electronic medical record) for reference.

[0272] The method 2000 can be performed using any suitable system or device. In some embodiments, some or all of the processes of the method 2000 are implemented as computer-readable instructions (e.g., program code) configured to be executed by one or more processors of a computing device.

[0273] Figure 19 FIG. 21 is a flow diagram illustrating a method 2100 for evaluating the outcome of a treatment of a patient in accordance with an embodiment of the present technology. The method 2100 can be performed as part of the post-operative phase 1906 of the workflow 1900 of FIG. 19. Figure 20 Although the method 2100 is described herein in connection with evaluating the outcome of endobronchial implant treatment, in other embodiments, the method 2100 can be modified for evaluating the outcome of other types of airway treatments (e.g., drug treatment, non-implant interventional treatment).

[0274] The method 2100 can involve receiving patient data, such as questionnaire information, medical record information, image data (e.g., CT data, MRI data, chest radiography data, fluoroscopy data, photographs), PFT data (e.g., spirometry data), bronchoscopy data, data from other diagnostic techniques, and / or any of the other patient data types described herein. Some or all of the patient data can be obtained at multiple points in time, as discussed above with respect to Figure 27 The method 2100 can implement one or more software algorithms that use the patient data to analyze whether the course of treatment was successful, and optionally propose additional procedures that can further improve patient outcomes.

[0275] Patient data (e.g., questionnaire information, PFT data, image data, bronchoscopy data, and / or data from other diagnostic techniques) can be provided to a fourth software algorithm. The fourth software algorithm can be a fourth machine learning algorithm that has been trained (e.g., via supervised learning) to synthesize the patient data to calculate lung metrics and / or implant metrics. In some embodiments, the fourth software algorithm can additionally or alternatively include other suitable automated processes. For example, the lung metrics can represent a state of the patient's lung after placement of one or more endobronchial implants (e.g., minimal endobronchial augmentation implants), such as any of the following: FEV (e.g., FEVi), FVC, VC, IC, IC / TLC ratio, functional residual capacity, TLC, carbon monoxide diffusing capacity, RV, RV / TLC ratio, CV, lung lobe and / or lung segment tissue destruction, lung lobe and / or lung segment air trapping, lung lobe and / or lung segment fissure status, lung lobe and / or lung segment fissure completeness, lung lobe and / or lung segment ventilation, lung function, disease phenotype (e.g., homogeneity / heterogeneity of emphysema, type of emphysema (e.g., acinar centric emphysema, panacinar emphysema, or paraseptal emphysema), location of diseased portion of lung), lung lobe volume, lung segment volume, lung segment location, septal shape, tissue density, opacity, proximity of diseased portion to anatomical structures, proximity of diseased portion to other medical devices, bronchial slice luminal diameter, airflow mapping, collapsed airways, airway pressure, airway compliance, pleural pressure, airway diameter and wall thickness, airway wall deformation, vascular perfusion, parenchymal density, lung bullae, information localizing disease in the lung, obstruction score, mucus score, degree of epithelialization, other implant-tissue interactions (e.g., granulation tissue, implant-induced airway deformation, airway tissue invagination into the implant's lumen, etc.). The set of lung metrics can characterize the lung state at a single point in time, and / or can characterize changes in the lung's state over multiple points in time (e.g., before and after endobronchial implant treatment, before and after administration of bronchodilators, before and during exercise). Additionally or alternatively, the lung metrics can be used to generate a disease "score" that characterizes the severity of lung disease that can remain in one or more regions of the lung after treatment and / or represents an estimate of patient response to treatment of lung disease. In some embodiments, the lung metrics can include one or more disease scores, where each disease score corresponds to a respective region of the lung (e.g., a particular lung, a particular lung lobe, a particular lung segment, a particular subsegment). In some embodiments, the lung metrics can include a single disease score that is based at least in part on a plurality of "local" disease scores, each corresponding to a respective region of the lung (e.g., a particular lung, a particular lung lobe, a particular lung segment, a particular subsegment). For example, the single disease score can be an average of the plurality of local disease scores, or any suitable calculation based on incorporating the plurality of local disease scores. As Figure 24The method 2700 for assessing a patient using this disease score lung metrics (described above with respect to pre-operative assessment) can additionally or alternatively be performed as a post-operative assessment.

[0276] The implant metrics can represent a state of each endotracheal implant placed in the lung, such as any of the following properties: implant position, distance between the distal end of the implant and the pleura, implant length, implant diameter at any one or more locations along the implant length, implant cross-sectional profile at any one or more locations along the implant length, implant integrity (e.g., implant breakage, deformation), indication of implant expansion and / or collapse (e.g., offset or "pancaking" of the implant in the longitudinal direction) (e.g., pitch of the implant rings or angle of the implant ring profile relative to the longitudinal axis of the implant), implant position relative to other placed implants, movement of the one or more implants between inhalation and exhalation, obstruction of the implant, and / or implant migration. The implant metrics can represent a state of the implant at a single point in time, or can represent changes in the state of the implant at multiple points in time. For example, a fourth software algorithm that identifies changes in implant properties from CT imaging performed at various points in time can be helpful in understanding the impact on patient benefit and / or implant interaction.

[0277] For example, in some embodiments, the fourth software algorithm can analyze follow-up exhalation CT scans to produce lung metrics including geometric, physical, and / or mechanical properties of the airways, such as airway compliance, pleural pressure, airway diameter and wall thickness, and / or airway wall deformation. Such properties can be measured especially at the lung segment level, which (as compared to such information determined only at the lung lobe level) can provide more insight into the patient's condition for determining the patient's response to treatment. Additionally or alternatively, the fourth software algorithm can produce lung metrics including identification of any remaining collapsed airways (and the severity of their collapse, such as airway diameter). Further, in some embodiments, the fourth software algorithm can produce implant metrics from the exhalation CT scans characterizing the state of the placed implants, such as any of those described above. Additionally or alternatively, the fourth software algorithm can include other suitable quantitative CT (QCT) techniques, such as those described in further detail herein. Identification of changes in the geometry and / or position of the implants over time, as well as changes in the lung anatomy, such as lung lobe volume, septal shape, density, opacity, and / or lung segment position, can be extracted to establish a link between the patient's anatomy, implant orientation, and treatment outcome.

