Invasive Procedure Optimization

Abstract

The controller 122, 910 / 920 for invasive procedure optimization includes a processor 12210, 910 and a memory 12220, 920 that stores instructions. When the instructions are executed by the processor, the controller 12210, 910 performs a process including, for each of a plurality of candidate types of invasive procedures for the anatomical tissue, identifying anatomical features from a pre-invasive image of the anatomical tissue (S210) and comparing the anatomical features with tool features of a candidate tool to be used with each of the plurality of candidate types (S220). The process also includes generating a feasibility report for each candidate type based on the identifying and comparing (S240). Each feasibility report includes a feasibility assessment for each of the candidate types. The process also includes selecting an optimal invasive procedure type from among the candidate types based on the feasibility report (S260). The invasive procedure is performed on the anatomical tissue using the optimal invasive procedure type based on the selecting (S260).

Description

[Background technology]

[0001] Lung cancer is the most lethal cancer in the world today. Several countries have implemented lung cancer screening programs to detect lung cancer at an early stage. Several treatment options are available for early stage lung cancer, resulting in improved 5-year survival rates. For patients with suspected lung cancer, it is essential to obtain a diagnosis of suspicious lung tissue, whether by screening or other means. Lung tissue can be biopsied by several types of biopsy, including endobronchial, transthoracic or surgical biopsy. intervention Endobronchial biopsy is the preferred type of biopsy to obtain a sample of lung tissue for diagnosis because it has a low complication rate. However, for peripheral lung cancer nodules, endobronchial biopsy may only have a diagnostic yield of 30%. Transthoracic and surgical biopsies have a much higher diagnostic yield but are associated with a higher complication rate.

[0002]

[0002] More than 60% of lung cancer patients require at least one biopsy to obtain a lung tissue sample of diagnostic quality. Typically, an endobronchial biopsy is attempted first to minimize complications. If an adequate lung tissue sample cannot be obtained with the endobronchial biopsy, the patient will undergo a transthoracic biopsy or a surgical biopsy, both of which are associated with a high risk of complications. Therefore, a balance is made between the risk of complications and the possibility of obtaining a good lung tissue sample with a high diagnostic yield. Summary of the Invention [Problem to be solved by the invention]

[0003]

[0003] Artificial intelligence (AI) is used in lung cancer screening, including image analysis to automatically detect and locate suspicious lung cancer nodules in computed tomography (CT) images. Information on size, appearance, and growth rate is used to set a threshold for whether or not suspicious tissue should be biopsied as part of lung cancer screening. However, there are currently no established guidelines or support tools to provide decision support regarding the type of biopsy a patient should undergo. The present invention provides a method for determining whether or not a patient should undergo a biopsy. intervention Treatment optimization addresses these challenges. [Means for solving the problem]

[0004]

[0004] According to one aspect of the present disclosure, intervention The controller for treatment optimization includes a memory and a processor. The memory stores instructions. The processor executes the instructions. When the instructions are executed by the processor, the controller performs a step of optimizing the anatomical structure of the tissue. intervention For multiple candidate types of procedures, anatomical features are compared with anatomical tissues. intervention The controller performs a process including identifying anatomical features from the previous image and comparing the anatomical features to tool features of a candidate tool for use with each of the plurality of candidate types. The process performed by the controller when the instructions are executed by the processor also includes generating a feasibility report for each of the plurality of candidate types based on the identifying and comparing. Each feasibility report includes a feasibility report for each of the plurality of candidate types. grade The processing performed by the controller when the instructions are executed by the processor also includes determining a best fit among the plurality of candidate types based on the feasibility report of each of the plurality of candidate types. intervention A procedure type may be selected. intervention Treatment is based on the selection of optimal intervention The procedure type is used to perform on the anatomy.

[0005]

[0005] According to another aspect of the present disclosure, interventionThe apparatus for treatment optimization includes an input interface and a controller. The input interface is a intervention The controller inputs a pre-treatment image. The controller includes a memory and a processor. The memory stores instructions. The processor executes the instructions. When the instructions are executed by the processor, the controller performs operations. The operations performed by the controller when the processor executes the instructions include: intervention For multiple candidate types of procedures, anatomical features are pre-registered into the anatomy intervention The process further comprises: identifying from the image an anatomical feature and comparing the anatomical feature to a tool feature of a candidate tool for use with each of the plurality of candidate types. The process performed by the controller when the processor executes the instructions also comprises generating a feasibility report for each of the plurality of candidate types based on the identifying and comparing. Each feasibility report includes a feasibility report for each of the plurality of candidate types. grade The processing performed by the controller when the processor executes the instructions further includes: determining a best candidate among the plurality of candidate types based on the feasibility report of each of the plurality of candidate types. intervention A procedure type may be selected. intervention Treatment is based on the selection of optimal intervention The procedure type is used to perform on the anatomy.

[0006]

[0006] According to yet another aspect of the present disclosure, intervention The system for treatment optimization includes an input interface, a monitor, and a controller. The input interface includes a intervention Input the pre-treatment image. The monitor displays the anatomical tissue. intervention The controller includes a memory and a processor. The memory stores instructions. The processor executes the instructions. When the instructions are executed by the processor, the controller displays a pre-treatment image of the anatomical tissue. intervention For multiple candidate types of procedures, anatomical features are pre-registered into the anatomy interventionThe process includes identifying anatomical features from the image and comparing the anatomical features to tool features of a candidate tool for use with each of the plurality of candidate types. The process performed by the controller when the processor executes the instructions also includes generating a feasibility report for each of the plurality of candidate types based on the identifying and comparing. Each feasibility report includes a feasibility report for each of the plurality of candidate types. grade The processing performed by the controller when the processor executes the instructions also includes determining a best fit among the plurality of candidate types based on the feasibility report of each of the plurality of candidate types. intervention A procedure type may be selected. intervention Treatment is based on the selection of optimal intervention The procedure type is used to perform on the anatomy.

[0007]

[0007] The exemplary embodiments are best understood from the following detailed description when read in conjunction with the accompanying drawings. It is emphasized that the various features are not necessarily drawn to scale. In fact, dimensions have been appropriately increased or decreased for clarity of illustration. Wherever applicable and practical, like reference numerals refer to like elements. [Brief description of the drawings]

[0008] [Figure 1A]

[0008] FIG. 1 illustrates a system for interventional procedure optimization, according to a representative embodiment. [Figure 1B]

[0009] FIG. 1 illustrates a controller for interventional procedure optimization, according to a representative embodiment. [Diagram 2]

[0010] FIG. 1 illustrates a method for interventional procedure optimization, according to a representative embodiment. [Diagram 3]

[0011] FIG. 1 illustrates an artificial intelligence schematic for interventional procedure optimization, according to a representative embodiment. [Figure 4]

[0012] FIG. 1 illustrates a controller for generating a feasibility report of an interventional procedure optimization, according to a representative embodiment. [Diagram 5]

[0013] FIG. 1 illustrates a diagram showing a path planning for an intervention in intervention optimization according to a representative embodiment. [Figure 6]

[0014] FIG. 1 illustrates a feasibility map for interventional procedure optimization, according to a representative embodiment. [Figure 7]

[0015] FIG. 13 illustrates another intervention path planning in intervention optimization according to a representative embodiment. [Figure 8]

[0016] FIG. 13 illustrates another feasibility map for interventional procedure optimization, according to a representative embodiment. [Figure 9]

[0017] FIG. 1 illustrates a computer system on which a method for interventional procedure optimization is implemented, according to another representative embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009]

[0018] In the following detailed description, for purposes of explanation and not limitation, representative embodiments disclosing specific details are presented to ensure a thorough understanding of the embodiments according to the present teachings. Descriptions of known systems, devices, materials, methods of operation, and methods of manufacture are omitted so as not to obscure the description of the representative embodiments. Nevertheless, systems, devices, materials, and methods within the scope of those skilled in the art are within the scope of the present teachings and are used in accordance with the representative embodiments. It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only, and is not limiting. Defined terms are intended to supplement the technical and scientific meaning of the defined terms as commonly understood and accepted in the art of the present teachings.

[0010]

[0019] Terms such as first, second, third, etc. are used herein to describe various elements or components, but it should be understood that such elements or components should not be limited by these terms. These terms are merely used to distinguish one element or component from another. Thus, a first element or component discussed below may also be referred to as a second element or component without departing from the teachings of the inventive concept.

