Systems and methods for automating clinical workflow decisions and generating priority read indicator

Abstract

To provide favorable systems and methods for automating clinical workflow decisions and generating a priority read indicator.SOLUTION: In a certain aspect, patient data may be collected from multiple data sources, such as imaging data. The patient data may be processed using an artificial intelligence (AI) component. The output of the AI component may be used by healthcare professionals to inform healthcare decisions for patients. The output of the AI component and additional information relating to the healthcare decisions and healthcare paths may be provided as input to a decision analysis component. The decision analysis component may process the input, and output an automated healthcare recommendation that may be used to further inform the healthcare decisions of the healthcare professionals. In some aspects, the output of the decision analysis component may be used to determine a priority or timeline for performing one or more actions relating to patient healthcare.SELECTED DRAWING: None

Description

Technical Field

[0001] (Cross - Reference to Related Applications) This application was filed as a PCT international patent application on July 31, 2020, and claims priority and the benefit thereof to U.S. Provisional Patent Application No. 62 / 881,156, filed on July 31, 2019, entitled "SYSTEMS AND METHODS FOR AUTOMATING CLINICAL WORKFLOW DECISIONS", and U.S. Provisional Patent Application No. 62 / 941,601, filed on November 27, 2019, entitled "SYSTEMS AND METHODS FOR AUTOMATING CLINICAL WORKFLOW DECISIONS AND GENERATING A PRIORITY READ INDICATOR", and the disclosures of U.S. Provisional Patent Application No. 62 / 881,156 and U.S. Provisional Patent Application No. 62 / 941,601 are hereby incorporated by reference in their entirety herein.

Background Art

[0002] (Background) Modern breast care involves the analysis of various complex factors and data points such as a patient's history, the experience of healthcare providers, and the imaging modalities utilized. The analysis enables healthcare providers to determine a breast care path that optimizes the quality of breast care and the patient experience. However, such decisions are subjective and can thus vary widely among healthcare providers. As a result, some patients may be provided with a sub - optimal breast care path, which can lead to increased hospital costs and a diminished patient experience.

[0003] The aspects disclosed herein relate to those and other general considerations. It should also be understood that while relatively specific problems may be considered, the examples are not to be limited to solving the specific problems identified in the background and elsewhere within the present disclosure.

Summary of the Invention

Means for Solving the Problems

[0004] (Summary) Examples of the present disclosure describe systems and methods for automating clinical workflow decisions. In one aspect, patient data can be collected from multiple data sources such as patient records, healthcare provider notes / assessments, imaging data, etc. The patient data can be processed using an artificial intelligence (AI) component. The output of the AI component can be used by a healthcare provider to inform a medical decision regarding one or more patients. The output of the AI component, information related to the healthcare provider's medical decision, and / or complementary medical-related information can be provided as input to a decision analysis component. The decision analysis component can process the input and output an automated medical recommendation that can be used to further inform the healthcare provider's medical decision. In some aspects, the output of the decision analysis component can be used to determine a priority or timeline for performing one or more actions related to a patient's healthcare. For example, the output of the decision analysis component can indicate a priority or level of importance for evaluating a patient's imaging data.

[0005] Aspects of the present disclosure are a system comprising at least one processor and a memory coupled to the at least one processor, the memory comprising computer-executable instructions that, when executed by the at least one processor, implement a method comprising collecting patient data from one or more data sources, providing the patient data to a first artificial intelligence (AI) algorithm to analyze characteristics of the patient data, receiving a first output from the first AI algorithm, providing the first output to a second AI algorithm to determine a clinical workflow decision regarding patient care, receiving a second output from the second AI algorithm, the second output comprising an automated patient care recommendation, and providing the automated patient care recommendation to a healthcare provider.

[0006] Aspects of the present disclosure include collecting patient data from one or more data sources, providing the patient data to a first artificial intelligence (AI) component to analyze characteristics of the patient data, receiving a first output from the first AI component, providing the first output to a second AI component to determine a decision for a clinical workflow related to patient care, receiving a second output from the second AI component, where the second output comprises automated patient care recommendations, and providing the automated patient care recommendations to healthcare providers.

[0007] Aspects of the present disclosure further provide a system comprising at least one processor and a memory coupled to the at least one processor, the memory comprising computer-executable instructions that, when executed by the at least one processor, implement a method comprising collecting image data from one or more data sources, evaluating the image data to identify one or more features, calculating a confidence score based on the one or more features, comparing the confidence score to a threshold, and assigning a high evaluation priority to the image data when the confidence score exceeds the threshold.

