Lesion image evaluation system for esophagus cancer

By generating initial lesion area focus data and combining it with the doctor's interactive acquisition module to learn individual preference parameters, the problem of existing systems being unable to adapt to different doctors' interpretation habits has been solved, personalized output has been achieved, and the efficiency and accuracy of esophageal cancer lesion image assessment have been improved.

CN122336478APending Publication Date: 2026-07-03ZHEJIANG HOSPITAL
1 Cites 0 Cited by

Patent Information

Application Number
CN202610478778.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-13
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

Existing esophageal cancer lesion image assessment systems are difficult to personalize and cannot adapt to the interpretation habits of different doctors, resulting in doctors needing to make repeated corrections, increasing their workload and time costs.

Method used

The initial lesion area data is generated by the basic image processing module, and the correction operations are recorded by the doctor interaction acquisition module. Individual preference parameters are learned, and personalized output is generated by the preference learning module. The model accuracy is improved by combining self-supervised training and pseudo-labeling enhancement training.

Benefits of technology

It reduces the amount of repetitive corrections doctors need to make in case processing, improves work efficiency, slows down the rate of increase in workload, and enhances the overall throughput efficiency and result consistency of assessment tasks.

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

Abstract

The invention discloses a lesion image evaluation system for esophagus cancer, and the system comprises a basic image processing module which is used for generating initial lesion region attention data for an input esophagus image; the doctor interaction acquisition module is used for acquiring a correction operation of a doctor on the attention data of the initial lesion area; the preference learning module is used for learning individual preference parameters of the corresponding doctors according to the correction operation; and the personalized output module is used for calibrating the initial lesion area attention data based on the individual preference parameters and outputting personalized lesion area attention data. According to the lesion image evaluation system for the esophagus cancer, the evaluation process of the lesion image of the esophagus cancer can be improved, the repeated correction operation of a doctor in continuous case processing is reduced, the extra labor amount generated along with the increase of the number of cases is reduced, the initial output better fits the interpretation mode of the doctor, and therefore the working efficiency of the overall evaluation task is improved.
Need to check novelty before this filing date? Find Prior Art