[0011]

[0020] The terminology used herein is for the purpose of describing particular embodiments only and is not limiting. As used in this specification and the appended claims, singular terms include both the singular and the plural unless the context clearly dictates otherwise. Furthermore, the terms "comprises, has, includes" and / or "comprises, has, includes" and / or similar terms, when used herein, specify the presence of stated features, elements, and / or components, but do not exclude the presence or addition of one or more other features, elements, components, and / or groups thereof. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0012]

[0021] Unless otherwise specified, when an element or component is said to be "connected," "coupled," or "adjacent" to another element or component, it is understood that the element or component can be directly connected or coupled to the other element or component, or there may be intervening elements or components. That is, these and similar terms encompass the cases where one or more intermediate elements or components are used to connect the two elements or components. However, when an element or component is said to be "directly connected" to another element or component, this only encompasses the cases where the two elements or components are connected to each other without any intermediate or intervening elements or components.

[0013]

[0022] The present disclosure thus derives one or more advantages, as specifically set forth below, through one or more of its various aspects, embodiments and / or specific features or subcomponents. For purposes of explanation and not limitation, exemplary embodiments disclosing specific details are presented so that embodiments according to the present teachings may be fully understood. However, other embodiments consistent with the present disclosure that depart from the specific details disclosed herein remain within the scope of the appended claims. Moreover, descriptions of well-known devices and methods are omitted so as not to obscure the description of the exemplary embodiments. Such methods and devices are within the scope of the present disclosure.

[0014]

[0023] As described herein, such as the type of biopsy and resection intervention Automated determination of the optimal type of treatment is based on multiple different types of intervention The process will be based on a feasibility analysis of each of the measures considered. intervention The various types of procedures are also referred to as candidate types. This analysis involves trade-offs such as maximizing diagnostic yield while minimizing complications. The management tool leverages artificial intelligence (AI) to integrate multimodality data including but not limited to imaging, medical risks, procedure costs, operator experience, and technical feasibility to quantify success rates and risk factor scores for each candidate type. The automated decision is intervention It can be used to improve patient management so that treatment is done right the first time. intervention For various types of biopsies as procedures, automated diagnosis can be performed cost-effectively while minimizing the risk of complications. Aspects This results in diagnostic quality tissue sampling.

[0015]

[0024] FIG. 1A illustrates a schematic diagram of a semiconductor device according to a representative embodiment. intervention 1 shows a system for treatment optimization.

[0016]

[0025] The system 100 of FIG. interventionA system for treatment optimization, including components provided together or distributed. System 100 includes computer 120, display 130, and AI system 140. Computer 120 includes controller 122. AI system 140 includes AI engine 142. Computer 120 is local to display 130 and is connected to display 130 via a local wired interface, such as an Ethernet cable, or via a local wireless interface, such as a Wi-Fi connection. Computer 120 may be remote from AI system 140 and may be connected to AI system 140 via the Internet using one or more wired and / or wireless connections.

[0017]

[0026] Computer 120 includes one or more input interfaces. The input interfaces (not shown) of computer 120 include ports, disk drives, wireless antennas, or other types of receiver circuitry. The input interfaces may also couple user interfaces to computer 120, such as a mouse, keyboard, microphone, video camera, touch screen display, or other elements or components. The input interfaces of computer 120 may include: intervention Before treatment intervention Input of the anatomy image, and intervention During treatment intervention The one or more input interfaces also include: intervention Candidate types of treatment and intervention Candidate tools to be used for treatment and candidate types intervention For example, the input interface of the computer 120 may be connected to a mouse, which may be used to select or deselect candidate types, candidate tools, and / or candidate paths through the anatomy to reach a target site during a procedure. interventionControls a cursor that is used to identify and select one of several different possible paths to reach the treatment target. Alternatives to a mouse connected to computer 120 include voice recognition or gesture recognition captured by a microphone or video camera connected to computer 120.

[0018]

[0027] Display 130 may be a monitor, such as a computer monitor, a mobile device display, a television, an electronic whiteboard, or other screen configured to display electronic images. Display 130 may also include one or more input interfaces, such as those described above, that couple other elements or components to computer 120, as well as a touch screen that allows for direct input by touch. For example, intervention Candidate type of treatment, candidate type intervention Selection and / or deselection of candidate tools for use in a procedure, as well as paths through the anatomy, are all accomplished via a touch screen input interface on the display 130. The display 130 includes: intervention Preanatomical images and intervention For example, the computer 120 may receive images, such as computed tomography images, magnetic resonance images, and / or ultrasound images, from a website, email, a portable disk, or other type of memory, via an input interface. intervention A computer 120 may acquire or separately receive a pre-image. intervention For displaying the previous image on the display 130 intervention The computer 120 also provides the image to the display 130 via a local wired interface or a local wireless interface. intervention Imaging machines and imaging systems that operate to generate images, such as X-ray images or ultrasound images, are connected via wired connections or the like. intervention Receive the image and intervention The image is provided to a display 130 for display.

[0019]

[0028] The controller 122 of the computer 120 in the system 100 includes a memory (see FIG. 1B) for storing instructions and a processor (see FIG. 1B) for executing the instructions. When the instructions are executed by the processor, the controller 122 generates a plurality of candidate types of anatomical tissue. intervention Anatomical features for each procedure intervention The process performed by the controller 122 based on the processor executing instructions also includes comparing the anatomical features with tool features of a candidate tool for use with each of the plurality of candidate types. The process performed by the controller 122 based on the processor executing instructions also includes generating a feasibility report for each of the plurality of candidate types based on the identifying and comparing. Each feasibility report includes a feasibility report with different weightings for each of the plurality of candidate types. grade The process performed by the controller 122 also includes determining the best candidate among the plurality of candidate types based on the feasibility report of each of the plurality of candidate types. intervention The feasibility report generated by the controller 122 also includes selecting the optimal treatment type. intervention By procedure type, which intervention It also defines the best chance that the tool will be able to successfully reach the target site. intervention Treatment is then determined based on the selection. intervention The procedure type is used to perform on the anatomy. intervention The treatment is selected based on the optimal intervention It may also be based on tools.

[0020]

[0029] The processing performed by the controller 122 includes one or more of the above-mentioned operations performed based on the processor executing instructions. For example, the controller 122 may perform operations such as identifying anatomical features, comparing anatomical features to tool features, generating a feasibility report, and determining optimal interventionPerforming processing by controller 122 may also include other operations that are performed indirectly by controller 122, such as by directing another element of system 100, such as display 130 or AI system 140, to perform one or more of the operations described above or other operations, or by otherwise communicating with that element. For example, controller 122 may instruct display 130 to: intervention Treatment and each intervention The controller 122 may provide images and instructions to the display 130 to display selected information, such as a selection of tools to be used in a procedure. Similarly, to the extent that the controller 122 is an element of the computer 120 as an apparatus, and the computer 120 is an element of the system 100, the operations attributed to the controller 122 above may also be intervention The computer 120 as a treatment optimization device also includes: intervention It also refers to the system 100 as a system for treatment optimization.

[0021]

[0030] The AI ​​system 140 is intervention The previous image, intervention Feasibility report corresponding to the previous image and the results based on the feasibility report intervention The AI ​​system 140 also performs machine learning based on the clinical outcome of the treatment. intervention such as sensor data from sensor-equipped tools used in the procedure; intervention Data from treatments is also received. As mentioned above, AI system 140 includes AI engine 142 to generate and implement artificial intelligence based on machine learning. AI engine 142 is implemented as software that performs and applies the machine learning described herein. AI system 140 may, for example, implement the machine learning and artificial intelligence in the cloud, such as in a data center, where AI system 140 is connected to computer 120 via the internet using one or more wired and / or wireless connections. AI system 140 may be configured to run a relatively large database of machine learning and artificial intelligence for a variety of patients in a variety of locations. interventionBased on and for a set of procedures, the AI ​​system 140 may be connected to multiple different computers, including the computer 120, so as to be implemented centrally. Alternatively, the AI ​​system 140 may be configured to perform a series of procedures of a similar nature for a number of patients. intervention Treatment (e.g., lung cancer intervention Machine learning and artificial intelligence are implemented locally in a computer 120 at a facility where a medical procedure is performed.

[0022]

[0031] FIG. 1B illustrates a cross-sectional view of a representative embodiment of a intervention A controller 122 for treatment optimization is shown.

