Medical image diagnosis examination method, apparatus, program product, and storage medium

CN122928073APending Publication Date: 2026-10-16SHENZHEN MINDRAY BIO MEDICAL ELECTRONICS CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202510426157.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-04-03
Publication Date
2026-10-16

AI Technical Summary

Technical Problem

[0004]有鉴于此,本申请提供了一种超声图像诊断考核方法、医学图像诊断考核方法、超声图像诊断考核、计算机设备、计算机程序产品及计算机可读存储介质,借助机器学习模型具体是文本生成模型实现诊断考核工作的自动化,以解决传统人工阅卷方式存在的一系列问题

Benefits of technology

[0025] As can be seen from the above technical solutions, the ultrasound image diagnostic assessment method, computer equipment, program product, and readable storage medium provided in this application embodiment can obtain the diagnostic text information input by the examinee user after making a diagnosis based on ultrasound images and related information, and obtain the answer diagnostic text information associated with the ultrasound image. The two parts of text information are input into a text generation model, which performs semantic analysis on the two parts of text information to obtain the target matching situation, and maps the target matching situation to the target assessment result according to the assessment criteria. This embodiment utilizes a text generation model with natural language parsing capabilities to automatically assess the diagnostic text information input by the examinee user using the answer diagnostic text information, thereby avoiding the problems of inconsistent assessment standards, low efficiency, and high labor costs caused by manual assessment methods, and significantly improving the quality, efficiency, and cost of ultrasound diagnostic assessment work.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application relates to the technical field of medical examination and training, and an ultrasonic image diagnosis examination method, a computer device, a program product, and a readable storage medium. Diagnosis text information input by an examinee user after diagnosis based on an ultrasonic image and auxiliary information can be acquired, and answer diagnosis text information associated with the ultrasonic image can be acquired. The two parts of text information are input into a text generation model, so that the text generation model performs semantic analysis on the two parts of text information to obtain a target matching condition. Diagnosis standards are input into the text generation model, so that the text generation model maps the target matching condition into a target examination result. The embodiment utilizes a text generation model with natural language analysis capability to automatically examine the diagnosis text information input by the examinee user by using the answer diagnosis text information, thereby avoiding problems such as non-uniform examination standards, low efficiency, and high labor cost caused by manual examination methods, and significantly improving the quality, efficiency, and cost of ultrasonic diagnosis examination work.
Need to check novelty before this filing date? Find Prior Art