[0008] This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. Additional aspects, features, and / or advantages of examples will be described in part in the following description, be apparent in part from the description, or may be learned by practice of the disclosure. The present invention provides, for example, the following. (Item 1) A system, wherein the system comprises at least one processor and a memory coupled to the at least one processor and The memory comprises computer-executable instructions which, when executed by the at least one processor, implement a method that includes collecting patient data from one or more data sources, providing the patient data to a first artificial intelligence (AI) algorithm to analyze characteristics of the patient data, receiving a first output from the first AI algorithm, providing the first output to a second AI algorithm to determine a decision for a clinical workflow related to patient care, receiving a second output from the second AI algorithm, the second output comprising automated patient care recommendations, and providing the automated patient care recommendations to healthcare providers. A system comprising. (Item 2) The system according to item 1, wherein the patient data comprises at least one of digital images of the breast, personal information of the patient, or historical information of the patient. (Item 3) The system according to item 1, wherein the one or more data sources comprise at least one of patient visit information, an electronic medical record (EMR) of the patient, a hospital information system (HIS) record, or a medical imaging system. (Item 4) The system according to item 1, wherein the first AI algorithm provides an assessment of breast density. (Item 5) The system according to item 1, wherein the first output comprises at least one of a category score of breast density, a result of a computer-aided detection marker, characteristics of a radiological measurement, or a result of a breast cancer risk assessment. (Item 6) The method further comprises providing at least a portion of the first output to the healthcare provider, receiving initial patient care recommendations from the healthcare provider, and Using the automated patient care recommendations to complement the initial patient care recommendations The system according to item 1, further comprising (Item 7) The method further comprises collecting, from a patient, one or more digital mammography images during a first visit; providing the one or more digital mammography images to the first AI algorithm to generate the first output; providing the first output to the medical staff and further comprising The first output enables the medical staff to perform one or more diagnostic procedures on the patient during the first visit. The system according to item 1 (Item 8) Supplemental information is further provided to the second AI algorithm to determine a clinical workflow decision regarding patient care, the supplemental information comprising at least one of the patient data, diagnostic reports, and practice guidelines from a clinical community. The system according to item 1 (Item 9) The automated patient care recommendations comprise diagnostic information and recommendations related to at least one of a biopsy procedure, chemotherapy, surgical intervention, radiation therapy, or mammography imaging procedure. The system according to item 1 (Item 10) A method for automating a clinical workflow decision, the method comprising collecting patient data from one or more data sources; providing the patient data to a first artificial intelligence (AI) component to analyze characteristics of the patient data; receiving a first output from the first AI component; providing the first output to a second AI component to determine a clinical workflow decision regarding patient care; receiving a second output from the second AI component, the second output comprising automated patient care recommendations Providing the automated patient care recommendations to healthcare providers A method comprising the above. (Item 11) The method according to item 10, wherein the patient data comprises at least one of digital mammography images, patient personal information, or patient history information. (Item 12) The method according to item 10, wherein the first AI component provides an assessment of the density of the patient's breast. (Item 13) The method according to item 10, wherein the first output comprises at least one of a category score of breast composition, a result of a computer-aided detection marker, a radiographic feature, or a result of a breast cancer risk assessment. (Item 14) The method according to item 10, wherein the second AI component implements at least one of an artificial neural network, a support vector machine (SVM), a linear boosting model, or a random decision forest. (Item 15) The method further comprises providing at least a portion of the first output to the healthcare provider receiving initial patient care recommendations from the healthcare provider using the automated patient care recommendations to complement the initial patient care recommendations The method according to item 10, further comprising the above. (Item 16) The method further comprises collecting one or more digital mammography images from the patient during a first visit providing the one or more digital mammography images to the first AI algorithm to generate the first output providing the first output to the healthcare provider The method further comprises The method according to item 10, wherein the first output enables the healthcare provider to perform one or more diagnostic procedures on the patient during the first visit. (Item 17) The automated patient care recommendation of item 10, comprising diagnostic information and recommendations related to at least one of a biopsy procedure, chemotherapy, surgical intervention, radiation therapy, or a mammography imaging procedure. (Item 18) A system, the system comprising at least one processor, and a memory coupled to the at least one processor, wherein the memory comprises computer-executable instructions that, when executed by the at least one processor, implement a method, the method comprising collecting image data from one or more data sources, evaluating the image data to identify one or more features, calculating a confidence score based on the one or more features, comparing the confidence score to a threshold, and assigning a high evaluation priority to the image data when the confidence score exceeds the threshold. A system as described above. (Item 19) Calculating the confidence score comprises comparing the image data to a set of stored data to identify a similarity between the image data and the set of stored data, the set of stored data comprising labeled image data, and calculating the confidence score based on at least one of an amount of similarity identified between the image data and the set of stored data or a degree of match between the identified similarities. A system as described in item 18. (Item 20) The high evaluation priority causes the image data to be evaluated before a previously received set of image data is evaluated, the previously received set of image data having a lower evaluation priority than the image data. A system as described in item 18.​

Brief Description of the Drawings

[0009] (Brief Description of the Drawings) Non-limiting and non-exhaustive examples are described with reference to the following figures.

[0010]

Figure 1

[0011]

Figure 2

[0012]

Figure 3

[0013]

Figure 4

[0014]

Figure 5

[0015]

Figure 6A

[0016]

Figure 6B

[0017]

Figure 7

DETAILED DESCRIPTION

[0018] (Detailed Description) Medical imaging has become a widely used tool for identifying and diagnosing abnormalities such as cancer or other diseases within the human body. Medical imaging processes such as mammography and tomosynthesis are particularly useful tools for imaging the breast to screen for or diagnose cancer or other lesions associated with the breast. A tomosynthesis system is a mammography system that enables high-resolution imaging of the breast based on limited-angle tomosynthesis. Tomosynthesis generally generates a plurality of X-ray images (for each individual layer or slice of the breast, throughout their thickness). In contrast to previous two-dimensional (2D) mammography systems, a tomosynthesis system acquires a series of X-ray projection images, each of which is obtained at different angular displacements as an X-ray source moves along a path such as an arc above the breast. In contrast to previous computed tomography (CT), tomosynthesis is typically based on projection images obtained with a limited angular displacement of an X-ray source around the breast. Tomosynthesis reduces or eliminates problems caused by tissue overlap and structural noise present in 2D mammography imaging.

[0019] In modern breast care centers, images generated using medical imaging are evaluated by various healthcare providers to determine the best breast care path for a patient. However, this evaluation can be overwhelming considering imaging data and system complexity, patient information and records, hospital information systems, healthcare providers' knowledge and experience, clinical practice guidelines, AI diagnostic systems and outputs, etc. As a result, the evaluation can lead to significantly different medical judgments among healthcare providers. Differences in medical judgments can cause some healthcare providers to offer suboptimal medical paths to some patients. Those suboptimal medical paths can significantly degrade the patient experience.

[0020] Furthermore, medical imaging evaluations typically involve a batch reading process, for which image data regarding a large number (e.g., 100 or more) of screening subjects is collected. Generally, after the screening subjects leave the imaging facility, the collected image data is evaluated (''read'') batch by batch at the convenience of the mammography radiologic technologist. When actionable (or potentially actionable) content is identified within the images evaluated during the batch reading process, each screening subject is ''called back'' (e.g., called back to the imaging facility) for follow-up imaging and / or biopsy. Due to scheduling and other competing factors, the time delay between screening (image acquisition) and the callback can be several days or weeks. This delay can result in an undesirable outcome, e.g., in the case of progressive cancer. The delay can also cause undue stress and anxiety for screening subjects who are ultimately determined to have nothing abnormal.

[0021] To address such challenges associated with suboptimal medical decision-making, the present disclosure describes systems and methods for automating clinical workflow decisions and supporting the decisions of healthcare providers. In one aspect, patient data regarding one or more patients (or “screening subjects”) may be collected from a plurality of data sources accessible by healthcare providers, healthcare facilities, or services affiliated therewith. As used herein, patient data may refer to information related to a patient's name / identifier, personal information, medical images, vital signs, and other diagnostic information, visit history, prior treatments, previously diagnosed medical conditions / disorders / diseases, prescribed medications, etc. Examples of data sources include, but are not limited to, patient visit information, a patient's electronic medical record (EMR), a hospital information system (HIS), and a medical imaging system. In one example, the patient data collection process may be performed manually, automatically, or a combination thereof.

