Systems and methods for automated segmentation of patient specific anatomies for pathology specific measurements
Systems and methods are provided for multi-schema analysis of patient specific anatomical features from medical images. The system may receive medical images of a patient and metadata associated with the medical images indicative of a selected pathology, and automatically classify the medical images using a segmentation algorithm. The system may use an anatomical landmark detection algorithm leveraging Deep Reinforcement Learning (DRL) techniques to automatically locate one or more anatomical landmarks associated with the patient specific anatomical feature within the medical images. A 3D surface mesh model may be generated representing the patient specific anatomical features including the located one or more anatomical landmarks. The located one or more anatomical landmarks may be used to guide placement of a 3D model of a medical device that may be fused with the 3D surface mesh model to generate a patient specific 3D model of the medical device.
1. A system for multi-schema analysis of patient specific anatomical features from medical images, the system comprising a server and configured to:
receive medical images of a patient and metadata associated with the medical images indicative of a selected pathology;
automatically segment the medical images to identify one or more patient specific anatomical features within the medical images;
extract an isolated patient specific anatomical feature comprising the selected pathology from the one or more patient specific anatomical features based on the metadata;
generate an isolated 3 D surface mesh model defining a surface of the isolated patient specific anatomical feature; and
provide a medical device to be used to treat the selected pathology based on physiological parameters of the isolated patient specific anatomical feature.
2. The system of claim 1 , wherein the physiological parameters of the isolated anatomical feature comprise a size of the selected pathology, and wherein the medical device provided comprises a specific sized medical device for treating the selected pathology.
3. The system of claim 1 , wherein the system is configured to generate physiological information associated with the selected pathology for the isolated 3 D surface mesh model.
4. The system of claim 3 , wherein the physiological information comprises a volume, cross-sectional area, diameter, centerline, surface, density, thickness, tortuosity, fracture size and location, blood clots, occlusions, and/or rate of growth over time of the anatomical feature and/or corresponding landmark.
5. The system of claim 1 , wherein the system is configured to automatically segment the medical images to identify the one or more patient specific anatomical features via a segmentation algorithm programmed to label pixels of the medical images and an anatomical feature identification algorithm programmed to classify the one or more patient specific anatomical features within the medical images based on the labeled pixels.
6. The system of claim 1 , wherein the medical device is selected for fixation to bone and to provide guidance for cutting planes.
7. The system of claim 1 , wherein the medical device is selected for fixation to bone and to provide drilling trajectories within the bone.
8. The system of claim 1 , wherein the medical device is selected based on a surgical procedure to be performed on the isolated patient specific anatomical feature to treat the selected pathology.
9. The system of claim 8 , wherein the surgical procedure comprises placement of bone fragments, tools, implants, holes, and/or screws, cutting, and/or bone realignment.
10. The system of claim 1 , wherein the medical device is selectable from a hospital inventory of available medical devices.
11. The system of claim 1 , wherein the system is configured to:
access a medical device database having knowledge of various medical devices, the knowledge comprising function and/or specifications of the various medical devices,
wherein the medical device is selectable from a list of medical devices extracted from the medical device database.
12. The system of claim 1 , wherein the system is configured to:
access a surgical implement database having knowledge of pathology-specific treatment options,
wherein the medical device is selectable from a list of medical devices extracted from the surgical implement database.
13. The system of claim 1 , wherein the system is configured to provide the medical device by providing a 3D digital model of the medical device specific to the physiological parameters of the isolated patient specific anatomical feature.
14. The system of claim 13 , wherein the system is configured to:
receive patient demographic data,
wherein the 3D digital model of the medical device is provided based at least partially on the patient demographic data.
15. The system of claim 13 , wherein the system is configured to cause a display to display the 3D digital model of the medical device.
16. The system of claim 15 , wherein the display comprises a graphical user interface, and wherein the system is configured to permit a user to move the 3D digital model of the medical device relative to the isolated patient specific anatomical feature via the graphical user interface to position the 3D digital model of the medical device at a target location relative to the isolated patient specific anatomical feature.
17. The system of claim 16 , wherein the system is configured to display one or more anatomical landmarks associated with the isolated patient specific anatomical feature, the one or more anatomical landmarks configured to serve as a guide for positioning of the 3D digital model of the medical device at the target location.
18. The system of claim 16 , wherein the system is configured to fuse the 3D digital model of the medical device with the isolated patient specific anatomical feature such that a fitting surface of the 3D digital model matches a surface contour of the isolated patient specific anatomical feature at the target location.
19. The system of claim 1 , wherein the system is further configured to cause the 3D digital model to be 3D printed to generate a physical, patient specific medical device.
20. The system of claim 19 , wherein the physical, patient-specific medical device is a cutting guide, pin guide, occlusion device, mitral valve implant, aortic valve implant, stent, coil, clip, fusion plate, or joint replacement implant.
21. A method for multi-schema analysis of patient specific anatomical features from medical images, the method comprising:
receiving medical images of a patient and metadata associated with the medical images indicative of a selected pathology;
automatically segmenting the medical images to identify one or more patient specific anatomical features within the medical images;
extracting an isolated patient specific anatomical feature comprising the selected pathology from the one or more patient specific anatomical features based on the metadata;
generating an isolated 3 D surface mesh model defining a surface of the isolated patient specific anatomical feature; and
providing a medical device to be used to treat the selected pathology based on physiological parameters of the isolated patient specific anatomical feature.
22. The method of claim 21 , wherein the physiological parameters of the isolated anatomical feature comprise a size of the selected pathology, and wherein the medical device provided comprises a specific sized medical device for treating the selected pathology.
23. The method of claim 21 , wherein automatically segmenting the medical images to identify the one or more patient specific anatomical features comprises executing a segmentation algorithm programmed to label pixels of the medical images and an anatomical feature identification algorithm programmed to classify the one or more patient specific anatomical features within the medical images based on the labeled pixels.
24. The method of claim 21 , wherein the medical device is selected for fixation to bone and to provide guidance for cutting planes, selected for fixation to bone and to provide drilling trajectories within the bone, and/or selected based on a surgical procedure to be performed on the isolated patient specific anatomical feature to treat the selected pathology.
25. The method of claim 21 , wherein providing the medical device comprises providing a 3 D digital model of the medical device specific to the physiological parameters of the isolated patient specific anatomical feature.
26. The method of claim 25 , further comprising:
causing a graphical user interface to display the 3D digital model of the medical device; and
permitting, via the graphical user interface, a user to move the 3D digital model of the medical device relative to the isolated patient specific anatomical feature to position the 3D digital model of the medical device at a target location relative to the isolated patient specific anatomical feature.
27. The method of claim 26 , further comprising causing the graphical user interface to display one or more anatomical landmarks associated with the isolated patient specific anatomical feature, the one or more anatomical landmarks configured to serve as a guide for positioning of the 3D digital model of the medical device at the target location.
28. The method of claim 25 , further comprising fusing the 3D digital model of the medical device with the isolated patient specific anatomical feature such that a fitting surface of the 3D digital model matches a surface contour of the isolated patient specific anatomical feature at the target location.
29. The method of claim 25 , further comprising 3D printing the 3D digital model to generate a physical, patient specific medical device.
30. The method of claim 29 , wherein the physical, patient-specific medical device is a cutting guide, pin guide, occlusion device, mitral valve implant, aortic valve implant, stent, coil, clip, fusion plate, or joint replacement implant.