[0278] In some embodiments, the method 2100 uses a fifth software algorithm that analyzes patient data (e.g., questionnaire information, PFT data, image data, bronchoscopy data, medical record information, and / or data from other diagnostic techniques), lung metrics, and / or implant metrics to determine a patient’s response to endobronchial implant therapy. The fifth software algorithm can be a fifth machine learning algorithm that has been trained (e.g., via supervised learning) to compare lung metrics, implant metrics, and / or patient data pre- and post- procedure to quantify a benefit to the patient. In some embodiments, the fifth software algorithm can additionally or alternatively include other suitable automated processes. The output of the fifth software algorithm can be an indicator of the degree of patient response, such as FEV (e.g., FEVi), FVC, VC, IC, IC / TLC, functional residual capacity, TLC, carbon monoxide diffusing capacity, RV / TLC, RV, lung segment volume, mMRC score, SGRQ score or subgroups thereof, CAT score or subgroups thereof, 6-minute walk test results, cycle ergometry results, CPET results, patient health metrics (e.g., heart rate, blood pressure, body mass index), patient exercise metrics (e.g., number of steps taken), patient visit metrics, quality of life metrics (e.g., breathability), number of implant removals required, time to re-intervention, treatment durability, comorbidities, dosing regimen, hospitalization time, healthcare utilization, and / or cost; and / or a change (e.g., increase or decrease) in any of the above.

[0279] In some embodiments, for example, the fifth software algorithm can include analyzing pre- and post-procedure CT scans, which can provide additional insight into the effectiveness and / or efficacy of the therapy. For example, as shown in Figure 21 the fifth software algorithm can analyze changes in lung volume, lobar volume, segmental volume, lung fissure location (e.g., integrity status and / or degree), diaphragm shape, central airway shape (e.g., collapsed central airways due to overinflation as compared to normal central airways due to release of post-procedure trapped air), and / or the like based on information derived from the CT scans (e.g., assessment of voxel density, and / or the like). Additionally or alternatively, the fifth software algorithm can include other suitable quantitative CT (QCT) techniques, such as those described in further detail herein.

[0280] In some embodiments, the method 2100 uses a sixth software algorithm that analyzes patient data (e.g., questionnaire information, PFT data, image data, bronchoscopy data, medical record information, and / or data from other diagnostic techniques), lung metrics, implant metrics, and / or determined responses to predict patient outcomes following endobronchial implant treatment. The sixth software algorithm can be a sixth machine learning algorithm that has been trained (e.g., via unsupervised learning) to analyze postoperative data metrics over time to predict future outcomes. In some embodiments, the sixth software algorithm can additionally or alternatively include other suitable automated processes. For example, the predicted outcomes can include whether a patient’s prognosis is likely to improve, remain stable, or worsen over time. As another example, the predicted outcomes can include a prediction of postoperative problems, such as excessive mucus, excessive granulation tissue, excessive fibrosis, implant collapse, implant migration, implant failure, implant invagination, implant obstruction, implant sputum, inadequate lung function, pneumothorax, infection, pneumonia, and / or hospitalization.

[0281] In some embodiments, the sixth software algorithm determines one or more interventions to prevent, mitigate, or otherwise address the predicted problems, such as a bronchoscopy to clean, retrieval and / or removal of one or more implants, replacement of one or more implants, repositioning of one or more implants, dilation of one or more implants, placement of one or more additional implants (e.g., in other lung lobes or in the contralateral lung), consultation with a healthcare professional, and / or additional treatment procedures (e.g., medication, surgery, other medical devices). For example, if excessive mucus is predicted, a bronchoscopy at a predetermined interval can be recommended. If excessive granulation tissue and / or fibrosis is predicted, implant removal can be recommended. If implant collapse is predicted, balloon dilation can be recommended. If inadequate FEV1 improvement is predicted, placement of additional implants can be recommended. If implant failure is predicted, implant removal or replacement can be recommended. If hospitalization is predicted, a prophylactic visit can be recommended.

[0282] The method 2100 can be modified in many different ways. For example, Figure 22 Any of the software algorithms described in the Summary can be combined with each other, subdivided into separate algorithms, and / or omitted entirely. Optionally, the fifth software algorithm can determine patient responses directly from patient data, without requiring lung metrics and / or implant metrics produced separately by the fourth software algorithm. Similarly, the sixth software algorithm can predict patient outcomes directly from patient data, without requiring lung metrics and / or implant metrics produced by the fourth software algorithm, and / or without requiring patient responses determined by the fifth software algorithm.

[0283] Similar to that described with respect to method 2000, in some embodiments, any of the outputs of the fourth, fifth, and / or sixth software algorithms in method 2100 can be provided to a user in the form of a patient report. For example, the report can include any one or more of the lung and implant metrics generated by the fourth software algorithm, the patient response to endobronchial implant therapy (e.g., quantified patient benefit) generated by the fifth software algorithm, and / or the predicted future patient outcomes and / or proposed interventions generated by the third software algorithm. The report can include a written summary or description of any of such outputs, annotated graphs, annotated images, and / or other media (e.g., videos) of the software algorithms of method 2100. For example, the report can include an anatomical illustration representing at least a portion of the lung and / or an image (e.g., a CT image) of at least a portion of the treated lung and / or an implant placed in the treated lung annotated with suitable information. For example, suitable annotation information can include airway measurements (e.g., lumen diameter, wall thickness, etc.) along one or more slices of the airway, disease scores for selected regions (e.g., lung lobes, lung segments, and / or subsegments) of the lung, lung lobes, portions of the lung, and / or implant placement locations having disease scores that exceed a predetermined threshold. In some embodiments, such annotations can be descriptive (e.g., with text or numbers) and / or otherwise visualized, such as with color coding or line thickness (e.g., thicker lines to emphasize airway walls of lung segments of interest). For example, the illustration or image of the lung can include a map or other visualization of the airways in the lung and identification (e.g., with color coding or line thickness) of lung lobes, lung segments, or subsegments having disease scores that exceed a predetermined threshold. As another example, the illustration or image of the lung can include a map or other visualization of the airways in the lung and identification (e.g., with the shape of the implant, with color or line thickness to highlight airway walls in segments of the airway, etc.) of one or more implant locations. As another example, the report can include access to a virtual bronchoscopy based on a reconstructed 3D model of the treated lung and placed implant, as described herein. In some embodiments, the report can be transmitted to a patient medical record (e.g., an electronic medical record) for reference.

[0284] Method 2100 can be performed using any suitable system or device. In some embodiments, some or all of the processes of method 2100 are implemented as computer-readable instructions (e.g., program code) configured to be executed by one or more processors of a computing device.

[0285] Figure 20 is a flowchart of a method 2200 for updating software algorithms of Figure 21 and 21 in accordance with embodiments of the present technology. Method 2200 can involve obtaining data from a plurality of different patients regarding patient response to endobronchial implant therapy. The data can be obtained by Figure 20The fifth software algorithm of method 2100 is generated. The patient response data can be provided to a seventh software algorithm. The seventh software algorithm can be a seventh machine learning algorithm that is trained (e.g., via supervised learning techniques) to classify patient responses to treatment into various categories, such as "best case," "worst case," "average case," and the like. In some embodiments, the seventh software algorithm may additionally or alternatively include other suitable automated processes. The output of the seventh software algorithm may be correlated with other types of data, such as indicators of treatment success (e.g., lung metrics), image data (e.g., CT data), and / or other types of patient data (e.g., medical record information). These correlations can be used to update Figure 20 and 21 At least some of the software algorithms of .

