Information processing apparatus, information processing method, and information processing program for supporting interpretation of medical image
AssigneeFUJIFILM Corporation
InventorsTaro Hatsutani, Akimichi Ichinose
Life of this patent
Estimating the term…
Abstract
An information processing apparatus comprising at least one processor, wherein the processor is configured to: acquire a medical image including a plurality of lesion regions; specify a plurality of pieces of first findings information for each of the plurality of lesion regions; and specify second findings information for at least one lesion region among the plurality of lesion regions based on a combination of the plurality of pieces of first findings information.
Claims8
An information processing apparatus comprising at least one processor, wherein the processor is configured to:
- acquire a medical image including a plurality of lesion regions;
- specify a plurality of pieces of first findings information for each of the plurality of lesion regions by using a first learning model trained in advance, wherein the first learning model receives the lesion region as an input and outputs the first findings information;
- and
- specify second findings information for at least one lesion region among the plurality of lesion regions based on a combination of the plurality of pieces of first findings information by using a second learning model trained in advance, wherein the second learning model receives the plurality pieces of first findings information and the medical image as inputs and outputs the second findings information.
An information processing method comprising:
- acquiring a medical image including a plurality of lesion regions;
- specifying a plurality of pieces of first findings information for each of the plurality of lesion regions by using a first learning model trained in advance, wherein the first learning model receives the lesion region as an input and outputs the first findings information;
- and
- specifying second findings information for at least one lesion region among the plurality of lesion regions based on a combination of the plurality of pieces of first findings information by using a second learning model trained in advance, wherein the second learning model receives the plurality pieces of first findings information and the medical image as inputs and outputs the second findings information.
A non-transitory computer-readable storage medium storing an information processing program for causing a computer to execute a process comprising:
- acquiring a medical image including a plurality of lesion regions;
- specifying a plurality of pieces of first findings information for each of the plurality of lesion regions by using a first learning model trained in advance, wherein the first learning model receives the lesion region as an input and outputs the first findings information;
- and
- specifying second findings information for at least one lesion region among the plurality of lesion regions based on a combination of the plurality of pieces of first findings information by using a second learning model trained in advance, wherein the second learning model receives the plurality pieces of first findings information and the medical image as inputs and outputs the second findings information.
Dependencies are inferred from the claim text.