Automatic segmentation algorithm for magnetic resonance imaging in prediction of breast tumour histological grading

To analyse the application value of dynamic contrast enhanced magnetic resonance imaging (DCE‐MRI) based on computer semi‐automatic segmentation (CSS) algorithm in tumour histological grading of breast cancer patients, the CSS algorithm of DCE‐MRI breast image was established based on Canny edge detection operator and dynamic binarization (DB) algorithm to compare with the fuzzy‐c‐means (FCM) algorithm based on FCM clustering and wavelet transform (WT) algorithm. Besides, CSS was applied to DCE‐MRI image diagnosis in 121 breast cancer patients, who were then classified as grade I, II, and III according to the 2019 edition of the World Health Organization Histological Grading Criteria for Breast Tumors. The results showed that the false positive rate (FPR) of CSS was sharply lower than that of FCM and WT, while the true positive rate (TPR) of CSS increased greatly in contrast to FCM and WT, indicating that there were statistically significant (p