[0286] For example, correlations between patient responses and lung metrics (and / or other indicators of treatment success) can be used to update a second software algorithm ( Figure 20 ), the third software algorithm ( Figure 21 ), the fifth software algorithm ( Figure 21 ) and / or the sixth software algorithm ( Figure 20 In embodiments where these software algorithms are or include machine learning algorithms, the correlations can be used as training data for the machine algorithms (e.g., for unsupervised learning). The correlations can inform the algorithm which lung metrics and / or other indicators of treatment success are associated with successful treatment procedures versus unsuccessful procedures.

[0287] As another example, correlation between patient responses and image data (eg, CT data) may be used to update a first software algorithm ( Figure 21 ), the fourth software algorithm ( Figure 21 ), the fifth software algorithm ( Figure 21 ) and / or the sixth software algorithm ( Figure 20 In embodiments where these software algorithms are or include machine learning algorithms, the correlations can be used as training data for the machine algorithms (e.g., for unsupervised learning). The correlations can inform the algorithms which observations from the CT data and / or other image data are associated with successful treatment procedures versus unsuccessful procedures. Optionally, observations from the CT data and / or other image data associated with successful and / or unsuccessful treatment procedures can be used to update (e.g., train) a second software algorithm ( Figure 20 ), the third software algorithm ( Figure 21 ), the fifth software algorithm ( Figure 21 ) and / or the sixth software algorithm ( Figure 20 ) to determine new lung metrics and / or other indicators of treatment success that may help predict the success or failure of a treatment course.

[0288] In another example, the correlation between patient response and medical record information can be used to update a second software algorithm Figure 21 ), a fifth software algorithm Figure 21 ), and / or a sixth software algorithm Figures 20 to 22 ). In embodiments where these software algorithms are or include machine learning algorithms, the correlation can be used as training data for the machine algorithms (e.g., for unsupervised learning). The correlation can inform the algorithms as to what information from the patient medical record is associated with a successful treatment course versus an unsuccessful course.

[0289] Any of the software algorithms described herein (e.g., algorithms 1-7 of Platform Independent Quantitative CT (QCT) ) can be updated and / or refined based on historical and / or repository patient data. This historical patient data can be sourced from a database of prior patients, which can include data from the same patient at an earlier point in time as well as data from other patients. This historical patient data can also be sourced from a repository, which can include patients with lung disease (e.g., GOLD IIICOPD, GOLD IV COPD), with or without intervention, such as an endobronchial implant (e.g., a minimal endobronchial augmentation implant, a valve, a coil), a vapor therapy, or a medication treatment (e.g., an inhaled bronchodilator). For example, the software algorithms can be updated for predictive power using hierarchical Bayesian modeling, where the prior probabilities in the Bayesian scheme are derived from historical or repository patient data.

[0290] V. Figure 26

[0291] As described in further detail herein, imaging data from a CT scan can be analyzed by one or more software algorithms (e.g., machine learning algorithms) to obtain lung metrics and / or implant metrics. To produce lung metrics and / or implant metrics, methods and systems according to the present technology can include one or more software algorithms (e.g., machine learning algorithms or other automated algorithms) to identify and characterize quantitative image features. To make quantitative image features valid for use as biomarkers for disease diagnosis and / or assessment of implant treatment (e.g., placement of an endobronchial augmentation implant), the quantitative image features must be reproducible. However, scanning techniques, parameters, and other scanner algorithms (also collectively referred to herein as “CT scan parameters”) can have a large impact on the reproducibility of QCT output. Different CT scanners (e.g., different scanner manufacturers) can vary, and any particular CT scanner can also be operated with a variety of scan parameters, affecting the results of QCT analysis. For example, the radiation dose applied during scanning and / or the reconstruction algorithm used to produce a tomographic image from acquired x-ray projection data can affect the results of QCT analysis. These and other examples of CT scan parameters that can affect QCT analysis are listed in Table 1 below.

[0292]

[0293]

[0294]

[0295]

[0296] Table 1 - CT scan parameters

[0297] In some embodiments, it can be advantageous to compensate for variations in QCT results due to CT scan parameters, for example by applying at least one correction factor. Correction factors can be used to quantify the effect of differences in one or more CT scan parameters on resulting QCT analysis. In general, such correction factors can be used to obtain normalized (e.g., standardized) results to more effectively assess lung metrics and / or implant metrics, for example in a more objective manner that is independent of the CT platform. For example, correction factors can be used to normalize the density of voxels associated with a particular x-ray attenuation threshold (e.g., -950 HU, -910 HU, etc.) in the CT data. A single correction factor can be associated with a single respective CT scan parameter, or can be associated with multiple CT scan parameters used in combination during a CT scan. Further, compensation for variations in a particular CT scan can involve the use of a single correction factor, or can involve the use of multiple correction factors.

[0298] In some embodiments, correction factors associated with one or more particular CT scan parameters can be determined empirically. For example, CT scans of a prosthesis (or multiple prostheses) of known density can be repeatedly acquired under different predetermined imaging conditions (e.g., known sets of CT scan parameters). The effect of changes in any one particular CT scan parameter on voxel density (and / or QCT analysis results) can be determined empirically by repeatedly acquiring CT scans of the prosthesis while modulating the CT scan parameter in a known manner across different CT scans. For example, to assess the effect of changes in tube voltage on voxel density, the tube voltage can be incrementally adjusted by a known amount between a series of CT scans of the prosthesis. The relationship between the CT scan parameter (and / or changes thereto) and resulting voxel density can be determined empirically (e.g., described by a formula). Additional CT scan parameters can similarly be individually modulated in a known manner to determine the relationship between other CT scan parameters (and / or changes thereto) and resulting voxel density.

[0299] Figure 26is a flowchart illustrating a method 2600 of normalizing one or more QCT results (e.g., lung metrics and / or implant metrics) for a patient (e.g., a patient having or suspected of having a lung disease). The method 2600 can be incorporated into other methods described herein, e.g., in the method 1900 (e.g., generating lung metrics and / or implant metrics of interest in a preoperative stage, a perioperative stage, and / or a postoperative stage), the method 2000 (e.g., generating lung metrics of interest), the method 2100 (e.g., generating lung metrics of interest and / or implant metrics of interest), and / or the method 2200. As Conclusion As shown in the method 2600, the method 2600 can include receiving first CT data for a patient, where the first CT data is obtained under predetermined imaging conditions (block 2610); transforming the first CT data to second CT data by applying at least one correction factor associated with the predetermined imaging conditions (block 2620); and generating a metric associated with the patient based on the second CT data (block 2630). Similar to that described above, the one or more correction factors applied to the CT data can be used to quantify the effects of known imaging conditions, e.g., CT scan parameters. Thus, in some variations, the metric (e.g., lung metrics and / or implant metrics) generated in block 2630 can be more objective and independent of the CT platform.

