Method for generating a 3D physical model of a patient specific anatomic feature from 2D medical images
There is provided a method for generating a 3D physical model of a patient specific anatomic feature from 2D medical images. The 2D medical images are uploaded by an end-user via a Web Application and sent to a server. The server processes the 2D medical images and automatically generates a 3D printable model of a patient specific anatomic feature from the 2D medical images using a segmentation technique. The 3D printable model is 3D printed as a 3D physical model such that it represents a 1:1 scale of the patient specific anatomic feature. The method includes the step of automatically identifying the patient specific anatomic feature.
1. A method for defining patient specific anatomical features from medical images, the method comprising:
receiving, by a server, medical images of a patient comprising one or more patient specific anatomical features;
automatically processing, by the server, the medical images using a segmentation algorithm to assign a label for each pixel of the medical images;
accessing, by the server, a database of medical image anatomical features;
using, by the server, an anatomical feature identification algorithm to probabilistically match the labeled pixels of the medical images against the database of medical image anatomical features to generate segmentation data that defines the one or more patient specific anatomical features based on the labeled pixels of the medical images;
generating, by the server, a 3D model of the one or more patient specific anatomical features using the generated segmentation data; and
validating the segmentation algorithm based on the generated segmentation data.
2. The method of claim 1 , wherein the database of medical image anatomical features comprises pre-labeled medical images and a graph database describing an ontology of the medical image anatomical features, and wherein the ontology takes into account standard medical imaging techniques.
3. The method of claim 2 , wherein the ontology is represented as a series of nodes representing the medical image anatomical features, the nodes connected with each other through at least one of: functions, proximity, anatomical groupings, or frequency of appearance in the same medical image scan.
4. The method of claim 2 , wherein the pre-labeled medical images comprise at least one of segmentation data previously generated by the server via the anatomical feature identification algorithm or manually labeled medical images.
5. The method of claim 1 , further comprising:
displaying the generated segmentation data via a web application,
wherein validating the segmentation algorithm based on the generated segmentation data comprises reviewing, by a user, the generated segmentation data via the web application.
6. The method of claim 5 , wherein reviewing the generated segmentation data comprises approving, by the user, the generated segmentation data via the web application.
7. The method of claim 6 , further comprising adding the approved generated segmentation data to the database of medical image anatomical features.
8. The method of claim 7 , further comprising training the segmentation algorithm using the database of medical image anatomical features.
9. The method of claim 5 , wherein reviewing the generated segmentation data comprises modifying, by the user, the generated segmentation data via the web application.
10. The method of claim 9 , wherein modifying the generated segmentation data comprises annotating, by the user, the generated segmentation data.
11. The method of claim 9 , further comprising generating, by the server, new segmentation data based on the modified generated segmentation data.
12. The method of claim 1 , wherein generating to 3D model of the one or more patient specific anatomical features using the generated segmentation data comprises generating, by the server, a 3D surface mesh model defining a surface of the one or more patient specific anatomical features using the generated segmentation data.
13. The method of claim 12 , further comprising:
displaying the 3D surface mesh model via a web application,
wherein validating the segmentation algorithm based on the generated segmentation data comprises reviewing, by a user, the 3D surface mesh model via the web application.
14. The method of claim 13 , wherein reviewing the 3D surface mesh model comprises approving, by the user, the 3D surface mesh model via the web application, the method further comprising 3D printing the approved 3D surface mesh model as a 3D physical model.
15. The method of claim 14 , further comprising performing, by a user, quality control to confirm that the 3D physical model matches dimensional accuracy of the medical images.
16. The method of claim 1 , further comprising:
generating, via the server, a set of standard anatomical models based on existing segmentation data from different datasets corresponding to various medical images stored in the database of medical image anatomical features,
wherein using the anatomical feature identification algorithm to generate the segmentation data comprises referencing, by the anatomical feature identification algorithm, the set of standard anatomical models stored in the database.
17. The method of claim 16 , wherein generating the set of standard anatomical models comprises aligning the existing segmentation data stored in the database and comparing one or more values of the aligned existing segmentation data.
18. The method of claim 16 , further comprising:
adding the generated segmentation data to the database of medical image anatomical features; and
updating the set of standard anatomical models based on the generated segmentation data added to the database.
19. The method of claim 1 , further comprising storing, by the server, a virtual record of steps taken by the server to generate the segmentation data to ensure quality control.
20. The method of claim 1 , wherein validating the segmentation algorithm based on the generated segmentation data comprises comparing, by the server, the generated segmentation data against the database of medical image anatomical features to provide a score indicative of the likelihood that the one or more patient specific anatomical features were classified correctly.