[0022] After collecting patient data, the patient data can be attested to the AI processing component. The AI processing component can utilize one or more rule sets, algorithms, or models. As used herein, a model can refer to a predictive or statistical utility or program that can be used to determine an established distribution of one or more character sequences, classes, objects, result sets, or events and / or to predict a response value from one or more predictors. The model can be based on or incorporate one or more rule sets, machine learning, neural networks, etc. In one example, the AI processing component can process patient data and provide one or more outputs. Exemplary outputs include, but are not limited to, category scores for breast composition / concentration, computer-aided detection markers (e.g., regarding calcifications and tumors detected within the breast), characteristics of computerized radiography, results of breast cancer risk assessment, etc. As used herein, a category score for breast composition / concentration can indicate the proportion of the breast consisting of fibroglandular tissue. Generally, a breast with a high concentration contains a greater amount of epithelial cells, stromal cells, and collagen, which are important factors in the transformation of normal cells into cancer cells. As used herein, a computer-aided detection marker can refer to a digital geometric shape (e.g., triangle, circle, square, etc.) added to (or overlapping) an image. The detection marker can indicate the area of the breast where a lesion or object of diagnostic interest has been detected using computer-aided detection software and / or machine learning algorithms. As used within this specification, characteristics of radiography can refer to properties that describe the information content within an image. Such properties can include image attributes / values related to breast density, breast shape, breast volume, image resolution, etc.

[0023] In some scenarios, the output and / or patient data may be provided to one or more recipients, or one or more receiving devices. Examples of receiving devices include, but are not limited to, image review workstations, medical imaging systems, and technician workstations. Healthcare providers (and / or those associated with them) may use the receiving devices to evaluate the output and / or patient data to inform one or more medical decisions or paths. As a specific example, a set of mammogram images of a patient and the output of an AI processing component may be provided to an image review workstation. A physician may evaluate the data provided to the image review workstation and determine an initial or primary breast care path for the patient. As used herein, a breast care path (or medical path) may refer to a plan or strategy for guiding decisions and timings regarding diagnosis, intervention, treatment, and / or complementary actions at one or more stages of a disease or medical condition. Generally, a breast care path may represent a strategy (e.g., a care path) for managing a population of patients with a particular problem or medical condition, or a strategy (e.g., a care plan) for managing an individual patient with a particular problem or medical condition. As another example, the output of an AI processing component may be provided to an imaging system or an acquisition room. A technician may evaluate the data provided to the imaging system / acquisition room to enable the technician to perform diagnostic procedures while the patient is in the facility.

[0024] In certain scenarios, various inputs may be provided to a decision analysis component configured to output a recommended medical pathway. The decision analysis component may utilize one or more of the rule sets, algorithms, or models described above with respect to the AI processing component. Exemplary inputs to the decision analysis component include, but are not limited to, patient data, the output of the AI processing component, initial / primary medical judgments and diagnostic assessments of healthcare providers, and medical practice guidelines from clinical professional groups. The decision analysis component may process the various inputs and provide one or more outputs. Exemplary outputs include, but are not limited to, automated patient medical recommendations, assessments of healthcare provider judgments, recommended treatments and procedures, instructions for performing the treatment / procedure, diagnostic and intervention reports, automated appointment scheduling, and evaluation priorities or timelines. In one example, the output of the decision analysis component may be provided to (or otherwise made accessible to) one or more healthcare providers. The output may be used to further inform the healthcare providers' medical judgments.

[0025] In some scenarios, the output of the determination analysis component may comprise (or otherwise indicate) a priority reading indicator. The priority reading indicator may indicate the evaluation (“reading”) priority for one or more medical images. In one example, the priority reading indicator may be determined by identifying aspects of the medical image (such as features of potentially actionable lesions), determining a confidence level for the identified aspects, and comparing the determined confidence level to a threshold. Those medical images that meet and / or exceed the threshold may be assigned a “priority” status or value. Alternatively, the “priority” status / value may be assigned to the patient corresponding to that medical image. The priority status / value may be used to arrange the evaluation importance or timeline for the reading of the medical image or further patient evaluation. For example, a medical image having a “high” priority status may be placed higher in the reading queue than a medical image having a normal or lower priority status. As a result of the “high” priority status of the medical image, healthcare providers may be notified of the medical image immediately (or promptly) and may evaluate the medical image while the screening subject is still at the screening facility. As another example, a patient having a “high” priority status may receive further evaluation immediately. For example, additional medical images of the patient may be collected, a specialist may meet with (or be assigned to) the patient immediately, or a medical appointment / treatment may be scheduled. Thus, the priority reading indicator improves the detection of anomalies and reduces the number of patient callbacks.

[0026] Accordingly, the present disclosure provides a plurality of technical advantages including, but not limited to, generating an automated (or semi-automated) clinical workflow, automating breast care analysis and risk assessment, generating automated treatment and procedure orders, generating automated diagnostic and intervention reports, enabling “same visit” diagnostic procedures to be performed while the patient is still in the facility, normalizing medical decision-making, optimizing medical recommendations, determining evaluation priorities for medical images, and enhancing the patient experience by reducing patient visits, patient anxiety, hospital costs, and long-term treatments.

[0027] Figure 1 illustrates an overview of an exemplary system for automating the determination of clinical workflows described herein. The presented exemplary system 100 is a combination of interdependent components that interact to form an integrated system for automating the determination of clinical workflows. The components of the system can be hardware components (e.g., used to run / operate an operating system (OS)), or software components implemented on and / or executed by the system's hardware components (e.g., applications, application programming interfaces (APIs), modules, virtual machines, runtime libraries, etc.). In one example, the exemplary system 100 can provide an environment in which software components run and utilize the resources or facilities of the system 100 according to a set of constraints for operation. For example, the software can run on a processing device such as a personal computer (PC), a mobile device (e.g., a smart device, mobile phone, tablet, laptop, personal digital assistant (PDA), etc.) and / or any other electronic device. For an example of the operating environment of a processing device, refer to the exemplary operating environment illustrated in FIG. 7. In other examples, the components of the systems disclosed herein can be distributed across multiple devices. For example, an input can be entered on a client device, and the information can be processed or accessed using other devices within a network such as one or more server devices.

[0028] As an example, system 100 may include computing devices 102, 104, and 106, processing system 108, decision system 110, and network 112. Those skilled in the art will understand that the scale of a system such as system 100 may vary and may include more or fewer components than those depicted in FIG. 1. For example, in some instances, the functionality and components of processing system 108 and decision system 110 may be integrated into a single processing system. Alternatively, the functionality and components of processing system 108 and / or decision system 110 may be distributed across multiple systems and devices.

