Image diagnosis supporting device and image processing method

Patent metadata

Field	Value
Publication number	US-11923072-B2
Application number	US-202117197445-A
Country	US
Kind code	B2
Filing date	Mar 10, 2021
Priority date	Sep 28, 2020
Publication date	Mar 5, 2024
Grant date	Mar 5, 2024

Abstract

An image diagnosis supporting device includes a model reader that reads an image diagnostic model that outputs a diagnostic result for a diagnostic image that is an input medical image, a storage unit that stores facility data that is a plurality of medical images associated with diagnostic results held in a facility, and an adjuster that adjusts, based on the facility data, the image diagnostic model or the diagnostic image input to the image diagnostic model.

First claim

What is claimed is:

1. An image diagnosis supporting device comprising:
a processor; and
a memory storing instructions, that when executed by the processor, configure the processor to:
read an image diagnostic model that outputs a diagnostic result for a diagnostic image that is an input medical image,
store facility data that is a plurality of medical images associated with diagnostic results held in a facility,
adjust, based on the facility data, the image diagnostic model or the diagnostic image input to the image diagnostic model, and
generate a facility histogram that is a histogram of a size of a tumor included in each of the medical images of the facility data, and adjust a size of the diagnostic image based on the facility histogram.

2. The image diagnosis supporting device according to claim 1 ,
wherein the image diagnostic model is generated by learning teacher data that is a plurality of medical images different from the facility data, and
wherein the processor is configured to generate a teacher histogram that is a histogram of a size of a tumor included in each of the medical images of the teacher data, and adjust the size of the diagnostic image based on a facility mode value that is a mode value of the facility histogram and a teacher mode value that is a mode value of the teacher histogram.

3. The image diagnosis supporting device according to claim 2 ,
wherein the processor is configured to multiply the size of the diagnostic image by a value obtained by dividing the teacher mode value by the facility mode value.

4. The image diagnosis supporting device according to claim 1 ,
wherein processor is configured to, when a high-luminance region is present near a tumor included in each of the medical images of the facility data, adjust the diagnostic image by removing the high-luminance region.

5. The image diagnosis supporting device according to claim 1 ,
wherein the processor is configured to adjust the image diagnostic model by relearning data that is data generated based on the facility histogram.

6. The image diagnosis supporting device according to claim 5 ,
wherein the image diagnostic model is generated by learning teacher data that is a plurality of medical images different from the facility data, and
wherein the processor is configured to extract the relearning data from the teacher data based on the facility histogram.

7. The image diagnosis supporting device according to claim 6 ,
wherein the processor is configured to calculate a probability function for extracting a medical image from the teacher data based on the facility histogram and use the probability function to extract the relearning data.

8. The image diagnosis supporting device according to claim 1 ,
wherein the processor is configured to:
determine, based on a diagnostic result of the image diagnostic model, whether the adjustment is to be executed, and
upon determining the adjustment is to be executed, adjust the image diagnostic model or the diagnostic image input to the diagnostic model.

9. The image diagnosis supporting device according to claim 1 ,
further comprising a display coupled to the processor,
wherein the processor is configured to display a screen for selecting an item to be used for a statistical process to be executed on the facility data on the display.

10. An image processing method for causing a computer to execute a process, the process comprising the steps of:
reading an image diagnostic model that outputs a diagnostic result for a diagnostic image that is an input medical image;
adjusting, based on facility data that is a plurality of medical images associated with diagnostic results held in a facility, the image diagnostic model or the diagnostic image input to the image diagnostic model;
generating a facility histogram that is a histogram of a size of a tumor included in each of the medical images of the facility data, and adjusting a size of the diagnostic image based on the facility histogram.

Assignees

• Hitachi Ltd

Inventors

• Kaneko Yukio
• Li Yun
• Li Zisheng
• Kishimoto Aya
• Matsuzaki Kazuki
• ZHU Peifei
• Ogino Masahiro

Classifications

• G16H30/40 Primary

  for processing medical images, e.g. editing · CPC title

• G06T5/40

  using histogram techniques · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G06T2207/20081

  Training; Learning · CPC title