Computer-aided method and device using medical ultrasonic image in tumor diagnosis

By extracting the imaging group feature of medical ultrasound images and processing the combined scoring model with clinical data, the limitations of tumor diagnosis relying on manual judgment in the prior art are solved, and a rapid and accurate assessment of the probability of tumor deterioration is achieved.

CN120031829AInactive Publication Date: 2025-05-23THE THIRD AFFILIATED HOSPITAL OF XINJIANG MEDICAL UNIV
0 Cites 0 Cited by

Patent Information

Application Number
CN202510107400.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-01-23
Publication Date
2025-05-23
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The prior art relies on the experience and subjective judgment of doctors in tumor diagnosis, resulting in limitations in the accurate diagnosis and prognosis of tumors.

Method used

By extracting the imaging group feature of medical ultrasound images and processing the extracted features and clinical data based on the scoring model, automated tumor degree evaluation is achieved.

Benefits of technology

A rapid and accurate assessment of the probability of tumor deterioration is achieved, and it has higher efficiency and repeatability than manual treatment.

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

Abstract

The invention relates to the technical field of medical image processing, in particular to a computer-aided method and device using medical ultrasonic images in tumor diagnosis. A segmented image about a tumor area is obtained by segmenting an ultrasonic image, multiple image group features and shape features of the segmented image are extracted, the image group features and the shape features are processed based on a joint scoring model to obtain a corresponding scoring result, and a tumor deterioration probability value is realized. According to the embodiment of the invention, automatic tumor degree evaluation can be realized, and compared with manual processing in the prior art, the image can be quickly segmented, and the segmentation result can be accurately evaluated.
Need to check novelty before this filing date? Find Prior Art