System for determining medical images corresponding to radiology reports using artificial intelligence models

By using AI models to generate structured data and segment and label medical images, the problem of radiologists having difficulty identifying the specific medical images corresponding to radiology reports has been solved, improving review efficiency and saving resources.

CN122158008APending Publication Date: 2026-06-05GE PRECISION HEALTHCARE LLC
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-13
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Radiologists often struggle to quickly identify specific medical image datasets and regions of interest that correspond to radiology reports, leading to increased review time and resource consumption.

Method used

The first AI model generates structured data, the second AI model segments and labels the medical image dataset, and the structured data and labeled region set are combined to determine the regions of interest in the medical images.

Benefits of technology

It reduces the number of requests to medical image datasets, saves equipment, database and network resources, and improves the efficiency of radiologists.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122158008A_ABST
    Figure CN122158008A_ABST
Patent Text Reader

Abstract

A system (100) can receive a radiology report including radiologist observations about a region of interest of a subject and use a first AI model (310) to generate structured data including a predetermined set of fields and a corresponding set of values extracted from the radiology report. The system (1000) can use the first AI model (310) to determine, using the structured data, a medical image dataset of the subject stored in a medical image database (150) corresponding to the radiology report. The system (100) can use a second AI model (320) to segment and label a set of regions of each medical image of the medical image dataset. The system (100) can use the first AI model (310) to determine, using the structured data, a medical image of the medical image dataset that depicts the region of interest of the subject and perform an action based on determining the medical image that depicts the region of interest.
Need to check novelty before this filing date? Find Prior Art