Lesion image lesion detection method and device

Abstract

The invention discloses a lesion detection method and device for a lesion image. The method comprises the following steps: extracting a background priori feature map from a preset lesion image according to a preset priori clustering algorithm; obtaining a potential target area in the background prior feature map through an adaptive threshold segmentation algorithm, and calculating normalized coordinates of a potential target center of the potential target area to obtain a center prior feature map; a preset Log-Gabor filter is adopted to perform band-pass filtering processing on the preset lesion image, so that a frequency prior feature map can be obtained; performing feature map fusion processing on the background prior feature map, the center prior feature map and the frequency prior feature map to obtain a fused prior feature map; and adopting a preset image segmentation algorithm to carry out smooth optimization processing on the fused prior feature map to obtain a target lesion detection result. According to the invention, the technical problem of poor detection effect on lesion images with poor image quality, small lesion area and fuzzy boundary in the prior art is solved.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to a lesion detection method and device for lesion images. Background technique [0002] Breast cancer is the most common cancer in women all over the world, and it is one of the main cancers that cause death in women all over the world. Statistics show that the incidence of breast cancer is increasing year by year, and the incidence is gradually getting younger. Clinical studies in recent years have found that if breast tumors can be detected early and treated effectively, the success rate of cure can be greatly improved. Therefore, early diagnosis and detection methods are very important. [0003] At present, breast ultrasound is the main means of breast cancer screening, and the automatic detection of lesions in breast ultrasound images is of great significance for computer-aided diagnosis in the era of artificial intelligence. In the traditional diagnosis of...

AI Technical Summary

Problems solved by technology

[0005] The present application provides a lesion detection method and device for a lesion image, which is used to solve the technical problem of poor detection effect of lesion images with poor image quality, small lesion area and blurred border in the prior art

Images