Automatic Auxiliary Detection System of Breast Tumor Based on Diffusion Magnetic Resonance Image

Abstract

The invention relates to an automatic auxiliary detection system for breast tumors based on diffusion magnetic resonance images, which is characterized in that an automatic lesion detection system including a threshold equipotential processing module, an averaging module and a parameterized fitting module is set; threshold equipotential processing The module uses the threshold equipotential algorithm to classify the selected b-value image to obtain the equipotential threshold, where b is the diffusion-sensitive gradient parameter; the averaging module is used to perform arithmetic mean processing on the pixel signal intensity selected under the equipotential threshold , to obtain the average signal intensity of the pixels in this area; the parameterized fitting module performs nonlinear fitting calculation on the average signal intensity under the allelic threshold, and obtains the apparent diffusion coefficient ADC and apparent diffusion Kurtosis AK. The invention can segment the tumor area, quantitatively calculate the diffusion-related parameters, and discriminate the benign and malignant attributes of breast tumors without trauma.

Description

technical field [0001] The invention relates to an automatic auxiliary detection system for breast tumors based on diffusion magnetic resonance images, and relates to the technical field of medical image acquisition and auxiliary detection. Background technique [0002] Breast cancer has developed into a disease with high morbidity and mortality in women. As the most commonly used method for diagnosing breast cancer, X-ray detection has relatively poor diagnostic effect in some relatively high-density tissues and organs. Magnetic resonance imaging (MRI) is gradually applied to the detection and diagnosis of breast tumors because of its high soft tissue contrast, good resolution of breast tissue, and no ionizing radiation. MRI detection of breast tumors usually involves injecting a certain amount of contrast agent, and combining the difference and distribution of time-domain signal amplitude values ​​before and after injection to determine the location of the malignant tumor...

AI Technical Summary

Problems solved by technology

However, unlike brain tissue, the boundaries of breast tumors are difficult to distinguish, and the heterogeneity is more obvious. Therefore, the reproducibility of breast cancer diagnosis results based on diffusion weighted imaging technology is low, and its related image processing needs to be further improved.

Images