Mammary gland lump image processing and classifying system

Abstract

The invention relates to a mammary gland lump image processing and classifying system which comprises a mammary gland X-ray machine used for shooting mammary gland X-ray photography images; an image preprocessing module used for preprocessing the mammary gland X-ray photography images; a breast area extraction module used for extracting breast area images in the preprocessed mammography images; and a lump detection and classification module used for carrying out lump position detection and benign and malignant classification on the breast area images by a DIoU-YOLOv3 target detection network.By implementing the mammary gland lump image processing and classifying system, the target detection network can be adopted to automatically detect and classify benign and malignant breast lumps, so that compared with manual film reading, speed is high, the efficiency is high, and accuracy rate is high.

Description

technical field [0001] The invention relates to image processing and classification technology, more specifically, relates to a mammary gland mass image processing and classification system. Background technique [0002] Relevant data show that on a global scale, breast cancer ranks first in the incidence of female malignancies in both developed and developing countries. Therefore, early detection of breast cancer is crucial to reduce female mortality. Among the current diagnostic methods for breast diseases, digital mammography is the most reliable screening method for early detection of suspicious breast masses and microcalcifications. When diagnosing breast abnormalities, radiologists classify suspicious masses as benign or malignant. However, a more accurate judgment on mammograms can only be made with extensive experience. More importantly, the existing diagnosis mainly relies on the subjective judgment of radiologists, which requires radiologists to have a high conc...

AI Technical Summary

Problems solved by technology

However, long hours and overloaded work will inevitably cause visual fatigue and mental fatigue

In addition, mammography is projection imaging, and dense glandular tissue is easy to block the tumor, while Asian women have a higher proportion of dense glandular glands, which is easy to misdiagnose and miss diagnosis

[0003] Therefore, in view of the low efficiency of breast mass image processing and classification in the prior art, heavy physician workload, and low accuracy and specificity, it is necessary to propose a breast mass image processing and classification with higher accuracy and faster diagnosis speed. system

Images