[0023]

[0032] The controller 122 of FIG. intervention The treatment optimization controller 122 may be provided as a stand-alone component as shown, or as a component of a device such as the computer 120 of Figure 1A. The controller 122 includes a processor 12210, a memory 12220, and a bus 12208. The processor 12210 obtains or otherwise receives instructions from the memory 12220 via the bus 12208.

[0024]

[0033] As described herein, the controller 122 intervention The memory 12220 stores instructions and the processor 12210 executes the instructions. When the instructions are executed by the processor 12210, the controller 122 selects a plurality of candidate types of anatomical tissue. intervention Anatomical features for each procedure intervention The processing performed by the controller 122 when the processor executes the instructions also includes comparing the anatomical features to tool features of a candidate tool for use with each of a plurality of candidate types based on the identifying and comparing. intervention The process also includes generating a feasibility report for each of the plurality of candidate types of treatment. interventionAlso included is identifying potential tools for use with each of the procedures, which are included in a feasibility report, each of which includes a feasibility report with different weightings for multiple candidate types. grade Feasibility grade The weighting of varies based on the different expected diagnostic yields for different candidate types. grade The weighting of is based on the diagnostic rate of previous instantiations, intervention The procedure is established based on applying artificial intelligence to previous instantiations of the procedure.

[0025]

[0034] The process performed by the controller 122 also includes determining the best candidate among the plurality of candidate types based on the feasibility report of each of the plurality of candidate types. intervention The process performed by the controller 122 also includes selecting the treatment type. intervention The optimal solution or solutions used to reach the target site for the procedure type intervention This also includes the selection of tools. intervention The treatment is optimally selected. intervention The procedure type is used to perform on the anatomy. intervention The treatment is selected based on the optimal intervention This is done using tools.

[0026]

[0035] The controller 122 directly performs some of the operations described herein and indirectly performs other operations described herein. For example, the controller 122 may: intervention Identify anatomical features directly from the pre-imaging, directly compare the anatomical features to the tool features, and directly generate a feasibility report for each of multiple candidate types, and / or select the optimal intervention The controller 122 directly selects the type of action, as well as the optimal tool to be used. The controller 122 initiates requests to the AI ​​system 140 to apply artificial intelligence; interventionAn action indirectly controls other operations, such as by initiating an action that is to be performed. Thus, the processing performed by controller 122 when processor 12210 executes instructions from memory 12220 may not be performed directly by controller 122.

[0027]

[0036] FIG. 2 is a block diagram of a system according to a representative embodiment of the present invention; intervention 2 illustrates a treatment optimization process.The method of FIG. 2 may be performed by or on behalf of a single device, system, or entity, or may be performed by or on behalf of a distributed device, system, or entity.

[0028]

[0037] In S210 of FIG. 2, anatomical features are identified. The anatomical features are identified by the controller 122 of the computer 120 of FIG. 1A based on preoperative images received by the computer 120 of FIG. 1A, etc. The anatomical features include organs, bones, blood vessels, airways, lung cancer tumors / nodules, and other human anatomical tissue parts. The anatomical features also include the diameter, curvature, elasticity of airways, and other anatomical features of the anatomical tissues. intervention Mechanical characteristics, such as the elasticity of the tissue surrounding the anatomical structure to be treated, may also be included. For example, anatomical characteristics may include the diameter of an airway, the curvature of an airway, the elasticity of tissue such as an airway, or the like. intervention The elasticity of the surrounding tissue surrounding the anatomical structure to be treated is also included. intervention Also included is the relative location of the treatment target and one or more routes to the relative location of the target. intervention The mechanical characteristics of the tissue are correlated to the origin of the three-dimensional coordinate system used in the procedure, as described below with respect to S220. intervention Particular comparisons are made with the mechanical features and functions of various possible tools to be used in the procedure.

[0029]

[0038] Anatomical features can be identified by computer tomography images of anatomical tissues. intervention Anatomical features are identified from the anatomy of the anatomy. intervention A number of candidate types of treatments may be identified. intervention The procedure is a biopsy, and the multiple candidate types include an endobronchial biopsy of lung tissue, a transthoracic biopsy of lung tissue through the chest cavity, and a surgical biopsy of lung tissue performed by surgery. Thus, S210 includes selecting the multiple candidate biopsy types or anatomical tissues. intervention For each type of procedure, the anatomical features are intervention Anatomical features include changing the path to the target location and allowing for two different types of intervention In cases where different anatomical structures are encountered during the procedure, various types of intervention Each procedure is different.

[0030]

[0039] In one embodiment, identifying anatomical features at S210 includes: intervention The method includes or is followed by automatically detecting a target location for treatment. The target location is a tumor identified as an anatomical feature by image analysis in S210. The image analysis first identifies recognizable anatomical features and then automatically identifies one or more of the identified anatomical features as a target location. The identified anatomical features may also include a pre-specified set of symbols for labeling a suspected tumor in the lung, heart, and lung and / or heart tissue. intervention It is labeled or marked by annotations in the previous image.

[0031]

[0040] The anatomical features are compared to tool features of the candidate tools at S220. The anatomical features are compared to tool features of the candidate tools at S220 by the controller 122 of the computer 120 of FIG. 1A. The candidate tools are used to compare the anatomical features of various types of anatomical tissue. intervention Each candidate type of procedure is different. As a result, the anatomical and tool characteristics are: intervention The various candidate types of procedures may differ individually or both. As an example, the minimum width or height of an anatomical opening or passage may vary for a particular candidate type. interventionThe diameter of the tool that will pass through or through the passageway during the procedure. Thus, S220 includes comparing the anatomical feature with tool features of the candidate tools for use in each of the multiple candidate types. By way of example and not limitation, examples of tool features that may be considered for suitability in comparison to the anatomical feature include tool stiffness / flexibility, dexterity of tool components, or shape along the length or tip of the tool.

[0032]

[0041] therapeutic intervention Especially in ablation procedures, the size of the tool is important and is compared to the anatomical features in S220. For example, in ablation procedures, the diameter or length of a resection needle is compared to the anatomical features to determine whether a resection needle is appropriate or whether the ablation should be performed by a tool other than a needle.

[0033]

[0042] In S230, anatomical motion is modeled. Modeling of anatomical motion in S230 may be performed by the controller 122 of the computer 120 of FIG. 1A. Alternatively, modeling of anatomical motion in S230 may be performed by the controller 122 of the computer 120 of FIG. 1A. intervention The modeling of anatomical motion in S230 may be performed outside the system 100 of FIG. 1A, based on previous imaging, etc., and provided to the controller 122 of the computer 120 of FIG. 1A. The modeling of anatomical motion in S230 may also be performed based on actual observed motions, such as breathing or heartbeat, based on various candidate types of motions. intervention The modeling in S230 may be incorporated into a feasibility report for each of the multiple candidate types, as described below with respect to S240. Thus, S230 includes a method for modeling multiple candidate types based on the predicted behavior of each of the multiple candidate types. intervention This includes modeling the anatomical movements expected from each of the procedures. The modeling in S230 includes, for example, measuring the maximum expansion of parts of the anatomy during breathing or based on the heartbeat, with observations made over a number of cycles, such as 50 or 100 breaths.

[0034]

[0043] In the case of ablation, the expected ablation zone motion is modeled in S230 and incorporated into the feasibility report in S240. In the case of ablation, modeling is used to ensure that the ablation zone is properly located so that the appropriate tissue is removed during ablation. The ablation zone is predicted or determined as a function of both tool characteristics as well as tissue motion, and this prediction or determination is made based on the relationship between the tool and tissue motion.

[0035]

[0044] At S240, a feasibility report is generated for each of the plurality of candidate types. The feasibility report is generated by the controller 122 of the computer 120 of FIG. 1A. The feasibility report may include a total score reflecting the feasibility of each candidate type, as well as qualitative and / or quantitative information about individual aspects of each candidate type. grade and / or score. The aggregate score is the weighted feasibility score for each feasibility report. grade Feasibility grade Based on the comparison in S220, intervention A numeric, alphabetic, or alphanumeric characterization of the procedure grade and for some candidate type intervention The procedure can be applied to other candidate types intervention Each feasibility report includes a feasibility report that can be used to rank treatments against each other or to evaluate separately. grade Feasibility grade is feasibility grade It may also be a feasibility score, such as where is simply a numerical value. grade The weighting of varies based on the different expected diagnostic yields for the various candidate types. Each feasibility report generated in S240 includes a feasibility report that includes a different weighting for each of the multiple candidate types. grade For example, interventionOne candidate type of treatment presents an inherent risk relative to another candidate type and, as a result of that inherent risk, is weighted less heavily than the other candidate types. Thus, S240 includes generating a feasibility report for each of the multiple candidate types based on the identification in S210 and the comparison in S220. grade Examples of qualitative and / or quantitative characteristics that may be included in or reflected in the intervention One or more of the experiences of the operator performing the procedure and the location of the anatomy intervention the relative location of a target location for treatment; intervention and patient health status characteristics of the patients to be treated. grade differs from other feasibility reports based on the qualitative and / or quantitative characteristics contained or reflected in the feasibility report.

