Segmentation of breast implants in MRI

Breast cancer is the most prevalent cancer among women globally, and magnetic resonance imaging (MRI) is increasingly being proposed as a screening tool in addition to its role as a diagnostic imaging modality. This creates a need for automated methods that analyse breast MR images. One of the tasks in BI-RADS based breast MRI reading is to assess whether implants are present. We trained nnU-Nets using 5-fold cross validation for the task of breast implant segmentation and assessed the segmentation quality on a multi-centric dataset consisting of 943 MRI studies, 207 of which contained breasts implants. Our models achieved a mean (standard deviation) Dice score of 0.96 (0.03) and an average symmetric surface distance of 0.95 (0.67) mm on the cases with breast implants. Of the 736 cases without implants, 575 were correctly predicted to have no implants, which was increased to 732 by simple volume filtering. Our findings suggest that breast implant detection and segmentation in MRI can be solved well by deep learning approaches, even with a limited amount of data.