Abstract
AbstractTo 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 < 0.05). The area under the curve (AUC) predicted by FCM, WT, and CSS for histological classification were 0.818, 0.801, and 0.924, respectively. The fractional anisotropy (FA) value of patients with grade III was less than that of patients with grade I and II, while the apparent diffusion coefficient (ADC) value of patients with grade III was greater than that of patients with grade I and II (p < 0.05). The tumour diameter, number of lesions, and number of lymph node metastasis of patients with grade III increased markedly compared to patients with grade I and II (p < 0.05). To sum up, DCE‐MRI image segmentation results based on CSS were superior to FCM and WT in the evaluation of breast tumour histological grading. What's more, there were substantial differences in the obtained tumour diameter, FA value, ADC value, and number of lymph node metastasis based on DCE‐MRI of patients with grade I, II, and III, which could be applied to predict the histological grading of patients with breast cancer.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.