[0029] Computing devices 102, 104, and 106 may be configured to receive patient data regarding a medical patient such as patient 114. Examples of computing devices 102, 104, and 106 include medical imaging systems / devices (e.g., X-ray, ultrasound, and / or magnetic resonance imaging (MRI) devices), medical workstations (e.g., EMR devices, image review workstations, etc.), mobile medical devices, patient computing devices (e.g., wearable devices, mobile phones, etc.), and similar processing systems and devices. Computing devices 102, 104, and 106 may be located within a medical facility or related facility, on a patient, on a healthcare provider, etc. In one example, patient data may be provided to computing devices 102, 104, and 106 using a manual or automated process. For example, a healthcare provider may manually enter patient data into a computing device. Alternatively, a patient's device may automatically upload patient data to a medical device based on one or more criteria.

[0030] The processing system 108 may be configured to process patient data. In one aspect, the processing system 108 may have access via a network 112 to one or more sources of patient data, such as computing devices 102, 104, and 106. At least a portion of the patient data may be provided as an input to the processing system 108. The processing system 108 may process the input using one or more AI processing techniques. Based on the processed input, the processing system 108 may generate one or more outputs, such as an assessment of breast composition, detection markers, characteristics of radiation measurements, etc. The output may be provided (or made accessible) to other components of the system 100, such as computing devices 102, 104, and 106. In one example, the output may be evaluated by one or more healthcare providers to determine a medical path for the patient. For example, a physician may use computing device 106 to evaluate an X-ray image collected from an imaging system and the results of detection markers collected from the processing system 108. Based on the evaluation, the physician may determine a medical judgment / plan for the patient.

[0031] The judgment system 110 can be configured to provide a recommended medical path. In one aspect, the judgment system 110 can have access to one or more sources such as patient data, output from the processing system 108, diagnostic assessments and notes, and medical practice guidelines. At least a portion of this data can be provided as input to the judgment system 110. The judgment system 110 can process the input using one or more AI processing techniques or models. For example, the judgment system 110 can implement an artificial neural network, a support vector machine (SVM), a linear boosting model, a random decision forest, or similar machine learning techniques. In at least one example, the AI processing techniques implemented by the judgment system 110 can be the same (or similar to) those implemented by the processing system 108. In such an example, the functionality of the judgment system 110 and the processing system 108 can be combined into a single processing system or component. Based on the processed input, the judgment system 110 can generate one or more outputs such as an automated diagnosis, patient care recommendations, assessment of medical staff judgment, step-by-step treatment instructions, etc. In one aspect, the output(s) can be used to further inform the medical judgment of medical staff. For example, a physician can compare the medical judgment of the judgment system 110 with the physician's own medical judgment to determine the best medical path for the patient.

[0032] Figure 2 is a diagram of an exemplary process flow for automating the judgment of the clinical workflow described herein. The exemplary system 200 presented includes a patient information record 202, an X-ray imaging system 204, an image review station 206, an AI processing component 208, a judgment supporter 210, practice guidelines 212, a diagnostic report 214, a biopsy recommendation 216, a radiation recommendation 218, a surgical recommendation 220, a chemotherapy recommendation 222, a priority read indicator 223, and an additional imaging system(s) 224. Those skilled in the art will understand that the scale of a system such as system 200 can vary and can include more or fewer components than those described in Figure 2.

[0033] As shown in FIG. 2, patient data can be collected from a patient. In some scenarios, patient data can be collected from a patient during a visit to a medical facility. In another example, patient data can be provided to a medical facility while the patient is not visiting the medical facility. For example, patient data can be remotely uploaded from a patient device to one or more HIS devices. In process flow 200, patient information record 202 can store patient information such as name or identifier, contact information, personal information, diagnostic history, vital sign information, prescribed medications, etc. X-ray imaging system 204 can generate and / or store, for example, an X-ray image of a patient's breast. Additional imaging system(s) 224 can generate and / or store, for example, an ultrasonic image of a patient's breast and / or an MRI image of the breast.

[0034] In one scenario, information recorded within the patient information record 202, as well as images generated using the X-ray imaging system 204 and additional imaging system(s) 224 (collectively referred to as "patient data") can be provided to the AI processing component 208. In one example, the AI processing component 208 can be configured to assess one or more characteristics of a patient's breast based on breast image data received as input. The assessment can include an analysis of the texture / tissue of the imaged breast and the identification of one or more patterns within the breast image. Based on the provided patient data, the AI processing component 208 can generate breast assessment data such as a category score for breast composition / density, computer-aided detection markers (e.g., regarding calcifications and tumors detected within the breast), computerized radiometric features, and results of a breast cancer risk assessment. The breast assessment data can be provided to the X-ray imaging system 204 and / or additional imaging system(s) 224. A technician can evaluate the breast assessment data provided to the X-ray imaging system 204 and / or additional imaging system(s) 224 and determine, for example, whether additional imaging should be performed for the patient. The breast assessment data and / or patient data can also be provided to the image review station 206. A physician can evaluate not only the information provided to the image review station 206 but also the practice guidelines 212 and create diagnostic information and / or medical judgment regarding the patient (collectively referred to as a "diagnostic report").

[0035] In some scenarios, breast assessment data, patient data, and / or diagnostic reports may be provided to the decision supporter 210. Based on the provided information and / or practice guidelines 212, the decision supporter 210 may automatically generate decision information such as patient medical recommendations, assessment of healthcare provider decisions, recommended imaging procedures, recommended treatments and procedures, instructions for performing the treatment / procedure, priorities and / or timelines for the treatment / procedure, and diagnostic reports 214. Examples of recommended treatments and procedures include biopsy recommendations 216, radiation recommendations 218, surgical recommendations 220, and chemotherapy recommendations 222. Examples of treatment and procedure priorities / timelines include priority read indicators 223. The priority read indicator 223 may include or represent a status, value, or date / time for evaluating medical images. In some scenarios, the decision information may be made accessible to one or more healthcare providers (or from computing devices associated with them). For example, the process flow 200 illustrates decision information provided to the physician who created the diagnostic report. As another more specific example, the process flow 200 illustrates the priority read indicator 223 provided to the technician, the X-ray imaging system 204, and the image review station 206.

[0036] Figure 3 illustrates an overview of an exemplary decision processing system 300 for automating decisions in the clinical workflow described herein. The automated clinical workflow techniques implemented by the input decision system 300 may include the automated clinical workflow techniques and data described in the system of FIG. 1. In some examples, one or more components (or their functionality) of the input decision system 300 may be distributed across multiple devices and / or systems. In other examples, a single device (comprising at least one processor and / or memory) may comprise the components of the input decision system 300.