[0036]

[0045] The feasibility report generated by S240 also intervention Regarding procedure type intervention predicted to successfully reach the target site of intervention Define the tools. For example, if endobronchial biopsy is the candidate type of choice and a 5F catheter is the optimal catheter to use to reach the biopsy site. intervention The tool features are identified as the candidate type intervention Treatment and intervention The optimal intervention Both the tool and the order are used as inputs for the selection. If multiple tools are selected, the order in which the tools are used is also included in the feasibility report.

[0037]

[0046] In one embodiment, multiple feasibility reports are generated for a single candidate type. For example, if there are multiple possible paths to a target location for a candidate type, each possible path is provided with its own feasibility report. In another example, multiple different tools may interventionEach different tool or combination of feasible tools is provided with its own feasibility report when used in alternative scenarios to reach treatment goals. grade And / or the feasibility report with the highest score is selected as the single candidate type feasibility report to be compared with other candidate type feasibility reports for selection in S260, as described below.

[0038]

[0047] At S250, a heat map is generated that can be used for a variety of purposes. The heat map can be generated by the controller 122 of the computer 120 of FIG. 1A and displayed on the display 130 of FIG. 1A. For example, the heat map can be used to display a graph of the anatomical structure of the tissue. intervention Another heat map shows the feasibility of multiple routes to at least one target of treatment by various tissues in the anatomy. intervention The heatmap visually reflects the feasibility report, or aspects of the feasibility report, generated in S240. As an example, the feasibility report is based on or consists of a feasibility heatmap over the entire lung. For example, the feasibility heatmaps in Figures 6 and 8 described below are color coded to indicate high risk biopsy plans in red and low risk biopsy plans in blue. In another embodiment, data from previous biopsy cases of similar patients with similar anatomies are used to generate such heatmaps in S250.

[0039]

[0048] S260: The highest qualitative and / or quantitative outcome from the feasibility report generated in S240 grade and / or based on the score, intervention A treatment type is selected. The selection in S260 is made by the controller 122 of the computer 120 of FIG. 1A. Thus, S260 includes selecting the best treatment type among a plurality of candidate types based on the feasibility report of each of the plurality of candidate types. intervention The selection in S260 also includes selecting the treatment type. interventionSelection of candidate tools for treatment is also included. For example, a tool may be intervention It is suitable for one type of procedure, but not another. The S260 selection includes intervention Various tools are taken into consideration so that a candidate tool suitable for the procedure is selected.

[0040]

[0049] In S270, intervention The treatment is the optimal one selected in S260. intervention The procedure type is used to perform the procedure on the anatomy. intervention The procedure may be a biopsy or a treatment type such as excision. intervention Sometimes it’s a procedure. intervention The procedure is performed under the guidance of the system 100 of FIG. 1A. intervention The actions may be performed immediately following performance of S210 through S260, or may be performed at a later time, such as at a later date, week, or even month. intervention As an example of the procedure, the optimal intervention There is a specific type of lung biopsy that is selected as the procedure type. intervention During the procedure, intervention For various purposes, such as verifying that the tools used in the procedure are of the expected or predicted shape, intervention The image is displayed on the display 130. Alternatively, or in addition, the image displayed on the display 130 may be used to ascertain mechanical features related to the anatomical tissue.

[0041]

[0050] Implemented in S280 and S270 intervention The clinical results of the procedure are fed back to the artificial intelligence engine. intervention Clinical outcomes and other information related to the treatment are fed back to the AI ​​system 140 from the controller 122 of the computer 120 of FIG. intervention This may be determined immediately after the procedure or much later, e.g., as a clinical outcome. interventionSince confirmation that a procedure was successful may take weeks or even months, clinical results indicating success may need to be delayed before being fed back to the AI ​​engine 142 of the AI ​​system 140 of FIG. 1A. The features used to generate the subsequent feasibility report include: intervention Based on the output from the AI ​​engine 142 based on the previous clinical results of the procedure. intervention The AI ​​system 140 may include feeding back clinical results of the treatment to the AI ​​system 140 and incorporating this feedback into the artificial intelligence to make future selections as in S260. For example, the computer 120 may store and execute an AI application that interfaces and interacts with the AI ​​system 140. The AI ​​application of the computer 120 may be used to provide input to the AI ​​system 140 such that the AI ​​system 140 makes the selection in S260, or may be used to obtain updated algorithms and / or updated models from the AI ​​system 140 based on the artificial intelligence implemented in the AI ​​system 140 such that the controller 122 of the computer 120 makes the selection in S260. The AI ​​system 140 may intervention Optimal based on previous instances of the procedure interventionIt is used interactively to select the procedure type and the most suitable tools. For example, in one embodiment, information available from previous biopsies from the patient, the corresponding success / failure outcomes, and actual risk measurements can be used to train a model for predicting the feasibility score. The feasibility score consists of a single numerical value for each node or other target in the patient's body, with a separate feasibility score for each path through the considered anatomical tissue, including each of multiple paths to the same target. For example, the higher the numerical feasibility score, the more likely the clinical outcome will be successful. Logistic regression is used to map the success / failure outcomes and actual risk measurements to determine the appropriate weighting of the inputs in generating the feasibility score. Training of the AI ​​engine 142 of the AI ​​system 140 is also performed with data from patients with similar criteria, such as node size, location, anatomical size, family history, etc., to ensure that the score calculation is as realistic as possible.

[0042]

[0051] Feedback in S280 also includes feedback from medical intervention, such as from sensors (not shown) on a sensor-equipped tool. intervention Determining the three-dimensional position of some or all of the tools during the procedure; intervention Providing real-time images of the anatomy during the procedure; intervention Quantifying tissue characteristics during a procedure, or intervention It is possible to provide mechanical feedback during the procedure, or a combination of both. intervention Data collected from sensors on sensor-equipped tools during a procedure is used to intervention The type of procedure and tool is fed back to the AI ​​system 140 to analyze whether it produced the desired results. Deviations from expectations, such as deviations from predicted path or anticipated tool shape, can be used as feedback to the AI ​​engine 142 to improve tool predictions and feasibility reporting. Force or pressure sensors provide an indication of whether the tool is interacting with tissue in an undesirable manner.

[0043]

[0052] intervention Images are also fed back in S280. For example, intervention In the image, intervention It is verified that the tools used in the procedure produced the desired results. intervention Images are fed back to the AI ​​system 140 of FIG. 1A from an ultrasound system (not shown) or an x-ray system (not shown).

[0044]

[0053] The S290 model was developed based on feedback from the S280, as well as other intervention The model is trained based at least in part on feedback from the treatment. The model is trained by the AI ​​system 140 of FIG. 1A, and the training is performed according to the method described herein. intervention For future instantiations of treatment optimization, intervention The artificial intelligence is applied to select the treatment type in S260. The model trained in S290 also selects the optimal treatment type selected in S260. intervention The feasibility report of each of the various candidate types is thus based on the same model trained in S290. intervention Procedure type feasibility report and intervention and training a model based on the feasibility reports and clinical outcomes of the treatment. The model trained in S290 is trained based on the feasibility reports and clinical outcomes of the plurality of patients and is constrained by similarity for at least one health state characteristic of the plurality of patients.

[0045]

[0054] An interface or connection between the AI ​​system 140 and the controller 122 allows the controller 122 to obtain a model to perform the operations of Fig. 2, such as S220, S240, and S260. Alternatively, some operations, such as S220, S240, and / or S260, are performed by the AI ​​system 140 or by a software program executing on the computer 120 in communication with the AI ​​system 140.

