The Breast Cancer Tumor Region Mapping Model Based on Multiple Sequences of Magnetic Resonance Images and Clustering Algorithms

The objective of this research is to solve the problem of target location mapping in breast cancer (BC) radiotherapy. We proposed a BC magnetic resonance (MR) images mapping model based on clustering algorithms. Compared with Digital Radiography (DR) and Computed Tomography (CT), MR images have unparalleled advantages in soft tissue imaging, and it can clearly distinguish the invasive range of breast tumors and surrounding tissues. The work used T1-weighted, T2-weighted, fat suppression sequence and enhancement sequence MR images from 12 patients with breast cancer to study. The MR images of the four sequences were clustered and compared using k-means and fuzzy c-means clustering methods. The experimental results show that using clustering algorithm, especially the k-means clustering combined with the MR images of multiple sequences, can well determine the region of breast tumors. At the same time, we compared the snake model and mapped the breast cancer MR images of the T1 sequence. The experimental results show that the k-means clustering combined with the multi-sequence MR images has higher mapping accuracy and robustness to noise. This shows that our method is feasible. It can solve the problem of lack of standard in breast cancer bed mapping.