[0037] With respect to FIG. 3, the input determination system 300 may include a data collection engine 302, a determination engine 304, and an output creation engine 306. The data collection engine 302 may be configured to access a set of data. In some aspects, the data collection engine 302 may have access to information related to one or more patients. The information may include patient data (e.g., patient identification, medical images of the patient, diagnostic information of the patient, etc.), assessment of breast composition, detection markers, characteristics of radiation measurements, diagnostic assessments and notes, medical practice guidelines, and the like. In some aspects, at least a portion of the information may be test data or training data. The test / training data may include labeled data and images used to train one or more AI models or algorithms.

[0038] The determination engine 304 may be configured to process the received information. In some aspects, the received information may be provided to the determination engine 304. The determination engine 304 may apply one or more AI processing algorithms or models to the received information. For example, the determination engine 304 may apply an AI-based fusion algorithm to the received information. The AI processing algorithm / model may evaluate the received information and determine the relationship between the received information and the training data used to train the AI processing algorithm / model. Based on the evaluation, the determination engine 304 may identify or determine the best medical path or recommendation for one or more patients associated with the patient data. In some aspects, the determination engine 304 may further identify and provide image reading priorities. For example, the determination engine 304 may assign a "priority" status to an image within the received information.

[0039] The output generation engine 306 may be configured to generate one or more outputs regarding the received information. In one scenario, the output generation engine 306 may use the identification or determination of the determination engine 304 to generate one or more outputs. As an example, the output generation engine 306 may recommend the use of one or more additional imaging modalities such as contrast-enhanced MRI, advanced ultrasound imaging (e.g., shear wave imaging, contrast imaging, 3D imaging, etc.), and positron emission tomography (PET) imaging. As another example, the output generation engine 306 may generate a diagnostic report and a comprehensive report including recommendations regarding biopsy procedures, chemotherapy, surgical interventions, or radiation therapy. The recommendations may include detailed treatment instructions and the relationship between data points and medical images. As a specific example, regarding a biopsy procedure, the output generation engine 306 may provide step-by-step biopsy instructions associated with the biopsy image, as well as previous diagnostic images from X-ray, ultrasound, and MRI imaging systems.

[0040] Although various systems that may be employed by aspects disclosed herein have been described, here, the present disclosure describes one or more methods that may be implemented by various aspects of the present disclosure. In one aspect, methods 400 and 500 may be executed by an exemplary system such as the system 100 of FIG. 1 or the determination processing system 300 of FIG. 3. In one example, methods 400 and 500 may be executed on a device having at least one processor configured to store and execute operations, programs, or instructions. However, methods 400 and 500 are not limited to such examples. In other examples, methods 400 and 500 may be implemented on an application or service for automating clinical workflow decisions. In at least one example, methods 400 and 500 may be executed by one or more components of a distributed network such as a web service / distributed network service (e.g., cloud service) (e.g., computer-implemented operations).

[0041] Figure 4 illustrates an exemplary method 400 for automating the determination of the clinical workflow described in this specification. The exemplary method 400 begins with an operation 402 in which patient data is collected from one or more data sources. In one aspect, a data collection component, such as the data collection engine 202, may collect patient data from one or more data sources. Exemplary data sources include patient visit information, the patient's EMR, the HIS records of the medical facility, and medical imaging systems. For example, during a patient's visit to a medical facility, patient information records stored (or accessible) by the medical facility may be used to collect or access the patient's personal information, such as the patient's age, diagnostic history, lifestyle information, etc. During the patient's visit, an X-ray imaging system may be used to generate one or more 2D and / or 3D X-ray images of the patient's breast(s). The X-ray images may be combined with (or otherwise associated with) the personal information and / or stored in one or more medical records or medical systems of the medical facility.

[0042] In one aspect, the data collection process may be initiated manually and / or automatically. For example, a healthcare provider may manually initiate the data collection process by requesting patient information from the patient and entering the requested patient information into the patient information record. Alternatively, the data collection process may be automatically initiated when one or more criteria are met. Exemplary criteria may include a patient check-in event, entering diagnostic information or the patient's medical path into the HIS, or evaluating a digital mammography image via an image review workstation. For example, in response to detecting a patient check-in event at a medical facility, the electronic system / service of the medical facility may automatically collect patient information from one or more of the patient's medical records. The collected data may be aggregated into an active working file for the patient's current visit.

[0043] In operation 404, patient data is provided to a processing component. In one scenario, one or more portions of the patient data may be provided to a processing component such as AI processing component 208. The processing component may comprise or have access to one or more rule sets, algorithms or predictive models. The processing component may use a set of AI algorithms to process the information and create a group of outputs. For example, continuing from the above example, the combined data (e.g., patient personal information and X-ray image) may be provided as input to an AI system accessible from a medical facility. The AI system may be implemented on a single device (such as a single workstation in a medical facility) or provided to multiple devices across multiple devices in a distributed computing environment as a distributed service / system. The AI system may be configured to perform a breast assessment using a machine learning algorithm that analyzes the attributes of each patient's breast (such as patterns, textures, etc.). The AI system may be implemented on a single device (such as a single workstation in a medical facility) or provided to multiple devices across multiple devices in a distributed computing environment as a distributed service / system. By applying a machine learning algorithm to the combined data, the AI system may identify one or more aspects of the X-ray image indicating that the imaged breast is heterogeneous high density. This density classification may be based on, for example, the American College of Radiology (ACR) Breast Imaging Reporting and Data System (BI-RADS) Mammographic Density (MD) assessment category. The AI system may further add detection markers to the X-ray image and indicate one or more calcifications or tumors detected within the X-ray image.

[0044] In operation 406, the output is received from the processing component. In one scenario, the processing component may create one or more outputs from the patient data. Exemplary outputs include category scores of breast composition, assessments of breast density, computer-aided detection markers, features of computerized radiological measurements, results of breast cancer risk assessments, etc. At least a portion of the output may be provided to one or more healthcare providers and / or one or more healthcare systems / devices. For example, continuing from the above example, the AI system may output a classification of the density of the imaged breast (e.g., heterogeneous high density) and / or corresponding X-ray image data (e.g., the original X-ray image, updated X-ray image using detection markers, and / or such as calcifications or tumors). The output of the AI system may be provided to one or more computing devices (e.g., workstations, mobile devices, etc.) of the patient's radiologic technologist and / or medical imaging technologist. Based on an evaluation of the output of the AI system by the radiologic technologist, the radiologic technologist may recommend that the patient undergo an ultrasound imaging of the breast. In response to the recommendation, the medical imaging technologist may perform the recommended diagnostic procedure (e.g., magnification / contrast diagnostic imaging) and / or complementary screening procedure (e.g., ultrasound imaging) while the patient is still at the facility (e.g., during the patient's current visit). Performing those procedures while the patient is still at the facility may avoid additional visits to the healthcare facility and may reduce the healthcare costs associated with rescheduling appointments.