[0046]

[0055] In addition, intervention Many tools used in procedures have smart sensing capabilities. Smart sensing refers to automatic sensing by sensors on the sensor-equipped tool. The sensor-equipped tool can be used to determine the three-dimensional position of part or all of the tool. For example, the sensors on the tool can be used to track the position of the tool by electromagnetic tracking or optical shape sensing. The sensor-equipped tool can also be used to obtain real-time images of anatomical tissue. For example, the sensors on the tool are used for imaging including ultrasound, optical coherence tomography, and x-ray. The sensor-equipped tool is also used to quantify tissue features. For example, the sensors on the tool are used to quantify tissue features with diffuse reflectance spectroscopy or Raman spectroscopy. The sensor-equipped tool is also used to provide mechanical feedback. For example, the sensors on the tool include force sensors or pressure sensors. Any of these sensors, or a combination of sensors, can also be used as feedback to the AI ​​engine 142. For example, a tool equipped with optical shape sensing technology can continuously provide information about its 3D shape and position. This information can be compared to the predicted shape and path the tool should have taken, and any deviations from the predicted path or shape can be used as feedback to the AI ​​engine 142 to improve tool predictions and feasibility reports. Force or pressure sensors also provide an indication of whether the tool is interacting with tissue in an undesirable manner. Readings from sensors on the sensor-equipped tool are provided as feedback to the AI ​​engine 142 to improve predictions of candidate tool performance and thus feasibility reports. That is, the inputs to the AI ​​engine 142 include the characteristics of the sensor-equipped tool and the data sensed by the sensors on the sensor-equipped tool.

[0047]

[0056] After the model is trained in S290, the method in Figure 2 returns to S210 to perform another intervention Anatomical features for treatment optimization are identified.

[0048]

[0057] FIG. 3 is a block diagram of a system according to a representative embodiment of the present invention; intervention 1 shows an outline of artificial intelligence for treatment optimization.

[0049]

[0058] As shown in FIG. 3, an artificial intelligence system 340 receives as input a number of different types of data from a number of modalities and performs intervention Outputs clinical judgment to be used in determining the type of treatment, once performed intervention 1A , the artificial intelligence system 340 may be the AI ​​system 140 of FIG. 1A , but the artificial intelligence system may be remote or proximate to the computer 120 of FIG. 1A . In one embodiment, the artificial intelligence system 340 is fully or partially implemented within the computer 120 of FIG. 1A , such that a medical professional can obtain the recommendation by the artificial intelligence system 340 directly from the computer 120 of FIG. 1A . In another embodiment, the computer 120 provides one or more of a plurality of different types of data from a plurality of modalities to the artificial intelligence system 340, and obtains the clinical judgment from the artificial intelligence system 340. In yet another embodiment, the artificial intelligence described herein is distributed between the computer 120 and the artificial intelligence system 340. The artificial intelligence system 340 may include, for example, a software-based artificial intelligence engine, as discussed with respect to the AI ​​engine 142. For example, the AI ​​engine 142 is implemented in the artificial intelligence system 340. The clinical judgment output from the artificial intelligence system 340 may indicate whether the patient was optimally selected based on the multi-modal input. intervention Stratified into groups corresponding to type of procedure.

[0050]

[0059] The artificial intelligence system 340 integrates the multimodal data to generate a clinical decision as an output. The multimodal data is provided to the artificial intelligence system 340 from the computer 120 of FIG. 1A as well as from other sources (not shown). The multimodal data shown in FIG. 3 includes, but is not limited to, imaging by type 343, medical risk 344, procedure cost 345, operator experience 346, and technical feasibility by type 347. The imaging 343 may be any type of imaging, such as computed tomography imaging, MR imaging, or ultrasound imaging. intervention Imaging 343 may also include other imaging techniques, such as x-ray imaging or ultrasound imaging. intervention It can be or include imaging. Imaging 343 intervention Imaging is used to verify that the tools used had the correct predicted shape or mechanical characteristics with respect to the anatomy. Medical risks 344 are the risks associated with each type of intervention The procedure cost 345 includes the monetary cost of performing the procedure, such as the services of a skilled professional, the use of specific equipment and / or facilities, and costs for recovery, such as using facilities for recovery. Operator experience 346 is intervention The experience of the personnel performing the procedure, based on the time spent performing similar procedures or on a number of similar procedures performed by that personnel. Technical feasibility 347 is the ability to perform each type of procedure, such as a type of biopsy, for a particular anatomy and condition of the patient. intervention Treatment grade A risk score can be generated by the artificial intelligence system 340 from the technical feasibility 347. For example, if a nodule or other target is very close to a blood vessel, there is a very high probability that the blood vessel will be hit during the biopsy because the planned path will pass through the blood vessel, or because the blood vessel is located directly behind the nodule or other target. The output of the artificial intelligence system 340 is a risk score for each type of biopsy being considered. interventionA quantification of the feasibility of a procedure, including the corresponding success rate and risk factor score. intervention It is determined using a historical database of treatment types. Risk factor scores are calculated based on success rates, failure rates, and similar. intervention Based on the complication rates of different types of complications resulting from performing the procedure type. Clinical decisions are made for each patient based on quantification. Feedback of the obtained clinical results helps to ensure continuous performance improvement.

[0051]

[0060] Applying the artificial intelligence of the artificial intelligence system 340 generates a variety of possible types of intervention The feasibility of the procedure is determined and provided in a feasibility report. In the biopsy example, a feasibility score is generated for each nodule requiring a biopsy by biopsy method. The feasibility report includes the imaging 343 intervention The previous image, intervention A feasibility score is included that is calculated for each biopsy procedure based on data from the previous images as well as information from one or more other modes of input to the artificial intelligence system 340. Data from the images includes, but is not limited to, node location and anatomical structures including or near the nodes, blood vessels, bone structures, and organs at risk. Other data that contribute to the feasibility score includes laboratory results such as blood tests, as well as procedure specific data such as the gauge of the biopsy needle.

[0052]

[0061] FIG. 4 illustrates a block diagram of a system according to a representative embodiment. intervention 1 illustrates a controller for generating a feasibility report of treatment optimization.

[0053]

[0062] In FIG. 4, the controller 122 intervention The anatomical structure of the tissue along with the tool characteristics of the candidate tools to be used in each of the procedures. intervention The controller 122 receives a previous image of the anatomical structure. intervention For multiple candidate types of procedures, anatomical features are compared with anatomical tissues. interventionThe controller 122 also compares the anatomical features to tool features of a candidate tool for use with each of a plurality of candidate types, including, for example, anatomical dimensions and tool dimensions.

[0054]

[0063] In one embodiment, intervention The procedure was a lung biopsy. intervention The previous image is a computed tomography (CT) image. In an endobronchial biopsy of lung tissue, computed tomography images are used to find airways and calculate the diameter of the airways at various locations, to find blood vessels associated with the airways and nodules, and to find nodule locations. The airways and airway diameters, blood vessels, and nodule locations are obtained manually or by utilizing computer-aided tools that perform automated image analysis. The dimensions and mechanical properties of the anatomical tissue serve as inputs to a feasibility calculator implemented by the controller 122. A list of candidate biopsy tools is also provided to the controller 122, including biopsy tool details including tool dimensions such as length, width, and diameter, as well as tool mechanical properties. For example, the maximum curvature or bending ability of the tool, the maneuverability of the tool, and other similar types of details are used to determine whether the tool can be mechanically moved through the airways. As another example, the feasibility calculator implemented by the controller 122 calculates the shortest path from the trachea through the airways to the nodule.

[0055]

[0064] FIG. 5 illustrates a block diagram of a system according to a representative embodiment. intervention In treatment optimization intervention 1 shows the treatment route plan.

[0056]

[0065] In Figure 5, intervention The shortest path to the treatment target is calculated, such as by controller 122 in Figure 4 or controller 122 in computer 120 in Figure 1A. Path planning is performed by starting at the node, locating the airway closest to the node, and walking through the airway until the trachea is reached. The diameter of the airway and the maximum curvature of the planned path are then calculated for this type of interventionThe available tool dimensions, such as diameter, and bendability of the various tools required for the procedure are compared. This generates a feasibility score for the node, as in S240 of FIG. 2. The path planning of FIG. 5 is a single type intervention For multiple different routes of treatment and / or multiple different types of intervention For example, intervention One type of procedure requires passage through a first portion of the anatomy but not through a second portion of the anatomy, whereas another type of procedure requires passage through a first portion of the anatomy but not through a second portion of the anatomy. intervention The procedure requires passage through a second portion of the anatomy, but not through a first portion of the anatomy.