[0300] The first CT data for a patient is received in block 2610 for obtaining initial image data for the patient obtained under predetermined and / or otherwise known imaging conditions. The CT data can include inspiratory CT data (e.g., obtained at the end of full inspiration) and / or expiratory CT data (e.g., obtained at the end of forced expiration). The CT data can be generated by a CT scan acquisition process in a preoperative stage, a perioperative stage, and / or a postoperative stage. The predetermined imaging conditions can include any one or more of the CT scan parameters listed in Table 1 (e.g., slice thickness, slice interval, tube potential, pitch, tube current, reconstruction algorithm, presence of any contrast agent administered to the patient, contrast agent type / dose, contrast agent administration modality, etc.). While these imaging conditions for which the scan is acquired are predetermined, each CT scan parameter can not necessarily be specifically known or identifiable. For example, some CT scan parameters (e.g., reconstruction algorithm and / or other algorithms used to determine lung fissure integrity) can simply be associated with a particular CT scan machine design or CT vendor in a manner typical of the machine design or vendor. Other CT scan parameters (e.g., slice thickness, slice interval) can be both predetermined and known.

[0301] Transforming the first CT data into second CT data in block 2620 is used to convert the first CT data into a normalized (e.g., standardized) data set from which more objective metrics can be analyzed (e.g., in block 2630). For example, the second CT data can include voxel densities that are independent of differences in CT scan parameters (e.g., scan acquisition parameters, dose modulation parameters, image reconstruction algorithms, contrast agent administration, etc.) and / or other variations such as CT scanner model and / or specific CT vendor providing the CT imaging service. One or more correction factors can be applied to the first CT data to obtain the second, more normalized CT data. As described above, a single correction factor can be associated with a single respective CT scan parameter, or can be associated with multiple CT scan parameters used in combination during a CT scan.

[0302] In some embodiments, a correction factor can be associated with a group of multiple related CT scan parameters. For example, a correction factor can be associated with some or all of the CT scan parameters related to scan acquisition as listed in Table 1, or include some or all of the CT scan parameters related to dose modulation as listed in Table 1, or include some or all of the CT scan parameters related to image reconstruction as listed in Table 1, or include some or all of the CT scan parameters related to contrast agent as listed in Table 1. In some embodiments, a correction factor can be associated with multiple groups of related CT scan parameters. Additionally or alternatively, in some embodiments, a correction factor can be associated with a specific CT scan machine design (e.g., scanner model) and / or a specific vendor providing CT imaging services.

[0303] Generating a metric associated with the patient based on the second CT data in block 2630 is used to generate a metric (e.g., a lung metric and / or an implant metric) for further analysis. In some embodiments, such metrics are generated from the second CT data using one or more software algorithms (e.g., one or more trained machine learning algorithms and / or other automated algorithms). For example, any of the suitable software algorithms described above with respect to methods 1900, 2000, 2100, and / or 2200 can be used to generate lung metrics and / or implant metrics from the second CT data (e.g., the first software algorithm with respect to method 2000, the fourth software algorithm with respect to method 2100, etc.).

[0304] The lung metrics can include any of the lung metrics described herein, such as those described with respect to the methods 1900, 2000, 2100, and / or 2200. For example, the lung metrics can represent a state of the patient's lung after placement of one or more endobronchial implants (e.g., minimal endobronchial augmentation implants), such as any of the following: FEV (e.g., FEVi), FVC, VC, IC, IC / TLC ratio, functional residual capacity, TLC, carbon monoxide diffusing capacity, RV, RV / TLC ratio, CV, lung lobe and / or lung segment tissue destruction, lung lobe and / or lung segment air trapping, lung lobe and / or lung segment fissure status, lung lobe and / or lung segment fissure completeness, lung lobe and / or lung segment ventilation, lung function, disease phenotype (e.g., homogeneity / heterogeneity of emphysema, type of emphysema (e.g., acinar centric emphysema, panacinar emphysema, or paraseptal emphysema), location of diseased portion of lung), lung lobe volume, lung segment volume, lung segment location, septal shape, tissue density, opacity, proximity of diseased portion to anatomical structures, proximity of diseased portion to other medical devices, bronchial slice lumen inner diameter, airflow mapping, collapsed airways, airway pressure, airway compliance, pleural pressure, airway diameter and wall thickness, airway wall deformation, vascular perfusion, parenchymal density, lung bullae, information localizing disease in the lung, obstruction score, mucus score, degree of epithelialization, other implant-tissue interactions (e.g., granulation tissue, implant-induced airway deformation, airway tissue invagination into the lumen of the implant, etc.). The set of lung metrics can characterize the lung state at a single point in time, and / or can characterize changes in the lung state over multiple points in time (e.g., before and after endobronchial implant treatment, before and after administration of a bronchodilator, before and during exercise). Additionally or alternatively, the lung metrics can be used to generate a disease "score" that characterizes the severity of lung disease that can remain in one or more regions of the lung after treatment. The lung metrics can include one or more disease scores, where each disease score characterizes the severity of lung disease in a respective region of the lung (e.g., a particular lung, a particular lung lobe, a particular lung segment, a particular subsegment).

[0305] The implant metrics can include any of the implant metrics described herein, such as those described with respect to methods 1900, 2000, 2100, and / or 2200. For example, the implant metrics can represent a status of each endotracheal implant after placement in the lung, such as any of the following properties: implant position, distance between implant distal end and pleura, implant length, implant diameter at any one or more positions along the implant length, implant cross-sectional profile at any one or more positions along the implant length, indication of implant expansion and / or collapse (e.g., implant biasing or "crushing" in the longitudinal direction) (e.g., pitch of implant rings or angle of implant ring profile relative to the longitudinal axis of the implant), implant position relative to other placed implants, movement of one or more implants between inhalation and exhalation, obstruction of the implant, invagination, and / or implant migration. The implant metrics can represent a status of the implant at a single point in time, or can represent changes in the status of the implant at multiple points in time.

[0306] In some embodiments, the various methods according to the present technology can further include analyzing generated metrics associated with the patient based on the second CT data. This analysis can be performed with one or more software algorithms, such as trained machine learning algorithms or other automated algorithms. For example, lung metrics based on the second CT data can be analyzed in a patient selection process, a surgical planning process, a result assessment process, and / or an intervention recommendation process. As another example, implant metrics based on the second CT data can be analyzed in a result assessment process and / or an intervention recommendation process.

[0307] In some embodiments, any of the suitable software algorithms described above with respect to methods 1900, 2000, 2100, and / or 2200 can be used to analyze the metrics generated based on the second CT data. For example, lung metrics based on the second CT data can be analyzed using the second software algorithm described with respect to method 2000 to determine whether the patient is a candidate for treatment (e.g., likelihood of treatment success), and / or using the third software algorithm described with respect to method 2000 to predict an optimized treatment plan (e.g., optimized implant placement). Additionally or alternatively, lung metrics and / or implant metrics based on the second CT data can be analyzed using the fifth software algorithm with respect to method 2100 to quantify patient benefit after implant placement, and / or using the sixth software algorithm to predict future outcomes and / or recommend interventions after implant placement.