[0045] In operation 408, the output of the processing component is provided to the judgment component. In one scenario, the output of the processing component, the recommendations of healthcare providers, X-ray image data, complementary data from diagnostic / screening procedures, and other information related to the patient can be provided to a judgment component such as the judgment engine 304. The judgment component may comprise or have access to one or more rule sets, algorithms, or predictive models. The judgment component may use one or more AI algorithms to process the information and create a group of outputs. For example, continuing from the above example, patient data, AI system output, X-ray image data, ultrasonic image data (recommended by a radiologic technologist), radiologic technologist's recommendation data, and practice guidelines from one or more clinical professional groups (such as the American College of Radiology (ACR), National Comprehensive Cancer Network (NCCN), etc.) can be provided as inputs to an AI-based fusion algorithm. The AI-based fusion algorithm can be configured to provide the best medical path or recommendation for one or more patients. Based on the provided inputs, the AI-based fusion algorithm can determine that surgical intervention is the best care plan for the patient.

[0046] In operation 410, the output is received from the judgment component. In one scenario, the judgment component can create one or more outputs from the received inputs. Exemplary outputs include automated patient medical recommendations, assessment of healthcare provider judgment, recommended treatments and procedures, instructions for performing the treatment / procedure, diagnostic and intervention reports, and automated reservation scheduling. For example, continuing from the above example, based on the inputs provided to the AI-based fusion algorithm, the AI-based fusion algorithm can output a comprehensive report including diagnostic information about the patient and recommendations regarding surgical intervention for the patient. The recommendations regarding surgical intervention may be accompanied by specific guidelines for performing the recommended surgical procedure. The instructions may include surgical images, step-by-step surgical instructions, computer-aided detection markers, recommended dosages, recovery procedures, etc.

[0047] In operation 412, automated patient medical recommendations are provided to healthcare providers. In one aspect, the output (or portions thereof) from the determination component may be provided to one or more targets. Exemplary targets include devices for healthcare providers, devices of a healthcare facility, devices for patients, data archives, one or more processing systems, and the like. The target may assess the automated patient medical recommendation and notify or evaluate the patient medical recommendation of the target itself. For example, continuing from the above example, the comprehensive report and recommendations regarding surgical intervention may be provided to one or more computing devices of the patient's radiologist. The comprehensive report may indicate that 93% of radiologists have recommended surgical intervention for patients with patient data similar to that of the patient and AI system output similar to that of the patient. Based on the comprehensive report and recommendations, the radiologist may create or approve a recommendation regarding surgical intervention. In at least one example, the radiologist may modify a previous medical recommendation created by the radiologist to be consistent with the recommendation provided by the determination component.

[0048] FIG. 5 illustrates an exemplary method 500 for determining image reading priorities described herein. In one aspect, the exemplary method 500 may be implemented (in whole or in part) on an X-ray imaging system or device such as the X-ray imaging system 204. The exemplary method 500 begins with an operation 502 in which image data is collected from one or more data sources. In one aspect, a data collection component such as the data collection engine 302 may collect image data from one or more data sources. Exemplary data sources include a patient's EMR, HIS records of a healthcare facility, and a medical imaging system. For example, during a visit to an imaging facility, the X-ray imaging system 204 may be used to generate one or more 2D and / or tomosynthesis X-ray images of the patient's breast(s). The X-ray images may be combined with (or otherwise associated with) the patient's personal information and / or stored in one or more medical records or medical systems of the healthcare facility.

[0049] In operation 504, features of the image data can be identified. In one scenario, the image data (or a portion thereof) can be provided to input processing components such as AI processing component 208 and / or judgment supporter 210. In at least one example, the input processing component can be incorporated into an X-ray imaging system or device in which exemplary method 500 is implemented. The image data can be provided to the input processing component while the image data is being collected (e.g., in real time), immediately after the image data is collected, or at any other time after the image data is collected. The input processing component can comprise or have access to one or more rule sets, algorithms, or prediction models. The input processing component can evaluate the image data and identify one or more features of the image data. Features of the image can include, but are not limited to, edges or boundaries of shapes, points of interest, and blobs. Identifying the features can include using feature detection and / or feature extraction techniques. Feature values can be calculated for and / or assigned to each feature using one or more featureization techniques such as ML processing, normalization operations, binning operations, and / or vectorization operations. Feature values can be numerical representations of the features, values paired with the features in the merged data, indications of one or more patient conditions regarding the features, and the like.

[0050] In operation 506, a confidence score can be calculated with respect to the features of an image. In one aspect, an input processing component (or a component associated therewith) can generate a confidence score using the feature values calculated with respect to the identified features of the image. The confidence score can represent the probability that a particular feature matches a predefined feature or category / classification of features. Generating a confidence score can include comparing the features and / or feature values of the image data against a set, known, or predefined set of labeled features and / or feature values. For example, for a received image, four points of interest can be identified, and each of the four points of interest can be assigned a set of feature values. Each set of feature values can be compared, respectively, to stored feature data from known images. The stored feature data can include feature values for various features and can be labeled to classify the features or images. For example, sets of feature data can be listed with respect to various abnormalities of the breast and / or findings by mammogram. The confidence score can be generated based on a match or similarity between the feature values for the received image and the stored feature values. In one aspect, the confidence score can be a numerical, non-numerical (or partially numerical) value, or a label. For example, the confidence value can be represented by a numerical value on a scale from 1 to 10, where "1" can represent a low confidence match and "10" can represent a high confidence match. In such an example, a higher confidence value can indicate a greater number (or percentage) of matches or similarities between the feature values for the received image and the stored feature values.