[0057]

[0066] FIG. 6 illustrates a block diagram of a system according to a representative embodiment. intervention 1 shows a feasibility map of treatment optimization.

[0058]

[0067] Figure 6 shows an example of two feasibility scores for an endobronchial biopsy for the example used in Figure 6. If the nodule is in a peripheral part of the lung that is difficult to reach with the available tools and small airways, the feasibility score would be low. However, if the nodule is close to the trachea and multiple different biopsy tools are available, the feasibility score would be high.

[0059]

[0068] The controller 122 of FIG. 1A and FIG. 4 may also be of other types. interventionThe feasibility report of the procedure is used to generate. For example, a transthoracic biopsy of lung tissue is suggested for a lung biopsy. Pre-operative images, such as computed tomography images, are analyzed to find the location of the node, blood vessels, rib cage and organs on the path to the node, which serve as inputs to a feasibility calculator implemented by the controller 122. The size and mechanism of the available tools are also used as inputs to the controller 122. For example, knowing the distance the biopsy needle travels in the tissue after it is "fired" is important to avoid overshooting, where an overshooting needle may puncture critical tissue and / or organs. The distance traveled by the biopsy needle is important for nodes close to the heart or large blood vessels. Information from the computed tomography images is used to calculate an optimal planned path to the node. Again, a feasibility score is provided for each node, as described below with respect to FIG. 7.

[0060]

[0069] FIG. 7 illustrates a block diagram of a system according to a representative embodiment. intervention Another approach in treatment optimization intervention 1 shows the treatment route plan.

[0061]

[0070] As shown in Figure 7, a lung model is used to project a path between the ribs for the transthoracic needle to reach the target location (node). The lung model can be a generic model applicable to many, even most, patients, or it can be customized according to the anatomical details of a particular patient. The path planning in Figure 7 is performed by the controller 122 of the computer 120 in Figure 1A.

[0062]

[0071] FIG. 8 illustrates a block diagram of a system according to a representative embodiment. intervention 13 shows another feasibility map for treatment optimization.

[0063]

[0072] Figure 8 shows two nodes with different actionability scores based on the path planning of Figure 7. The node close to the periphery of the lung is closer to the rib cage and therefore has a higher actionability score. The node deep within the lung and located behind the ribs is more difficult to reach with the available biopsy needle and therefore has a lower actionability score.

[0064]

[0073] A similar analysis is presented for surgical biopsies as presented above for endobronchial (FIGS. 4, 5, and 6) and transthoracic (FIGS. 7 and 8) biopsies. The analysis is performed by the controller 122 of the computer 120 of FIG. 1A. For all three biopsy techniques (Biopsy approaches) In the method, respiratory motion or lung deflation is also modeled, as in S230 of Figure 2. This motion modeling serves as an additional input to the feasibility calculator implemented by the controller 122 to improve prediction of technique feasibility.

[0065]

[0074] FIG. 9 illustrates a cross-sectional view of a second exemplary embodiment of the present invention. intervention 1 illustrates a computer system on which the method for treatment optimization is implemented.

[0066]

[0075] The computer system 900 of Figure 9 shows a complete set of components for a communications or computing device. However, a "controller" as described herein may be implemented with less than the set of components shown in Figure 9, such as with a combination of memory and a processor. intervention In the form of a system for treatment optimization, it may include some or all of the elements of one or more component devices, although any such device may not necessarily include one or more of the elements described for computer system 900, and may include other elements not described.

[0067]

[0076] 9, computer system 900 includes a set of software instructions that can be executed to cause computer system 900 to perform any of the methods or computer-based functions disclosed herein. Computer system 900 operates as a stand-alone device or is connected to other computer systems or peripheral devices, for example, using a network 901. In various embodiments, computer system 900 performs logical processing based on digital signals received via an analog-to-digital converter.

[0068]

[0077] In a networked deployment, the computer system 900 operates in the capacity of a server, or as a client user computer in a server-client user network environment, or as a peer computer system in a peer-to-peer (or distributed) network environment. The computer system 900 can also be implemented as or incorporated in a variety of devices, such as the computer 120 of FIG. 1A, a stationary computer, a mobile computer, a personal computer (PC), a laptop computer, a tablet computer, or any other machine capable of executing a set of software instructions (sequential or otherwise) that specify operations to be performed by the machine. The computer system 900 can be implemented as or incorporated in an integrated system that includes additional devices. In one embodiment, the computer system 900 can be implemented using electronic devices that provide voice, video, or data information. Additionally, although the computer system 900 is illustrated in the singular, the term "system" is also intended to include any collection of systems or subsystems that individually or jointly execute a set or sets of software instructions to perform one or more computer functions.

[0069]

[0078] As shown in FIG. 9, the computer system 900 includes a processor 910. The processor 910 may be considered as a representative example of the processor 12210 of the controller 122 of FIG. 1B and executes instructions to perform some or all aspects of the methods and processes described herein. The processor 910 is tangible and non-transient. The term "non-transient" as used herein should be interpreted as a property of a state that persists for a period of time, rather than as a permanent property of a state. The term "non-transient" specifically negates transitory properties, such as properties of a carrier wave or signal, or other forms of properties that exist only temporarily at any time and place. The processor 910 is an article of manufacture and / or a machine component. The processor 910 is configured to execute software instructions to perform the functions described in various embodiments herein. The processor 910 may be a general-purpose processor or part of an application specific integrated circuit (ASIC). The processor 910 may also be a microprocessor, a microcomputer, a processor chip, a controller, a microcontroller, a digital signal processor (DSP), a state machine, or a programmable logic device. The processor 910 may also be a logic circuit including a programmable gate array (PGA), such as a field programmable gate array (FPGA), or another type of circuit including discrete gate and / or transistor logic. The processor 910 may be a central processing unit (CPU), a graphics processing unit (GPU), or both. Additionally, any processor described herein may include multiple processors, parallel processors, or both. Multiple processors may be included in or coupled to a single device or multiple devices.

[0070]

[0079] As used herein, the term "processor" encompasses an electronic component capable of executing a program or machine-executable instructions. References to a computing device with a "processor" should be interpreted to include multiple processors or processing cores, such as a multi-core processor. A processor may also refer to a collection of processors within a single computing system or a collection of processors distributed among multiple computing systems. The term computing device should also be interpreted to include a collection or network of computing devices, each of which includes a processor. A program comprises software instructions that are executed by one or more processors, which may be within the same computing device or distributed across multiple computing devices.

[0071]

[0080] The computer system 900 further includes a main memory 920 and a static memory 930, the memories in the computer system 900 communicating with each other and with the processor 910 via a bus 908. Either or both of the main memory 920 and the static memory 930 may be considered representative of the memory 12220 of the controller 122 of FIG. 1B, storing instructions used to implement some or all aspects of the methods and processes described herein. The memory described herein is a tangible storage medium for storing data and executable software instructions, and is non-transient while the software instructions are stored therein. The term "non-transient" as used herein should be interpreted as a characteristic of a state that persists for a period of time, rather than as a permanent characteristic of a state. The term "non-transient" specifically negates the characteristics of a transitory nature, such as the characteristics of a carrier wave or signal or other forms that exist only temporarily at any time and place. The main memory 920 and the static memory 930 are articles of manufacture and / or machine components. The main memory 920 and the static memory 930 are computer-readable media from which data and executable software instructions can be read by a computer (e.g., the processor 910). Each of the main memory 920 and the static memory 930 is implemented as one or more of a random access memory (RAM), a read-only memory (ROM), a flash memory, an electrically programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a register, a hard disk, a removable disk, a tape, a compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a floppy disk, a Blu-ray disk, or other form of recording medium known in the art. The memory may be volatile or non-volatile, secure and / or encrypted, non-secure and / or non-encrypted.

[0072]

[0081] A "memory" is an example of a computer-readable storage medium. Computer memory is any memory that is directly accessible to a processor. Examples of computer memory include, but are not limited to, RAM memory, registers, and register files. References to "computer memory" or "memory" should be construed as multiple memories in some cases. A memory may be, for example, multiple memories within the same computer system. A memory may also be multiple memories distributed among multiple computer systems or devices.