[0308] Figures 1 to 28

[0309] While many embodiments are described above with respect to systems, devices, and methods for treating COPD and emphysema, the technology is applicable to other applications and / or other methods, such as identifying and / or treating tracheobronchial bronchiectasis (TBM), excessive dynamic airway collapse (EDAC), or benign prostatic hyperplasia (BPH). Moreover, other embodiments are within the scope of the technology in addition to those described herein. Additionally, several other embodiments of the technology could have different configurations, components, or processes than those described herein. As a result, it will be understood by those of ordinary skill in the art that the technology can have other embodiments with additional elements or that the technology can have different configurations, components, or processes without departing from the technology described herein. Accordingly, the technology is not limited to those embodiments that may ​ Other embodiments of several features shown and described.

[0310] The various processes described herein can be partially or entirely implemented using program code containing instructions that can be executed by one or more processors of a computing system to implement particular logical functions or steps in the processes. The program code can be stored on any type of computer readable medium, such as a storage device including a disk or hard drive. Computer readable media containing code or portions of code can include any suitable media known or used in the art, such as non-transitory computer readable storage media. Computer readable media can include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage and / or transmission of information, including but not limited to random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology; compact disc read only memory (CD-ROM), digital video disc (DVD), or other optical storage; magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices; solid state drives (SSD) or other solid-state storage devices; or any other medium that can be used to store the desired information and that can be accessed by a system device.

[0311] The description of embodiments of the technology is not intended to be exhaustive or to limit the technology to the precise form disclosed above. Singular or plural terminology can also include the plural or singular term, respectively, where context and recitation permit. While specific embodiments of, and examples for, the technology are described above, it will be appreciated that various modifications are possible that fall within the scope of the technology. For example, the steps can be performed in a different order than described. Various embodiments described herein can also be combined to provide other embodiments.

[0312] As used herein, the terms “generally,” “substantially,” “about,” and similar terms are used as approximation terms and not as degree terms, and are intended to account for the inherent variations in measurement or calculation values that would be recognized by those of ordinary skill in the art.

[0313] Also, the use of "or" in such a list is to be interpreted as inclusive of either single items that are in the list by themselves, or any combination of items in the list, unless expressly limited by context as only meaning single items. The phrases "and / or" and "and / or" as used herein refer to a total combination of single items, multiple items, individual items or combination of items that are stated to be either disjunctively, conjunctively, individually or in any combination. Additionally, the terms "comprise," "comprises," "comprising" or "comprises" when used in this document are used to mean including, but not closed to, the stated features or objects. The terms "comprise," "comprises," "comprising" or "comprises" when used in this document are used to mean including, but not closed to, the stated features or objects.

[0314] To the extent any material incorporated-by-reference herein conflicts with this disclosure, the disclosure controls.

[0315] While specific embodiments have been described herein for purposes of illustration, various modifications can be made without departing from the technology. In addition, while advantages associated with certain embodiments of the technology have been described in the context of those embodiments, other embodiments can also exhibit such advantages, and not all embodiments need necessarily exhibit such advantages to fall within the scope of the technology. Accordingly, the disclosure and associated technology can encompass other embodiments not expressly shown or described herein.

Claims

1. A method for planning treatment of a patient suffering from a lung disease, the method comprising: receiving patient data comprising computed tomography (CT) data of a lung of the patient; generating a set of lung metrics by inputting the patient data into a first machine learning algorithm, wherein the set of lung metrics represents a state of the lungs of the patient; predicting the patient's response to treatment for the lung disease by inputting the set of lung metrics into a second machine learning algorithm; and Whether the patient is a candidate for the treatment of the lung disease is assessed based on the predicted response.

2. The method of claim 1 , wherein the patient data comprises one or more of: questionnaire information, medical record information, magnetic resonance imaging (MRI) data, single photon emission computed tomography (SPECT) data, bronchoscopy data, ventilation perfusion data, pulmonary function test data, chest X-ray data, fluoroscopy data, photographs, or sensor data. The method according to claim 1 , wherein the CT data comprises expiratory CT data. The method of claim 3 , wherein the CT data comprises inspiratory CT data.

5. The method of any one of claims 1 to 4, wherein the patient data comprises data obtained at a plurality of different time points.

6. The method of any one of claims 1 to 5, wherein the set of lung metrics is correlated with whether the patient has at least one of chronic obstructive pulmonary disease (COPD), severe emphysema, or severe emphysema with hyperinflation.

7. The method of any one of claims 1 to 6, wherein the set of lung metrics characterizes one or more lung parameters, the one or more lung parameters comprising one or more of: forced expiratory volume in 1 second, forced vital capacity, vital capacity, inspiratory volume, inspiratory volume / total vital capacity ratio, functional residual capacity, total vital capacity, diffusing capacity for carbon monoxide, residual volume, residual volume / total vital capacity ratio, closed volume, lobar and / or segmental tissue destruction, lobar and / or segmental air trapping, lobar and / or segmental fissure status, lobar and / or segmental fissure integrity, lobar and / or segmental ventilation , lung function, homogeneity / heterogeneity of lobar and / or segmental emphysema, type of emphysema, location of the diseased part of the lung, lobar volume, segmental volume, segmental location, septal shape, tissue density, opacity, proximity of the diseased part to anatomical structures, proximity of the diseased part to other medical devices, luminal diameter of bronchial sections, airflow mapping, collapsed airways, airway pressure, airway compliance, pleural pressure, airway diameter and wall thickness, airway wall deformation, vascular perfusion, parenchymal density, bullae, information on locating the disease in the lung, obstruction score, mucus score or degree of epithelialization.

8. The method of any one of claims 1 to 7, wherein the set of lung metrics includes at least one disease score characterizing the severity of lung disease in the patient.

9. The method of claim 8, wherein the at least one disease score represents a predictor of patient response to the treatment of the lung disease.

10. The method of claim 8 or 9, wherein the set of lung metrics comprises a plurality of disease scores, each disease score corresponding to a respective lobe, segment, or subsegmental region of the lung of the patient.

11. The method of claim 8 or 9, wherein the set of lung metrics comprises a single disease score based on a plurality of local disease scores, each local disease score corresponding to a respective lobe, segment, or subsegmental region of the lung of the patient.

12. The method of claim 11, wherein the single disease score is an average of the plurality of local disease scores.

13. The method of any one of claims 8-12, wherein the at least one disease score represents a degree of at least one of air trapping or hyperinflation in the lungs of the patient.