[0051] In determination operation 508, the confidence score can be compared with a threshold value. In one scenario, an input processing component (or a component associated therewith) can compare the confidence score with a confidence threshold value that can constitute the confidence score. The confidence threshold value can represent the level of confidence that needs to be met or exceeded before an image (or image data) is assigned a priority reading status. The confidence threshold value can be selected based on the desired balance between positive screening cases (e.g., cases where cancer is confirmed) and negative screening cases (e.g., cases where no cancer is found). For example, in a specific example, the selected confidence threshold value can result in the identification of a set of 1000 cases where 70% of the cases are positive screening cases, 20% of the cases show abnormalities other than cancer, and 10% of the cases are negative screening cases. Each of the positive screening cases can be assigned a priority reading status. By increasing the selected confidence threshold value, a reduced set of cases can be selected. For example, a set of 750 cases where 80% of the cases are positive screening cases, 15% of the cases show abnormalities other than cancer, and 5% of the cases are negative screening cases can be identified. Alternatively, by decreasing the selected threshold value, an increased set of cases can be selected. For example, a set of 1,250 cases where 60% of the cases are positive screening cases, 25% of the cases show abnormalities other than cancer, and 15% of the cases are negative screening cases can be identified.

[0052] In some examples, the confidence threshold can be determined and configured manually. For example, a user can select or modify the confidence threshold using the user interface of the input processing component. The selection of the confidence threshold can be based on various factors. For example, for at least a portion of the X-ray imaging system associated with a specific medical facility, the confidence threshold can be selected based on whether a sufficient number of radiologists are associated with the medical facility or how quickly radiologists can review cases with priority read status. In other examples, the confidence threshold can be determined automatically and / or dynamically by the input processing component. For example, feedback or output from one or more entities or components of the system 200 related to a proposed medical path, image reading priority, etc. can be accessible to the input processing component. The feedback / output can include accuracy ratings or comments from technicians, doctors, or radiologists. The feedback / output can additionally include treatments, reports, patient notes, etc. Based on the feedback / output, the input processing component can modify the threshold and increase or decrease the number of identified positive and / or negative screening cases.

[0053] In a situation where it is determined that the confidence score is below the confidence threshold, the flow proceeds to operation 510. In operation 510, the received image data can be assigned a standard level of priority (e.g., standard priority level, low priority level, or non-priority level). The standard level of priority can indicate that the received image data should be evaluated based on the normal convenience and / or workload of the relevant medical staff. For example, when the image data is assigned a standard level of priority, the image data can be added to the image reading queue. The position of the image data in the queue (e.g., the order in which the image data is added to the queue) can determine the order of evaluation of the image data. As a specific example, in a first-in-first-out (FIFO) queue, any data item with a standard priority level that was added to the queue prior to the received image data will be evaluated before the received image data. In such an example, it is possible that the image data is not evaluated even though the screening subject is still at the screening facility.

[0054] However, if it is determined that the confidence score meets or exceeds the confidence threshold, the flow proceeds to operation 512. In operation 512, the received image data can be assigned a high level of priority. Assigning a high level of priority can include adding one or more indicators to the image data and / or metadata, such as a header for medical digital imaging and communications (DICOM) regarding the image data. Exemplary indicators can include labels (such as "high priority", "priority", etc.), numerical values, emphasis, arrows or pointers, font or style modifications, date / time values, and the like. In one aspect, a high level of priority can indicate that the received image data should receive a prioritized evaluation. As an example, when image data is assigned a high level of priority, the image data can be added to an image reading queue. Based on the high level of priority, the image data can be evaluated before other data items in the queue that have a lower priority level and / or a later time / date of entry into the queue. As another example, a priority indicator regarding image data assigned a high level of priority can be presented to one or more healthcare providers. For example, when assigning a high level of priority to image data, the priority indicator and / or the image data can be presented to a technician using the user interface of an X-ray imaging system or device. In at least one example, the priority indicator and / or the image can be presented to the technician while the technician is collecting the image data (e.g., in real time). As yet another example, when image data is assigned a high level of priority, the image data (or an indication thereof) can be sent to one or more destinations. For example, a radiology technician can receive a message (such as an email, text, voice call, etc.) associated with the assignment of the priority of the image data. The message can include information such as the patient's current status or location, the reading priority regarding the image data, the current and / or past medical records regarding the patient, and the like.As a specific example, image data including a priority read indicator can be sent to the radiologist's image review workstation along with an indication that the patient is currently in the medical facility waiting for the image data to be read. Alternatively, the image data can be sent to a software application or service used to manage the radiologist's workflow. The software application / service can be configured to create and / or assign a worklist of cases requiring immediate evaluation. In such an example, a high-priority read indicator can enable follow-up imaging and other actions to be performed while the screening subject is still at the screening facility.

[0055] FIG. 6A illustrates an exemplary user interface 600 associated with the determination of an automated clinical workflow described herein. In one example, the user interface 600 represents software used by a technician at a mammography acquisition workstation. The software can be used to collect images from an x-ray imaging system, such as the x-ray imaging system 204, during a breast screening exam and / or review images collected during a breast screening exam. The user interface 600 includes a button 602 that activates an "Analysis" dialog when selected.

[0056] FIG. 6B illustrates an analysis dialog 610 that is displayed when button 602 in FIG. 6A is selected. The analysis dialog 610 includes a button 612, an analysis result section 614, and a reading priority instruction 616. In one aspect, when button 612 is selected, image evaluation software is launched and one or more collected images are analyzed using the techniques described in FIGS. 3 and 4. As a result of the analysis, the analysis result section 614 is at least partially populated with data such as the reading priority instruction 616. In FIG. 6B, the reading priority instruction 616 indicates that the reading priority for the analyzed image(s) is "high". Based on the "high" reading priority, a technician may require that the screening subject remain at the facility while the collected image(s) are reviewed by a radiologic technologist. This immediate review by the radiologic technologist (e.g., while the screening subject is at the facility) may reduce or eliminate the need to recall the screening subject for follow-up appointments.

[0057] FIG. 7 illustrates an exemplary and suitable operating environment for a technique that automates the determination of the clinical workflow described in FIG. 1. In its most basic configuration, the operating environment 700 typically includes at least one processing unit 702 and a memory 704. Depending on the precise configuration and type of the computing device, the memory 704 (which stores instructions for implementing the techniques disclosed herein) can be volatile (such as RAM), non-volatile (such as ROM, flash memory, etc.) or some combination of the two. This most basic configuration is illustrated within FIG. 7 by dashed line 706. Further, the environment 700 can also include storage devices (removable 708 and / or non-removable 710) including, but not limited to, magnetic or optical disks or tapes. Similarly, the environment 700 can also have input devices (singular or plural) 714 such as a keyboard, mouse, pen, voice input, etc., and / or output devices (singular or plural) 716 such as a display, speaker, printer, etc. One or more communication connections 712 such as LAN, WAN, point-to-point, etc. are also included within the environment. In certain embodiments, the connection can be operable for point-to-point communication of devices, connection-oriented communication, connectionless communication, etc.