[0073]

[0082] As shown, computer system 900 further includes a video display unit 950, such as, for example, a liquid crystal display (LCD), an organic light emitting diode (OLED), a flat panel display, a solid state display, or a cathode ray tube (CRT). In addition, computer system 900 includes input device(s) 960, such as a keyboard / virtual keyboard, a touch sensitive input screen, or voice input with voice recognition, and a cursor control device 970, such as a mouse, a touch sensitive input screen, or a pad. Computer system 900 also optionally includes a disk drive unit 980, a signal generating device 990, such as a speaker or a remote control, and / or a network interface device 940.

[0074]

[0083] In one embodiment, as shown in FIG. 9, the disk drive unit 980 includes a computer readable medium 982 having one or more sets of software instructions 984 (software) embedded therein. The set of software instructions 984 is read from the computer readable medium 982 for execution by the processor 910. Furthermore, the software instructions 984, when executed by the processor 910, perform one or more steps of the methods and processes described herein. In one embodiment, the software instructions 984 reside, in whole or in part, in the main memory 920, the static memory 930, and / or the processor 910 during execution by the computer system 900. Furthermore, the computer readable medium 982 includes the software instructions 984 or receives and executes the software instructions 984 in response to a propagated signal, whereby devices connected to the network 901 communicate voice, video, or data over the network 901. The software instructions 984 are transmitted or received over the network 901 by the network interface device 940.

[0075]

[0084] In one embodiment, dedicated hardware implementations such as application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), programmable logic arrays, and other hardware components are constructed to perform one or more of the methods described herein. One or more embodiments described herein may perform functions using two or more specific interconnected hardware modules or devices, along with associated control and data signals that can be communicated between and through the modules. Thus, the present disclosure encompasses software, firmware, and hardware implementations. Nothing in this application should be construed as being implemented or capable of being implemented solely in software, rather than by hardware such as a tangible non-transitory processor and / or memory.

[0076]

[0085] According to various embodiments of the present disclosure, the methods described herein are implemented using a hardware computer system executing a software program. Furthermore, in exemplary non-limiting embodiments, implementations may include distributed processing, component / object distributed processing, and parallel processing. A virtual computer system process may perform one or more of the methods or functions described herein, and a processor described herein may be used to support a virtual processing environment.

[0077]

[0086] therefore, intervention Treatment optimization allows for the following: intervention This allows for automated determination of the type of treatment optimization. intervention Treatment optimization is not limited to application to the lungs, but rather is applicable to other organs where multiple biopsy procedures are feasible. intervention Treatment optimization is not limited to biopsies, but rather involves multiple techniques. (approaches) viable resection or other type of therapeutic option intervention Other types of intervention It is also applicable to treatment.

[0078]

[0087] intervention Although treatment optimization has been described with reference to certain exemplary embodiments, it should be understood that the words used are words of description and illustration, rather than words of limitation. Changes may be made within the scope of the appended claims as presently described and amended. intervention It is to be added without departing from the scope and spirit of treatment optimization in its aspects. intervention Although treatment optimization has been described with reference to specific means, materials and embodiments, intervention Treatment optimization is not limited to the specifics disclosed, but rather intervention Treatment optimization extends to all functionally equivalent structures, methods and uses, as fall within the scope of the appended claims.

[0079]

[0088] The drawings of the embodiments described herein are intended to provide a general understanding of the structure of the various embodiments. The drawings do not serve as a complete description of all of the elements and features of the disclosure described herein. Many other embodiments will become apparent to those skilled in the art upon review of the present disclosure. Other embodiments may be utilized and derived from the present disclosure, such that structural and logical substitutions and modifications may be made without departing from the scope of the present disclosure. In addition, the drawings are merely symbolic and may not be drawn to scale. Some dimensions in the drawings may be exaggerated and other dimensions may be minimized. Thus, the present disclosure and the drawings should be considered illustrative and not limiting.

[0080]

[0089] One or more embodiments of the present disclosure may be referred to herein, individually and / or collectively, under the term "invention" for the sake of mere convenience and without any intention of intentionally limiting the scope of the present application to any particular invention or inventive concept. Furthermore, although specific embodiments are illustrated and described herein, it should be understood that any subsequent configurations designed to achieve the same or similar purpose may be substituted for the specific embodiment illustrated. The present disclosure is intended to encompass any and all subsequent modifications or variations of the various embodiments. Combinations of the above embodiments, as well as other embodiments not specifically described herein, will be apparent to those of skill in the art upon review of this specification.

[0081]

[0090] The Abstract of the Disclosure is provided for purposes of compliance with 37 C.FR §1.72(b) and is not intended to be used to interpret or limit the scope or meaning of the claims. In addition, in the above Detailed Description, various features have been grouped together or described in a single embodiment for the purpose of streamlining the disclosure. This disclosure should not be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as reflected in the appended claims, inventive subject matter is directed to less than all of the features of any of the disclosed embodiments. That is, the appended claims are incorporated herein in the Detailed Description, with each claim standing on its own to define separately claimed subject matter.

[0082]