14. The method of any one of claims 7 to 13, wherein the set of lung metrics characterizes changes in at least one of the one or more lung parameters over multiple time points.

15. The method of claim 14, wherein the plurality of time points comprises two or more of: before endobronchial implant treatment, after endobronchial implant treatment, before bronchodilator administration, after bronchodilator administration, before exercise, or during exercise.

16. The method of any one of claims 1-15, wherein the predicted response comprises a prediction of one or more of: forced expiratory volume in 1 second, forced vital capacity, vital capacity, inspiratory volume, inspiratory volume / total vital capacity ratio, functional residual capacity, total vital capacity, diffusing capacity for carbon monoxide, residual volume, residual volume / total vital capacity ratio, segmental volumes, mMRC score, SGRQ score or a subset thereof, CAT score or a subset thereof, 6-minute walk test results, bicycle ergometer results, cardiopulmonary exercise test (CPET) results, patient health metrics, patient exercise metrics, patient visit metrics, number of implant removals required, time to reintervention, treatment persistence, quality of life scores, body mass index, comorbidities, dosing regimen, length of stay, healthcare utilization, or cost.

17. The method of any one of claims 1 to 16, wherein the treatment comprises airway treatment of COPD.

18. The method of claim 17, wherein the airway treatment comprises medication.

19. The method of claim 17 or 18, wherein the airway treatment comprises an interventional treatment.

20. The method of claim 19, wherein the interventional treatment comprises one or more of: vapor therapy, application of a sealant, transbronchial fenestration, placement of an endobronchial coil, placement of an endobronchial valve, or placement of a minimal endobronchial enhancement implant.

21. The method of claim 20, wherein the interventional treatment comprises the placement of the minimal endobronchial enhancement implant.

22. The method of any one of claims 1-21, further comprising generating a plan for the treatment of the lung disease if the patient is a candidate for the treatment.

23. The method of claim 22, wherein the plan is generated by inputting one or more of the predicted response or the set of lung metrics into a third machine learning algorithm.

24. The method of claim 22 or 23, wherein the treatment comprises placement of at least one minimal endobronchial augmentation implant, and the plan comprises one or more of: implant placement location, number of implants, implant size, implant type, path to target location, or localized treatment solution.

25. The method of claim 24, wherein the implant placement location is based at least in part on one or more of: the location of dynamic airway collapse determined from expiratory CT data, the severity of disease in a peripheral region of the lung, the location of the patient's pleural wall, or the location of lobes, segments, and / or subsegmental airways.

26. The method of any one of claims 1 to 25, further comprising generating a report comprising a summary of one or more of: at least a portion of the set of lung metrics, the predicted response, an assessment of whether the patient is a candidate for the treatment, or the generated plan for the treatment.

27. The method of any one of claims 1-26, further comprising updating one or more of the first machine learning algorithm or the second machine learning algorithm based on historical or repository patient data.

28. The method of claim 27, wherein the historical or repository patient data comprises data of patients with GOLD III COPD, data of patients with GOLD IV COPD, or a combination thereof.

29. The method of claim 27 or 28, wherein the historical or repository patient data comprises data for patients treated with one or more of: a minimal endobronchial enhancement implant, an endobronchial valve, an endobronchial coil, or vapor therapy.

30. The method of any one of claims 27 to 29, wherein the historical or repository patient data comprises data for the patient from an earlier point in time.

31. A system comprising: processor; and A memory operatively coupled to the processor and storing instructions that, when executed by the processor, cause a computing system to perform operations including the method of any one of claims 1-30.

32. A non-transitory computer-readable storage medium comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations including the method of any one of claims 1-30.

33. A method for evaluating a patient's treatment outcome, the method comprising: receiving patient data comprising computed tomography (CT) data of a lung after placing an endobronchial implant in the patient; Generating a set of state metrics by inputting the patient data into a first machine learning algorithm, wherein the set of state metrics comprises: a set of lung metrics representing the status of the patient's lungs after the placement of the endobronchial implant, and a set of implant metrics representing a status of the endobronchial implant after placement in the lung; determining a response of the patient to the endobronchial implant by inputting the set of state metrics into a second machine learning algorithm; and An outcome for the patient following the placement of the endobronchial implant is predicted by inputting one or more of the set of state metrics or the determined responses into a third machine learning algorithm.

34. The method of claim 33, wherein the patient data comprises one or more of: questionnaire information, medical record information, magnetic resonance imaging (MRI) data, single photon emission computed tomography (SPECT) data, bronchoscopy data, ventilation perfusion data, pulmonary function test data, chest X-ray data, fluoroscopy data, photographs, or sensor data.

35. The method of claim 33 or 34, wherein the CT data comprises expiratory CT data.

36. The method of any one of claims 33 to 35, wherein the CT data comprises inspiratory CT data.

37. The method of any one of claims 33 to 36, wherein the patient data comprises data obtained at a plurality of different time points.

38. The method of any one of claims 33 to 37, wherein the set of lung metrics characterizes one or more lung parameters, the one or more lung parameters characterizing any one of: forced expiratory volume in 1 second, forced vital capacity, vital capacity, inspiratory volume, inspiratory volume / total vital capacity ratio, functional residual capacity, total vital capacity, diffusing capacity for carbon monoxide, residual volume, residual volume / total vital capacity ratio, closed volume, lobar and / or segmental tissue destruction, lobar and / or segmental air trapping, lobar and / or segmental fissure status, lobar and / or segmental fissure integrity, lobar and / or segmental ventilation, lung function, lobar and / or segmental emphysema Homogeneity / heterogeneity, type of emphysema, location of the diseased portion of the lung, lobar volume, segmental volume, segmental location, septal shape, tissue density, opacity, proximity of the diseased portion to anatomical structures, proximity of the diseased portion to other medical devices, luminal diameter of bronchial sections, airflow mapping, collapsed airways, airway pressure, airway compliance, pleural pressure, airway diameter and wall thickness, airway wall deformation, vascular perfusion, parenchymal density, bullae, information localizing the disease in the lung, obstruction score, mucus score, degree of epithelialization, granulation tissue, implant-induced airway deformation or invagination of airway tissue into the lumen of the implant.

39. The method of any one of claims 33-38, wherein the set of lung metrics comprises a disease score characterizing the severity of lung disease in the patient.

40. The method of claim 38 or 39, wherein the set of lung metrics characterizes changes in at least one of one or more lung parameters over multiple time points.

41. The method of claim 40, wherein the plurality of time points comprises two or more of: before endobronchial implant treatment, after endobronchial implant treatment, before bronchodilator administration, after bronchodilator administration, before exercise, or during exercise.

42. The method of any one of claims 33-41, wherein the endobronchial implant comprises a minimal endobronchial enhancement implant.

