Hybrid cloud-based measurement automation in medical imagery
View Patent ↗Measurement of medical images as a hybrid cloud service is provided. In various embodiments, pre-trained parameters are received at a client from a remote server. A local cognitive system is instantiated using the pre-trained parameters. The cognitive system is applied to evaluate a medical image. A result is sent to the remote server for training of a remote cognitive system.
1. A method comprising:
determining a first plurality of trained parameters via a remote cognitive system on a remote server;
receiving at a client the first plurality of trained parameters from the remote server;
using the first plurality of trained parameters to instantiate a local cognitive system at the client;
applying the local cognitive system to evaluate a medical image at the client;
receiving from a user a correction to the evaluation of the medical image, wherein the correction comprises an indication of a new lesion not identified in the evaluation of the medical image;
sending the correction to the remote server for training of the remote cognitive system;
receiving at the client a second plurality of trained parameters from the remote cognitive system, wherein the second plurality of trained parameters are determined by the remote cognitive system and are different than the first plurality of trained parameters; and
using the second plurality of trained parameters to instantiate the local cognitive system at the client.
2. The method of claim 1 , wherein the evaluation of the medical image comprises measuring an anatomical feature appearing in the medical image.
3. The method of claim 1 , wherein the local cognitive system is a neural network.
4. The method of claim 1 , wherein the remote cognitive system is a neural network.
5. The method of claim 1 , wherein the training of the remote cognitive system comprises updating the first plurality of trained parameters.
6. A computer program product for performing measurements of medical images, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:
determining a first plurality of trained parameters via a remote cognitive system on a remote server;
receiving at a client a first plurality of trained parameters from the remote server;
using the first plurality of trained parameters to instantiate a local cognitive system at the client;
applying the local cognitive system to evaluate a medical image at the client;
receiving from a user a correction to the evaluation of the medical image, wherein the correction comprises an indication of a new lesion not identified in the evaluation of the medical image;
sending the correction to the remote server for training of the remote cognitive system;
receiving at the client a second plurality of trained parameters from the remote cognitive system, wherein the second plurality of trained parameters are determined by the remote cognitive system and are different than the first plurality of trained parameters; and
using the second plurality of trained parameters to instantiate the local cognitive system at the client.
7. The computer program product of claim 6 , wherein the evaluation of the medical image comprises measuring an anatomical feature appearing in the medical image.
8. The computer program product of claim 6 , wherein the local cognitive system is a neural network.
9. The computer program product of claim 6 , wherein the remote cognitive system is a neural network.
10. The computer program product of claim 6 , wherein the training of the remote cognitive system comprises updating the first plurality of trained parameters.
11. The method of claim 2 , wherein the correction is a modification to a measurement obtained by the measuring of the anatomical feature appearing in the medical image.
12. The computer program product of claim 7 , wherein the correction comprises a modification to a measurement obtained by the measuring of the anatomical feature appearing in the medical image.
13. The method of claim 11 , wherein the measurement comprises a boundary and the correction comprises an adjustment to the boundary.
14. The computer program product of claim 12 wherein the measurement comprises a boundary and the correction comprises an adjustment to the boundary.