Disease grading method and device based on machine learning, equipment and medium

Abstract

The invention discloses a disease grading method and device based on machine learning, equipment and a medium, the method belongs to the field of medical artificial intelligence, and the method comprises the following steps: acquiring a breast ultrasound image; calling a multi-task network to process the mammary gland ultrasonic image to obtain a first feature map and a semantic segmentation map of the mammary gland ultrasonic image, the first feature map comprising high-level semantic features of the mammary gland ultrasonic image, and the semantic segmentation map being a map for semantic segmentation of a focus area in the mammary gland ultrasonic image; performing feature extraction of different weights on the lesion area and the non-lesion area in the first feature map according to the semantic segmentation map to obtain a second feature map; and predicting according to the second feature map to obtain the BI-RADS grading of the breast ultrasound image. High-level semantic features with classification guidance are adopted as main grading features, different feature extraction is carried out on a lesion area and a non-lesion area by introducing a lesion contour, and an accurateBI-RADS grading result is obtained through regression.

Description

technical field [0001] The embodiments of the present application relate to the field of machine learning, and in particular to a machine learning-based disease grading method, device, device, and medium. Background technique [0002] Breast cancer is the number one killer of women, and early diagnosis and treatment is the most effective way to reduce the mortality rate of breast cancer. Ultrasound imaging is the most widely used breast cancer screening method in China due to its real-time, low-cost and non-radiation characteristics. Breast imaging reporting and data system (BI-RADS) grading is a clinical index for grading breast cancer. [0003] In related technologies, a neural network model is used to identify lesions in breast ultrasound images, thereby locating suspicious lesions in breast ultrasound images and predicting results of benign and malignant ones, and then the doctor infers the lesion according to all abnormal information in breast ultrasound images. Overa...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a disease grading method, device, equipment and medium based on machine learning, which can solve the problem of poor contrast in breast ultrasound images. Therefore, it is not possible to directly perform BI-RADS levels of breast ultrasound images in related technologies. problem of prediction

Images