43. A method according to any one of claims 33 to 42, wherein the set of implant measurements characterizes one or more of: implant position, distance between the distal end of the implant and the pleura, implant length, implant diameter at any one or more positions along the length of the implant, implant cross-sectional profile at any one or more positions along the length of the implant, implant integrity, pitch of implant rings, angle of implant ring profile relative to the longitudinal axis of the implant, implant position relative to one or more additional implants, movement of the implant between inspiration and expiration, obstruction of the implant, or implant displacement.

44. The method of any one of claims 33-43, further comprising generating and displaying a virtual bronchoscopy depicting a model incorporating one or more of at least a portion of the lung measurements or at least a portion of the implant measurements.

45. The method of any one of claims 33-44, wherein the determined response comprises determination of one or more of: forced expiratory volume in 1 second, forced vital capacity, vital capacity, inspiratory volume, inspiratory volume / total vital capacity ratio, functional residual capacity, total vital capacity, diffusing capacity for carbon monoxide, residual volume, residual volume / total vital capacity ratio, segmental volumes, mMRC score, SGRQ score or a subset thereof, CAT score or a subset thereof, 6-minute walk test results, bicycle ergometer results, cardiopulmonary exercise test (CPET) results, patient health metrics, patient exercise metrics, patient visit metrics, number of implant removals required, time to reintervention, treatment persistence, quality of life scores, body mass index, comorbidities, dosing regimen, length of stay, healthcare utilization, or cost.

46. ​​The method of any one of claims 33-45, wherein the predicted outcome comprises a prediction of post-operative problems following the placement of the endobronchial implant.

47. The method of claim 46, wherein the postoperative problem comprises one or more of: excessive mucus, excessive granulation tissue, excessive fibrosis, implant collapse, implant failure, implant migration, implant expectoration, insufficient lung function, pneumothorax, infection, pneumonia, or hospitalization.

48. The method of claim 46 or 47, further comprising determining an intervention to address the postoperative problem.

49. The method of claim 48, wherein the determined intervention comprises one or more of: a clean-up bronchoscopy, retrieval or removal of the endobronchial implant, repositioning the endobronchial implant, replacing the endobronchial implant, dilating the endobronchial implant, placement of an additional endobronchial implant, or consultation with a healthcare professional.

50. The method of any one of claims 33 to 49, further comprising generating a report comprising a summary of one or more of: at least a portion of the lung measurements, at least a portion of the implant measurements, the patient's determined response to the endobronchial implant, the predicted outcome for the patient following placement of the endobronchial implant, or the determined intervention to address a postoperative issue.

51. The method of any one of claims 33-50, further comprising updating one or more of the first machine learning algorithm, the second machine learning algorithm, or the third machine learning algorithm based on historical or repository patient data.

52. The method of claim 51, wherein the historical or repository patient data comprises data of patients with GOLD III COPD, data of patients with GOLD IV COPD, or a combination thereof.

53. The method of claim 51 or 52, wherein the historical or repository patient data comprises data for patients treated with one or more of: a minimal endobronchial enhancement implant, an endobronchial valve, an endobronchial coil, or vapor therapy.

54. The method of any one of claims 51 to 53, wherein the historical or repository patient data comprises data for the patient from an earlier point in time.

55. The method of any one of claims 33-54, further comprising comparing the set of lung measurements with a second set of lung measurements determined from one or more of: image data of the lungs before the placement of the endobronchial implant, image data of the lungs at an earlier point in time after the placement of the endobronchial implant, image data of the lungs after placement of another endobronchial implant at a location different from the location of the endobronchial implant, or image data from other patients with COPD.

56. A system comprising: processor; and A memory operatively coupled to the processor and storing instructions that, when executed by the processor, cause a computing system to perform operations including the method of any one of claims 33 to 55.

57. A non-transitory computer-readable storage medium comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations including the method of any one of claims 33-55.

58. A method for evaluating a patient having or suspected of having a lung disease, the method comprising: receiving patient data comprising computed tomography (CT) data of a lung of the patient; and A lung disease score for the region of interest of the lung is generated by inputting the patient data into a machine learning algorithm, wherein the lung disease score characterizes the severity of lung disease in the region of interest of the lung of the patient, wherein the region of interest is a segmental or subsegmental region of the lung.

59. The method of claim 58, wherein the machine learning algorithm evaluates voxel density in the CT data associated with the region of interest of the lung of the patient.

60. The method of claim 58 or 59, wherein the lung disease score is based on a plurality of regional disease scores, each regional disease score corresponding to a respective lobe, segment, or subsegmental region of the lung of the patient.

61. The method of claim 60, wherein the lung disease score is an average of the plurality of regional disease scores.

62. The method of claim 58 or 59, wherein the lung disease score is a first lung disease score, wherein the method further comprises generating a plurality of lung disease scores including the first lung disease score, wherein each of the plurality of lung disease scores corresponds to a respective lobe, segment, or subsegmental region of the lung of the patient.

63. The method of any one of claims 58-62, wherein the lung disease score represents a degree of at least one of air trapping or hyperinflation in the lungs of the patient.

64. The method of any one of claims 58-63, wherein the CT data comprises expiratory CT data.

65. The method of any one of claims 58-64, wherein the CT data comprises inspiratory CT data.

66. The method of any one of claims 58-65, wherein the CT data is generated prior to administration of a therapy to the patient to treat the lung disease.

67. The method of any one of claims 58-65, wherein the CT data is generated after a therapy is administered to the patient to treat the lung disease.

68. The method of claim 66 or 67, wherein the treatment comprises placement of an endobronchial implant.

69. A system comprising: processor; and A memory operatively coupled to the processor and storing instructions that, when executed by the processor, cause a computing system to perform operations including the method of any one of claims 58-68.

70. A computed tomography (CT) scanner comprising: processor; and A memory operatively coupled to the processor and storing instructions that, when executed by the processor, cause the CT scanner to perform operations including the method of any one of claims 58-68.

71. A non-transitory computer-readable storage medium comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations including the method of any one of claims 58-68.

72. A method for normalizing quantitative computed tomography (CT) results of a patient, the method comprising: receiving first CT data of the patient, wherein the first CT data is generated under predetermined imaging conditions; and The first CT data is transformed into second CT data by applying at least one correction factor associated with the predetermined imaging condition to the first CT data.

73. The method of claim 72, wherein the at least one correction factor maps voxel density in the first CT data to a normalized voxel density.

74. The method of claim 72 or 73, wherein the at least one correction factor compensates for voxel density in the first CT data that is affected by one or more of: tube current, tube potential, pitch.

75. The method of any one of claims 72-74, wherein the at least one correction factor compensates for voxel density in the first CT data that is affected by at least one of slice thickness or slice spacing.

76. The method of any one of claims 72 to 75, wherein the at least one correction factor compensates for voxel density in the first CT data that is affected by a reconstruction algorithm used to determine sharpness or smoothness of an image in an axial plane.

