Method and device for processing ultrasonic images and breast cancer diagnosis equipment

Abstract

The invention provides a method and a device for processing ultrasonic images and breast cancer diagnosis equipment. The method for processing the ultrasonic images comprises the following steps of: partitioning an ultrasonic image into a plurality of sub regions of the same type; determining the sub regions are object sub regions or background sub regions; and combining the determined object sub regions to form an object region. According to the method for processing the ultrasonic images, relatively clear object images can be obtained.

Description

technical field [0001] The present invention relates to processing ultrasound images. More particularly, it relates to a method and apparatus for processing ultrasound images and breast cancer diagnosis equipment. Background technique [0002] Breast cancer is one of the most common malignant tumors that seriously affects women's physical and mental health and even threatens their lives. Early detection is the key to reducing mortality, which can reduce mortality by about 40% or more. Ultrasound and mammography are increasingly used in breast imaging and as additional diagnostic testing techniques. Ultrasound is the imaging technique of choice when mammography is likely to have reduced sensitivity or presents unacceptable radiation hazards. Thus, computer-aided diagnosis (CAD) systems can help inexperienced physicians avoid misdiagnosis, reduce the number of benign lesion biopsies, and reduce inter-observer variability. [0003] Currently, most systems are either interact...

AI Technical Summary

Problems solved by technology

The breast computer-aided detection system (B-CAD) developed by Canada's Medipattern can reduce the time it takes for radiologists to analyze breast ultrasound images. It can automatically analyze, segment and classify images, but still requires manual input to achieve highly accurate results.

[0004] In addition, there are some methods using a single feature and a single classifier, but these methods cannot solve the problem of irregular tumor detection

For example, US7736313 relates to the detection of lesions in ultrasound images, which performs lesion detection based on the histogram in the window, and then classifies the lesions into three categories: benign, malignant and unknown, however the histogram is an imprecise feature and thus will lead to lesion detection big error in

US2003 / 0125621 relates to a method and system for automatically detecting lesions in ultrasound images, which detects lesions based on a pixel-based radial gradient index (RGI), but such lesion detection based only on RGI is inaccurate

Images