Methods and devices for grading a medical image

Patent metadata

Field	Value
Publication number	US-11145405-B2
Application number	US-201916509950-A
Country	US
Kind code	B2
Filing date	Jul 12, 2019
Priority date	Dec 27, 2018
Publication date	Oct 12, 2021
Grant date	Oct 12, 2021

Abstract

Method and system for grading a medical image. For example, a system for grading a medical image comprising a grading network configured to provide a grading result corresponding to the medical image based on at least the medical image and/or a list of lesion candidates generated by a lesion identification network.

First claim

What is claimed is:

1. A system for grading a medical image, the system comprising:
a grading network configured to provide a grading result corresponding to the medical image based on at least the medical image and/or a list of lesion candidates generated by a lesion identification network;
wherein the grading network is further configured to at least one of:
provide one or more outputs to guide manual scheduling of a plurality of radiographs for manual review and diagnosis based on at least a plurality of grading results corresponding to the plurality of radiographs; or
automatically schedule the plurality of radiographs for manual review and diagnosis based on at least a plurality of grading results corresponding to the plurality of radiographs.

2. The system of claim 1 , wherein:
the grading network is further configured to provide the grading result corresponding to the medical image based on at least the medical image and the list of lesion candidates generated by the lesion identification network.

3. The system of claim 1 , wherein:
the grading network is further configured to provide the grading result corresponding to the medical image based on at least the medical image.

4. The system of claim 1 , wherein:
the lesion identification network is configured to provide a score corresponding to the list of lesion candidates;
the grading result is provided further based on the score; and
the score is provided based on at least a probability value corresponding to the medical image including lesions of multiple lesion categories.

5. The system of claim 1 , wherein:
the medical image includes a chest radiograph; and
the list of lesion candidates includes at least one list selected from a group consisting of a list of lung lesion candidates, a list of cardiac lesion candidates, a list of cardiovascular lesion candidates, a list of hilar lesion candidates, a list of bone tissue lesion candidates, and a list of pleural lesion candidates.

6. The system of claim 1 , wherein the grading network is a student network trained by an attention transfer learning process comprising:
establishing a teacher network and the student network for the grading network;
training the teacher network; and
training the student network based on at least:
extracting a feature map from one or more middle layers corresponding to both the student network and the teacher network;
calculating one or more attention transfer learning losses corresponding to the one or more middle layers; and
backpropagating the one or more attention transfer learning losses into the student network.

7. The system of claim 1 , wherein the grading result corresponds to at least one selected from a group consisting of severity and urgency.

8. The system of claim 1 , wherein the lesion identification network is configured to identify at least one lesion characteristic selected from a group consisting of color, shape, size, grayscale value, position, and morphology.

9. The system of claim 1 , wherein the grading result is provided based on the medical image as a whole or one or more partial regions of the medical image.

10. The system of claim 1 , wherein the grading result is selected from a group consisting of a first grade, a second grade, and a third grade, wherein:
the first grade corresponds to a first priority for reading and diagnosis;
the second grade corresponds to a second priority for reading and diagnosis;
the third grade corresponds to a third priority for reading and diagnosis;
the first priority being greater than the second and third priorities.

11. A computer-implemented method for grading a medical image, the method comprising:
providing a grading result corresponding to the medical image based on at least the medical image and/or a list of lesion candidates generated by a lesion identification network; and at least one of:
providing one or more outputs to guide manual scheduling of a plurality of radiographs for manual review and diagnosis based on at least a plurality of grading results corresponding to the plurality of radiographs; or
automatically scheduling the plurality of radiographs for manual review and diagnosis based on at least a plurality of grading results corresponding to the plurality of radiographs.

12. The computer-implemented method of claim 11 , further including:
providing the grading result corresponding to the medical image based on at least the medical image and the list of lesion candidates generated by the lesion identification network.

13. The computer-implemented method of claim 11 , further including:
providing the grading result corresponding to the medical image based on at least the medical image.

14. The computer-implemented method of claim 11 , further includes:
providing a score corresponding to the list of lesion candidates using the lesion identification network;
wherein the providing a grading result is further based on the score; and
wherein the providing a score is based on at least a probability value corresponding to the medical image including lesions of multiple lesion categories.

15. The computer-implemented method of claim 11 , further includes training a student network to be the grading network based on an attention transfer learning process comprising:
establishing a teacher network and the student network for the grading network;
training the teacher network; and
training the student network based on at least:
extracting a feature map from one or more middle layers corresponding to both the student network and the teacher network;
calculating one or more attention transfer learning losses corresponding to the one or more middle layers; and
backpropagating the one or more attention transfer learning losses into the student network.

16. The computer-implemented method of claim 11 , wherein the scheduling of the plurality of radiographs for manual review and diagnosis is based on at least one selected from a group consisting of expertise, pay level, and seniority.

17. A non-transitory computer-readable medium with instructions stored thereon, that when executed by a processor, perform the processes of:
providing a grading result corresponding to the medical image based on at least the medical image and/or a list of lesion candidates generated by a lesion identification network; and at least one of:
providing one or more outputs to guide manual scheduling of a plurality of radiographs for manual review and diagnosis based on at least a plurality of grading results corresponding to the plurality of radiographs; or
automatically scheduling the plurality of radiographs for manual review and diagnosis based on at least a plurality of grading results corresponding to the plurality of radiographs.

Assignees

• Shanghai United Imaging Intelligence Co Ltd

Inventors

• Cheng Jie-Zhi
• Gong Zaiwen
• He Zhiqiang
• Zhan Yiqiang
• Zhou Xiang Sean

Classifications

• G06F18/2413

  based on distances to training or reference patterns · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06N3/096

  Transfer learning · CPC title

• G06N3/0895

  Weakly supervised learning, e.g. semi-supervised or self-supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title