77. The method of any one of claims 72 to 76, wherein the first CT data is obtained from a CT scan provider having a provider-specific machine learning algorithm for reconstructing a CT image from the CT data, wherein the at least one correction factor compensates for voxel density in the first CT data affected by the provider-specific machine learning algorithm.

78. The method of any one of claims 72 to 77, wherein the at least one correction factor compensates for voxel density in the first CT data affected by administration of a contrast agent in the patient prior to generating the first CT data.

79. The method of any one of claims 72 to 78, wherein the second CT data is normalized with respect to CT scan parameters.

80. The method of any one of claims 72-79, wherein the first CT data is obtained during a preoperative phase prior to placement of an endobronchial implant in the patient.

81. The method of any one of claims 72-80, further comprising generating a set of lung metrics associated with the patient based on the second CT data.

82. The method of any one of claims 72-79, wherein the first CT data is obtained during a perioperative phase during placement of an endobronchial implant in the patient.

83. The method of any one of claims 72-79, wherein the first CT data is obtained during a postoperative period after placement of an endobronchial implant in the patient.

84. The method of claim 82 or 83, further comprising generating at least one of a set of lung metrics or a set of implant metrics associated with the patient based on the second CT data.

85. A system comprising: processor; and A memory operatively coupled to the processor and storing instructions that, when executed by the processor, cause a computing system to perform operations including the method of any one of claims 72-84.

86. A computed tomography (CT) scanner comprising: processor; and A memory operatively coupled to the processor and storing instructions that, when executed by the processor, cause the CT scanner to perform operations including the method of any one of claims 72-84.

87. A non-transitory computer-readable storage medium comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations including the method of any one of claims 72-84.

88. A method for planning treatment for a patient suffering from a lung disease, the method comprising: receiving patient data comprising computed tomography (CT) data of a lung of the patient; generating a set of lung metrics by inputting the patient data into a first machine learning algorithm, wherein the set of lung metrics represents a state of the lungs of the patient; A potential target region in the lung for treating the lung disease is identified based at least in part on the generated lung metrics.

89. The method of claim 88, wherein the patient data comprises one or more of: questionnaire information, medical record information, magnetic resonance imaging (MRI) data, single photon emission computed tomography (SPECT) data, bronchoscopy data, ventilation perfusion data, pulmonary function test data, chest X-ray data, fluoroscopy data, photographs, or sensor data.

90. The method of claim 88 or 89, wherein the CT data comprises expiratory CT data.

91. The method of any one of claims 88-90, wherein the CT data comprises inspiratory CT data.

92. The method of any one of claims 88 to 91, wherein the patient data comprises data obtained at a plurality of different time points.

93. The method of any one of claims 88-92, wherein the set of lung metrics is correlated with whether the patient has at least one of chronic obstructive pulmonary disease (COPD), severe emphysema, or severe emphysema with hyperinflation.

94. The method of any one of claims 88 to 93, wherein the set of lung metrics characterizes one or more lung parameters, the one or more lung parameters comprising one or more of: forced expiratory volume in 1 second, forced vital capacity, vital capacity, inspiratory volume, inspiratory volume / total vital capacity ratio, functional residual capacity, total vital capacity, diffusing capacity for carbon monoxide, residual volume, residual volume / total vital capacity ratio, closed volume, lobar and / or segmental tissue destruction, lobar and / or segmental air trapping, lobar and / or segmental fissure status, lobar and / or segmental fissure integrity, lobar and / or segmental Ventilation, lung function, homogeneity / heterogeneity of lobar and / or segmental emphysema, type of emphysema, location of the affected portion of the lung, lobar volume, segmental volume, segmental location, septal shape, tissue density, opacity, proximity of the affected portion to anatomical structures, proximity of the affected portion to other medical devices, luminal diameter of bronchial sections, airflow mapping, collapsed airways, airway pressure, airway compliance, pleural pressure, airway diameter and wall thickness, airway wall deformation, vascular perfusion, parenchymal density, bullae, information localizing the disease in the lung, obstruction score, mucus score, or degree of epithelialization.

95. The method of any one of claims 88-94, wherein the set of lung metrics comprises at least one disease score characterizing the severity of lung disease in the patient.

96. The method of claim 95, wherein the at least one disease score represents a predictor of patient response to the treatment of the lung disease.

97. The method of claim 95 or 96, wherein the set of lung metrics comprises a plurality of disease scores, each disease score corresponding to a respective lobe, segment, or subsegmental region of the lung of the patient.

98. The method of claim 95 or 96, wherein the set of lung metrics comprises a single disease score based on a plurality of local disease scores, each local disease score corresponding to a respective lobe, segment, or subsegmental region of the lung of the patient.

99. The method of claim 98, wherein the single disease score is an average of the plurality of local disease scores.

100. The method of any one of claims 95-99, wherein the at least one disease score represents a degree of at least one of air trapping or hyperinflation in the lungs of the patient.

101. The method of any one of claims 94-100, wherein the set of lung metrics characterizes changes in at least one of the one or more lung parameters over multiple time points.

102. The method of claim 101, wherein the plurality of time points comprises two or more of: before endobronchial implant treatment, after endobronchial implant treatment, before bronchodilator administration, after bronchodilator administration, before exercise, or during exercise.

103. The method of any one of claims 88-102, wherein the treatment comprises airway treatment of COPD.

104. The method of claim 103, wherein the airway treatment comprises medication.

105. The method of claim 103 or 104, wherein the airway treatment comprises interventional therapy.

106. The method of claim 105, wherein the interventional treatment comprises one or more of: vapor therapy, application of a sealant, transbronchial fenestration, placement of an endobronchial coil, placement of an endobronchial valve, or placement of a minimal endobronchial enhancement implant.

107. The method of claim 106, wherein the interventional treatment comprises the placement of the minimal endobronchial enhancement implant.

108. The method of any one of claims 88-107, further comprising generating a plan for the treatment.

109. The method of claim 108, wherein the plan is generated by inputting the set of lung metrics into a second machine learning algorithm.

110. The method of claim 108 or 109, wherein the treatment comprises placement of at least one minimal endobronchial augmentation implant and the plan comprises one or more of: implant placement location, number of implants, implant size, implant type, path to target location, or localized treatment solution.

111. A method according to claim 110, wherein the implant placement location is based at least in part on one or more of: the location of dynamic airway collapse determined from expiratory CT data, the severity of disease in the peripheral region of the lung, the location of the patient's pleural wall, or the location of lung lobes, segments and / or subsegmental airways.

112. A system comprising: processor; and A memory operatively coupled to the processor and storing instructions that, when executed by the processor, cause a computing system to perform operations including the method of any one of claims 88 to 111.

113. A computed tomography (CT) scanner comprising: processor; and A memory operatively coupled to the processor and storing instructions that, when executed by the processor, cause the CT scanner to perform operations including the method of any one of claims 88 to 111.

114. A non-transitory computer-readable storage medium comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations including the method of any one of claims 88-111.

Images