[0058] The operating environment 700 typically includes at least some form of computer-readable medium. A computer-readable medium can be any usable medium that can be accessed by a processing unit 702 or other device with the operating environment. By way of example, and not limitation, computer-readable media can comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transitory media which can be used to store the desired information. Computer storage media does not include communication media.

[0059] Communication media embodies computer-readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism and includes any information delivery media. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media includes wired media such as a wired network or direct-wired connection, as well as wireless media such as acoustic, RF, infrared, microwave and other wireless media. Any combination of the above should also be included within the scope of computer-readable media.

[0060] The operating environment 700 can be a single computer operating within a networked environment using logical connections to one or more remote computers. The remote computers can be personal computers, servers, routers, network PCs, peer devices, or nodes of other common networks, and typically include many or all of the elements described above, as well as others not so recited. The logical connections can include any method supported by a useable communication medium. Such networked environments are commonplace in offices, enterprise-wide computer networks, intranets, and the Internet.

[0061] The embodiments described herein can be implemented and carried out using software, hardware, or a combination of software and hardware to implement and practice the systems and methods disclosed herein. Although specific devices have been recited throughout this disclosure as performing certain functions, those skilled in the art will understand that those devices are provided for illustrative purposes only and that other devices can be employed to perform the functionality disclosed herein without departing from the scope of this disclosure.

[0062] This disclosure describes some embodiments of the technology with reference to the accompanying drawings, which show only some of the possible embodiments. However, the other aspects can be embodied in many different forms and should not be construed as limited to the embodiments described herein. Rather, those embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the possible embodiments to those skilled in the art.

[0063] Although specific embodiments are described herein, the scope of the technology is not limited to those specific embodiments. Those skilled in the art will recognize other embodiments or improvements within the scope and spirit of the technology. Accordingly, the specific structure, acts, or media are disclosed only as illustrative embodiments. The scope of the technology is defined by the following claims and any equivalents thereof.

Claims

1. A system associated with an imaging device for imaging a breast of a patient, the system comprising: a display associated with a workstation configured to collect image data associated with the patient using the imaging device; and At least one processor; a memory coupled to the at least one processor; Equipped with The memory comprises computer-executable instructions that, when executed by the at least one processor, perform a method; The method comprises: an input processing component receiving the image data from the imaging device; providing the image data to an artificial intelligence (AI) component in real time; the artificial intelligence (AI) component identifying one or more features in the image data indicative of an abnormality in the breast; the input processing component calculating a confidence score based on the one or more features, the confidence score being a value or a label; and receiving feedback related to current priority case loading over a network from one or more devices remote from said workstation; the input processing component dynamically configuring thresholds based on the feedback; comparing the confidence score to a threshold; assigning a high evaluation priority to the patient's patient case when the confidence score exceeds the threshold; automatically displaying a priority reading indicator on the display used by a medical practitioner in response to the high evaluation priority being assigned to the patient case, and storing the image data with the high evaluation priority and the one or more features concurrently with the image data being processed by the input processing component. Including, the system.

2. The system of claim 1, wherein the image data includes at least one of a 2D x-ray image, multiple tomosynthesis x-ray images of the patient's breast, or an ultrasound image.

3. The system of claim 1, further comprising receiving patient data from one or more data sources including at least one of patient visit information, a patient's electronic medical record (EMR), a hospital information system (HIS) record, or a medical imaging system.

4. The system of claim 1, wherein the patient data is evaluated by the AI ​​component and used in part to calculate the confidence score.

5. The system of claim 1, wherein the one or more features include at least one of a shape edge, a shape boundary, a point of interest, or a blob.

6. The system of claim 1, wherein identifying the one or more features includes calculating a feature vector using at least one of a machine learning (ML) process, a normalization operation, a binning operation, or a vectorization operation.

7. The system of claim 1, wherein the confidence score represents the probability that a particular feature among the one or more features matches a predefined feature.

8. The system of claim 1, wherein calculating the confidence score includes comparing the one or more features to a set of labeled features of one or more previously classified images.

9. The system of claim 1, wherein the threshold is selected based on a desired balance between screening positive cases and screening negative cases.

10. The system of claim 1, wherein the threshold is selected based on at least one of whether a sufficient number of radiologists are associated with a clinical facility or the amount of time before the radiologists are available to review cases with high evaluation priority.

11. The system of claim 1, wherein the threshold is dynamically configured based on information related to the proposed medical path.

12. The system of claim 1, wherein when the patient case is assigned the high evaluation priority, the patient case is added to a priority queue having a higher position than another case that does not have the high priority.

13. The system of claim 1, wherein assigning the high evaluation priority to the patient case includes adding one or more priority indicators to metadata associated with the image data.

14. The system of claim 1, wherein assigning the high evaluation priority to the patient case includes storing the high evaluation priority associated with the patient case.

15. The display is associated with a workstation in the same room as the imaging device, the workstation comprising: collecting said image data; assigning said high evaluation priority to said patient case; storing the high assessment priority with the patient case; presenting the preferred reading indicator on the display based on the high rating priority; The system of claim 14 configured to:

16. A method, comprising: an input processing component receiving image data from one or more data sources, the image data including one or more images of a patient's breast; an artificial intelligence (AI) component evaluating the image data to identify one or more features, the one or more features corresponding to at least one of a point of interest or a shape edge of the patient's breast; the input processing component calculating a confidence score based on the one or more features, the confidence score being a value or a label, and calculating the confidence score including matching the one or more features to labeled or known image features; the input processing component receiving feedback related to current priority case loading over a network from one or more devices remote from the workstation; the input processing component dynamically configuring thresholds based on the feedback; the input processing component comparing the confidence score to a threshold; the input processing component assigning a high evaluation priority to the image data when the confidence score exceeds the threshold; automatically, in response to the high assessment priority being assigned to the patient case, the input processing component displays a priority reading indicator on the display used by the medical personnel, and the input processing component stores the image data with the high assessment priority and the one or more features concurrently with the image data associated with the patient being processed by the input processing component. A method comprising:

17. The method of claim 16, wherein the one or more data sources further include patient data.

18. The method of claim 16, further comprising, in response to assigning the high evaluation priority to the image data, the input processing component providing the image data to a workflow service, the workflow service configured to manage a worklist of cases.

19. The method of claim 18, wherein the input processing component further includes displaying the worklist for the case to a radiologist, and the worklist service displays the image data having the high evaluation priority higher on the worklist for the case than another set of image data.

20. The system of claim 1, wherein the one or more features indicating an abnormality include cancer features.

21. The method of claim 16, wherein the input processing component identifying the one or more features includes identifying a cancer feature.

Images