Detecting and classifying medical images based on continuously-learning whole body landmarks detections
A computer-implemented method for automatically generating metadata tags for a medical image includes receiving a medical image and automatically identifying a set of body landmarks in the medical image using one or more machine learning models. A set of rules are applied to the set of body landmarks to identify anatomical objects present in the image. As an alternative to using the set of rules, in some embodiments, one or more machine learning models to the set of body landmarks to identify anatomical objects present in the image. Once the anatomical objects are identified, metadata tags corresponding to the anatomical objects are generated and stored in the medical image. Then, the medical image with the metadata tags is transferred to a data repository.
1. A computer-implemented method for automatically generating metadata tags for a medical image, the method comprising:
receiving a medical image;
automatically identifying a set of body landmarks in the medical image using one or more machine learning models;
applying a set of rules to the set of body landmarks to identify anatomical objects present in the image;
generating one or more metadata tags corresponding to the anatomical objects;
storing the metadata tags in the medical image;
transferring the medical image with the metadata tags to a data repository;
receiving user feedback comprising a modification to one or more of the metadata tags associated with the medical image stored in the data repository; and
updating the set of rules based on the received modification.
2. The method of claim 1 , wherein the one or more machine learning models comprise a deep reinforcement learning model.
3. The method of claim 1 , wherein each rule in the set of rules defines an upper bound landmark and a lower bound landmark for a corresponding anatomical object.
4. The method of claim 3 , wherein each rule in the set of rules defines a left bound landmark and a right bound landmark for the corresponding anatomical object.
5. The method of claim 1 , wherein the modification comprises a modification or deletion of one or more of the metadata tags.
6. The method of claim 1 , wherein the modification comprises an addition of one or more new metadata tags.
7. The method of claim 1 , wherein the medical image is acquired using a medical image scanner and the method is performed immediately following image reconstruction on a computer connected to the medical image scanner.
8. The method of claim 7 , wherein the medical image scanner is a magnetic resonance imaging (MM) scanner.
9. A computer-implemented method for automatically generating metadata tags for a medical image, the method comprising:
receiving a medical image;
identifying a set of body landmarks in the medical image;
applying one or more machine learning models to the set of body landmarks to identify anatomical objects present in the image;
generating one or more metadata tags corresponding to the anatomical objects;
storing the metadata tags in the medical image;
transferring the medical image with the metadata tags to a data repository;
receiving user feedback comprising a modification to one or more of the metadata tags associated with the medical image stored in the data repository; and
retraining the one or more machine learning models based on the received modification.
10. The method of claim 9 , wherein the one or more machine learning models comprise a random forest.
11. The method of claim 10 , wherein the random forest is trained using a plurality of medical images labeled with an upper bound landmark, a lower bound landmark, and one or more labeled anatomical objects located between the upper bound landmark and the lower bound landmark.
12. The method of claim 11 , wherein the plurality of medical images are further labeled with a left bound landmark and a right bound landmark, and the one or more labeled anatomical objects are located between the left bound landmark and the right bound landmark.
13. The method of claim 9 , wherein the modification comprises a modification or deletion of one or more of the metadata tags.
14. The method of claim 9 , wherein the modification comprises an addition of one or more new metadata tags.
15. The method of claim 9 , wherein the medical image is acquired using a medical image scanner and the method is performed immediately following image reconstruction on a computer connected to the medical image scanner.
16. The method of claim 15 , wherein the medical image scanner is a MM scanner.
17. A system for automatically generating metadata tags for a medical image, the method comprising:
a medical image scanner configured to acquire a medical image; and
an image processing system comprising one or more processors configured to
automatically identify a set of body landmarks in the medical image;
identify anatomical objects present in the image based on the set of body landmarks;
generate, using a program module configured to identify anatomical objects present in the image from the set of body landmarks, one or more metadata tags corresponding to the anatomical objects;
store the metadata tags in the medical image;
transfer the medical image with the metadata tags to a data repository;
receive user feedback comprising a modification to one or more of the metadata tags associated with the medical image stored in the data repository; and
adjust the program module based on the received modification.
18. The system of claim 17 , wherein the medical image scanner is a MM scanner.
19. The system of claim 17 , wherein:
the program module comprises a set of rules; and
the image processing system is configured to adjust the program module by updating the set of rules based on the received modification.
20. The system of claim 17 , wherein:
the program module comprises one or more machine learning models; and
the image processing system is configured to adjust the program module by retraining the one or more machine learning models based on the received modification.