Learning data creation support apparatus, learning data creation support method, and learning data creation support program

US10916010B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-10916010-B2
Application numberUS-201916274723-A
CountryUS
Kind codeB2
Filing dateFeb 13, 2019
Priority dateFeb 28, 2018
Publication dateFeb 9, 2021
Grant dateFeb 9, 2021

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

Candidate positions of a plurality of lesion candidate region images obtained by performing an image analysis process for a medical image are displayed on schematic diagrams of a human body. Lesion candidate region images other than a lesion candidate region image corresponding to a denied candidate position where a denial operation has been received are registered as correct answer data or the lesion candidate region images corresponding to confirmed candidate positions where a confirmation operation has been received are registered as the correct answer data.

First claim

Opening claim text (preview).

What is claimed is: 1. A learning data creation support apparatus comprising: a display displays candidate positions of a plurality of lesion candidate region images obtained by performing an image analysis process for a medical image on a schematic diagram of a human body; and a processor configured to, receive a designation of a denial operation to all of at least one of the candidate positions that are denied; and after receiving a designation of the denial operation, register, as correct answer data, lesion candidate region images other than a lesion candidate region image corresponding to the at least one denied candidate positions where the denial operation has been received, wherein the processor further registers, as incorrect answer data, the lesion candidate region image corresponding to the at least one denied candidate positions and lesion candidate region images other than the lesion candidate region image corresponding to a confirmed candidate position. 2. The learning data creation support apparatus according to claim 1 , wherein marks are provided at a plurality of candidate positions on the schematic diagram of the human body, and the denial operation is an operation of removing the mark displayed at the candidate position. 3. The learning data creation support apparatus according to claim 2 , wherein marks are provided at a plurality of candidate positions on the schematic diagram of the human body, and the processor further configured to record a schematic diagram in which the marks are put at candidate positions other than the at least one denied candidate positions in a case in which the denial operation has been received in an interpretation report, or record a schematic diagram in which the mark is put at the confirmed candidate position in a case in which the confirmation operation has been received in an interpretation report. 4. The learning data creation support apparatus according to claim 2 , wherein the schematic diagram is a schema diagram. 5. The learning data creation support apparatus according to claim 1 , wherein marks are provided at a plurality of candidate positions on the schematic diagram of the human body, and the denial operation is an operation of removing the mark displayed at the candidate position. 6. The learning data creation support apparatus according to claim 1 , wherein marks are provided at a plurality of candidate positions on the schematic diagram of the human body, and the processor further configured to record a schematic diagram in which the marks are put at candidate positions other than the at least one denied candidate positions in a case in which the denial operation has been received in an interpretation report, or record a schematic diagram in which the mark is put at the confirmed candidate position in a case in which the confirmation operation has been received in an interpretation report. 7. The learning data creation support apparatus according to claim 6 , wherein the schematic diagram is a schema diagram. 8. The learning data creation support apparatus according to claim 1 , wherein marks are provided at a plurality of candidate positions on the schematic diagram of the human body, and the processor further configured to record a schematic diagram in which the marks are put at candidate positions other than the at least one denied candidate positions in a case in which the denial operation has been received in an interpretation report, or record a schematic diagram in which the mark is put at the confirmed candidate position in a case in which the confirmation operation has been received in an interpretation report. 9. The learning data creation support apparatus according to claim 1 , wherein the image analysis process is a process of detecting the lesion candidate region image with a discriminator that has learned the correct answer data, and the processor further configured to cause the discriminator to relearn the registered correct answer data. 10. The learning data creation support apparatus according to claim 9 , wherein the schematic diagram is a schema diagram. 11. The learning data creation support apparatus according to claim 1 , wherein the image analysis process is a process of detecting the lesion candidate region image with at least one of a discriminator that has learned the correct answer data or a discriminator that has learned the incorrect answer data, and the processor further configured to cause the discriminator to relearn at least one of the registered correct answer data or the registered incorrect answer data. 12. The learning data creation support apparatus according to claim 11 , wherein the schematic diagram is a schema diagram. 13. The learning data creation support apparatus according to claim 1 , wherein the schematic diagram is a schema diagram. 14. The learning data creation support apparatus according to claim 1 , wherein the schematic diagram is a schema diagram. 15. A learning data creation support method performed in a learning data creation support apparatus, the method comprising: displaying candidate positions of a plurality of lesion candidate region images obtained by performing an image analysis process for a medical image on a schematic diagram of a human body; receiving a designation of a denial operation to all of at least one of the candidate positions that are denied and after receiving a designation of the denial operation, registering, as correct answer data, lesion candidate region images other than a lesion candidate region image corresponding to the at least one denied candidate positions where the denial operation has been received, and registering, as incorrect answer data, the lesion candidate region image corresponding to the at least one denied candidate positions and lesion candidate region images other than the lesion candidate region image corresponding to a confirmed candidate position. 16. A non-transitory computer readable recording medium storing a learning data creation support program that causes a computer to: display candidate positions of a plurality of lesion candidate region images obtained by performing an image analysis process for a medical image on a schematic diagram of a human body; receive a designation of a denial operation to all of at least one of the candidate positions that are denied and after receiving a designation of the denial operation, registering, as correct answer data, lesion candidate region images other than a lesion candidate region image corresponding to the at least one denied candidate positions where the denial operation has been received, and register, as incorrect answer data, the lesion candidate region image corresponding to the at least one denied candidate positions and lesion candidate region images other than the lesion candidate region image corresponding to a confirmed candidate position. 17. A learning data creation support apparatus comprising: a memory that stores commands for causing a computer to perform processes; and a processor that is configured to execute the stored commands, wherein the processor displays candidate positions of a plurality of lesion candidate region images obtained by performing an image analysis process for a medical image on a schematic diagram of a human body, and the processor receives a designation of a denial operation to all of at least one of the candidate positions that are denied; and after receiving a designation of the denial operation, registers, as correct answer data, lesion candidate re

Assignees

Inventors

Classifications

  • G06T7/0012Primary

    Biomedical image inspection · CPC title

  • Computed x-ray tomography [CT] · CPC title

  • Region-based segmentation · CPC title

  • Positron emission tomography [PET] · CPC title

  • characterised by displaying multiple images or images and diagnostic data on one display · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US10916010B2 cover?
Candidate positions of a plurality of lesion candidate region images obtained by performing an image analysis process for a medical image are displayed on schematic diagrams of a human body. Lesion candidate region images other than a lesion candidate region image corresponding to a denied candidate position where a denial operation has been received are registered as correct answer data or the…
Who is the assignee on this patent?
Fujifilm Corp
What technology area does this patent fall under?
Primary CPC classification G06T7/0012. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Feb 09 2021 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 4 related publications on this page (citations in our corpus or others sharing the same primary CPC).