[0091] The foregoing description of the disclosed embodiments is presented to enable those skilled in the art to practice the concepts described in this disclosure. As such, the subject matter disclosed above should be considered as illustrative and not limiting, and the appended claims are intended to embrace all such modifications, enhancements, and other embodiments that fall within the true spirit and scope of the present disclosure. Thus, to the full extent permitted by law, the scope of the present disclosure should be determined by the broadest permissible interpretation of the following claims and their equivalents, and should not be limited or restricted by the foregoing detailed description. Various aspects of the present invention will be described below. (Appendix 1) 1. A controller for interventional procedure optimization, comprising: A memory for storing instructions; a processor for executing the instructions, the instructions, when executed by the processor, causing the controller to: identifying anatomical features from a pre-intervention image of an anatomical tissue for each of a plurality of candidate types of interventional procedures for the anatomical tissue; comparing the anatomical features to tool features of candidate tools for use with each of the plurality of candidate types; generating a feasibility report for each of the plurality of candidate types based on said identifying and said comparing, each feasibility report including a viability grade for each of the plurality of candidate types; selecting an optimal intervention type among the plurality of candidate types based on the feasibility report for each of the plurality of candidate types; and wherein the interventional procedure is performed on the anatomical tissue using the optimal interventional procedure type based on the selecting. (Appendix 2) 2. The controller of claim 1, wherein the processing performed when the processor executes the instructions further includes automatically detecting a target location for the interventional procedure as one of the anatomical features identified by identifying an anatomical feature from a pre-interventional image of the anatomical tissue, and wherein the multiple candidate types of interventional procedures include an intra-airway biopsy of lung tissue through an airway, a transthoracic biopsy of lung tissue through the thoracic cavity, and a surgical biopsy of lung tissue performed by surgery. (Appendix 3) The process performed when the processor executes the instructions further comprises: generating a plurality of feasibility reports of a candidate type of the plurality of candidate types of the intervention using different paths to the target of the intervention based on the identifying and comparing; and selecting a feasibility report of one candidate type from the plurality of candidate types to be compared with the feasibility reports of the plurality of candidate types for selecting the optimal intervention procedure type based on the feasibility report of each separate path. (Appendix 4) The process performed when the processor executes the instructions further comprises: generating a plurality of feasibility reports of a candidate type of the plurality of candidate types of the intervention using different tools to reach the target of the intervention based on the identifying and comparing; and selecting a feasibility report of one candidate type from the plurality of candidate types to be compared with the feasibility reports of the plurality of candidate types for selecting the optimal intervention procedure type based on the feasibility report of each separate tool. (Appendix 5) 2. The controller of claim 1, wherein the weighted feasibility grade for each feasibility report varies based on at least one of an operator's experience performing the interventional procedure for each of the plurality of candidate types, a relative location of a target location for the interventional procedure within the anatomical tissue, or a health status characteristic of a patient to be targeted by the interventional procedure. (Appendix 6) 2. The controller of claim 1, wherein the weighting of the feasibility grade varies for each of the plurality of candidate types of the interventional procedure based on different predicted diagnostic rates for each of the plurality of candidate types. (Appendix 7) 2. The controller of claim 1, wherein the processing performed when the processor executes the instructions further comprises feeding back clinical results of the interventional procedure to an artificial intelligence engine, wherein the features used to generate each feasibility report are based on output from the artificial intelligence engine based on previous clinical results of the interventional procedure, and wherein features of a sensor-equipped tool are included in the input to the artificial intelligence engine from the previous clinical results. (Appendix 8) 2. The controller of claim 1, wherein the anatomical features include at least one of an airway diameter, an airway curvature, an airway elasticity, or an elasticity of tissue surrounding the anatomical tissue targeted by the interventional procedure. (Appendix 9) 2. The controller of claim 1, wherein the anatomical features include a relative position of a target of the interventional procedure within the anatomical tissue and a path to the relative position of the target of the interventional procedure. (Appendix 10) 2. The controller of claim 1, wherein the processing performed when the processor executes the instructions further comprises generating a heat map indicating the feasibility of multiple paths to at least one target of the interventional procedure within the anatomical tissue. (Appendix 11) 2. The controller of claim 1, wherein the processing performed when the processor executes the instructions further comprises generating a heat map indicating relative risk of differentiating interventions by various tissues within the anatomical tissue. (Appendix 12) The process performed when the processor executes the instructions further comprises: modeling expected anatomical motion from each of a plurality of candidate types of interventional procedures; incorporating said modeling into said feasibility report for each of said plurality of candidate types; 2. The controller of claim 1, (Appendix 13) 2. The controller of claim 1, wherein the processing performed when the processor executes the instructions further comprises training a model based on the feasibility report of the optimal intervention type and a clinical outcome of the intervention, wherein the feasibility report of each of the plurality of candidate types is based on the model. (Appendix 14) 14. The controller of claim 13, wherein the model is trained based on feasibility reports and clinical outcomes of a plurality of patients and is constrained by similarity of at least one health characteristic of the plurality of patients. (Appendix 15) the interventional procedure comprises a biopsy; 2. The controller of claim 1, wherein the plurality of candidate types of interventional procedure includes a biopsy type. (Appendix 16) 1. An apparatus for interventional procedure optimization, comprising: an input interface for inputting pre-intervention images of anatomical tissue; a controller including a memory for storing instructions and a processor for executing the instructions; The instructions, when executed by the processor, cause the controller to: identifying anatomical features from the pre-intervention image of an anatomical tissue for each of a plurality of candidate types of interventional procedures for the anatomical tissue; comparing the anatomical features to tool features of candidate tools for use with each of the plurality of candidate types; generating a feasibility report for each of the plurality of candidate types based on said identifying and said comparing, each feasibility report including a viability grade for each of the plurality of candidate types; selecting an optimal intervention type among the plurality of candidate types based on the feasibility report for each of the plurality of candidate types; and an interventional procedure is performed on the anatomical tissue using the optimal interventional procedure type based on the selecting. (Appendix 17) 17. The apparatus of claim 16, wherein the input interface accepts input for selecting and deselecting at least one of a candidate type of interventional procedure, a candidate tool to be used for the candidate type of interventional procedure, and a path through the anatomical tissue to reach a target site for the candidate type of interventional procedure. (Appendix 18) the interventional procedure comprises a biopsy; 17. The apparatus of claim 16, wherein the plurality of candidate types of interventional procedure includes a biopsy type. (Appendix 19) 1. A system for interventional procedure optimization, comprising: an input interface for inputting pre-intervention images of anatomical tissue; a monitor displaying said pre-interventional image of the anatomical structure; a controller including a memory for storing instructions and a processor for executing the instructions; The instructions, when executed by the processor, cause the controller to: identifying anatomical features from the pre-intervention image of an anatomical tissue for each of a plurality of candidate types of interventional procedures for the anatomical tissue; comparing the anatomical features to tool features of candidate tools for use with each of the plurality of candidate types; generating a feasibility report for each of the plurality of candidate types based on said identifying and said comparing, each feasibility report including a viability grade for each of the plurality of candidate types; selecting an optimal intervention type among the plurality of candidate types based on the feasibility report for each of the plurality of candidate types and an optimal tool to use for reaching a target site of the optimal intervention; and an interventional procedure is performed on the anatomical tissue using the optimal interventional procedure type based on the selecting. (Appendix 20) 20. The system of claim 19, wherein the weighting of the feasibility grade is set based on applying artificial intelligence to previous instantiations of the interventional procedure.

Claims

1. A controller for optimizing an intervention, comprising: A memory for storing instructions; a processor for executing the instructions, the processor comprising: For each of a plurality of interventional procedures for a target site including an anatomical structure, identifying an anatomical feature from a pre-intervention image including the target site, the anatomical feature being a feature of an anatomical structure on a path to the target site for that procedure; - for each procedure, comparing the characteristics of the anatomical structure with characteristics of each of a plurality of types of interventional tools available, the comparison being performed on corresponding characteristics of the anatomical structure and the interventional tools; generating, for each technique, a feasibility report based on the comparison, said generating including generating a feasibility grade representative of the feasibility of the technique based on the comparison, each feasibility report including the feasibility grade of the technique; selecting an optimal technique from the plurality of techniques based on a feasibility grade of the feasibility report for each technique; Run The feasibility report of the optimal technique further comprises information defining which of the plurality of types of interventional tools is optimal to use in the optimal technique, the controller.

2. 2. The controller of claim 1, wherein the processor further performs the step of automatically detecting a location of the target site as one of the identified anatomical features, and the multiple techniques of the interventional procedure include an endobronchial biopsy of lung tissue through an airway, a transthoracic biopsy of lung tissue through a thoracic cavity, and a surgical biopsy of lung tissue performed by surgery.

3. The processor further comprises: generating a plurality of feasibility reports for a technique among the plurality of techniques, where a plurality of routes to the target site exist for the technique, and each of the plurality of feasibility reports includes a feasibility grade for a different route; and selecting a feasibility report having a highest feasibility grade from the plurality of feasibility reports for the technique as a feasibility report for the technique. The controller of claim 1 , further comprising:

4. The processor further comprises: generating a plurality of feasibility reports for a technique of the plurality of techniques, the technique having a plurality of intervention tools available, each of the plurality of feasibility reports including a feasibility grade for a different intervention tool; selecting a feasibility report having a highest feasibility grade from among the plurality of feasibility reports of the one technique as a feasibility report of the one technique; The controller of claim 1 , further comprising:

5. 2. The controller of claim 1, wherein the weighted feasibility grade for each feasibility report varies based on at least one of an operator's experience in the approach of that feasibility report, a location of the target site, or a health status characteristic of a patient targeted for the interventional procedure.

6. The controller of claim 1 , wherein the weighting of the feasibility grades differs for each procedure based on a success rate of the intervention procedure.

7. 2. The controller of claim 1, wherein the processor further performs the step of feeding back clinical results of the interventional procedure to an artificial intelligence engine, the clinical results including information regarding success or complications of the interventional procedure, the corresponding features used in the comparison to generate each feasibility report being based on output from the artificial intelligence engine based on previous clinical results of the interventional procedure, and features of a sensor-equipped interventional tool being included in the input to the artificial intelligence engine from the previous clinical results.

8. 2. The controller of claim 1, wherein the anatomical features include at least one of a diameter of an airway in a pathway to the target site, a curvature of an airway in the pathway, an elasticity of an airway in the pathway, and an elasticity of tissue surrounding the target site.

9. The controller of claim 1 , wherein the anatomical features include a location of the target site and features of a path to the location of the target site.

10. 2. The controller of claim 1, wherein the processor further performs the step of generating a heat map indicating a feasibility grade for each path, if there are multiple different paths to the target site calculated for a technique of the plurality of techniques.

11. The controller of claim 1 , wherein the processor further comprises: generating a heat map indicating a viability grade for each target site when multiple target sites are present for the interventional procedure.

12. The processor further comprises: modeling expected target site motion for each of the plurality of techniques; Incorporating said modeling into said feasibility report for each approach; The controller of claim 1 , further comprising:

13. 2. The controller of claim 1, wherein the processor further comprises training a machine learning model based on the feasibility report of the optimal technique and clinical outcomes of the interventional procedure using the optimal technique, the clinical outcomes including information regarding a success or complication of a procedure, and wherein the feasibility report for each of the plurality of techniques is generated based on the trained machine learning model.

14. 14. The controller of claim 13, wherein the machine learning model is trained based on a plurality of patient feasibility reports and clinical outcomes including information regarding treatment success or complications, and is constrained by a similarity of at least one health characteristic of the plurality of patients.

15. the interventional procedure comprises a biopsy; The controller of claim 1 , wherein each of the multiple techniques of the interventional procedure corresponds to a different technique of the biopsy.

Images