A Human-Machine Collaborative Nodule Risk Rating System Based on Ultrasound Data

Abstract

The invention discloses a human-machine collaborative nodule risk rating system based on ultrasound data, which relates to the field of information technology. 1) Nodule area extraction module 2) Nodule feature extraction module 3) Interactive feature modification module 4) Comprehensive evaluation module. The nodule area extraction module screens the ultrasound data, extracts the nodule area data to be evaluated, and records the regional characteristics of the area to be evaluated; the nodule feature extraction module performs directional extraction of clinical features on the nodule area data, interactive features The modification module accepts users to delete and modify the clinical feature extraction results, and the comprehensive evaluation module reads the clinical features in real time and gives nodule risk scores and ratings based on the regional features and clinical features of the area to be evaluated.

Description

technical field [0001] The invention belongs to the field of information technology, and in particular relates to a human-machine collaborative nodule risk rating system based on ultrasound data, which can be used for quantitative evaluation of nodules in ultrasound data. Background technique [0002] Ultrasound images are an important basis for the evaluation of many nodules, such as the thyroid. At present, the evaluation of ultrasound images of various nodules relies on the subjective judgment given by the sonographer through experience with human eyes, and the repeatability and accuracy are heavily dependent on experience. Although there are some semi-quantitative evaluation indicators, they still have strong subjectivity. Physicians often use some subjective narratives in mutual communication and learning, which are prone to misunderstanding. Therefore, there is an urgent need for an efficient, stable, and repeatable quantitative evaluation tool. [0003] The current...

AI Technical Summary

Problems solved by technology

However, the disadvantages of this solution are: both traditional features and deep learning features are difficult to be understood by doctors, the identification process cannot be manually reviewed, and the security is insufficient

Images