Developing breast dense tissue segmentation algorithm in digital breast tomosynthesis

Digital Breast Tomosynthesis (DBT) is an imaging modality that has proven to more effective for breast cancer screening, which is important for reducing mortality. However, existing studies on segmenting dense tissue in DBT remain limited, largely due to the challenges posed by the complexity of multi-slice variations, blurring, and out-of-plane artifacts. This study introduced a fully automated dense tissue segmentation algorithm in DBT image using a fully convolutional network. We employed 20 DBT scans from 20 normal patients (BIRADS 1) from the Breast-Cancer-Screening-DBT dataset. For establishing ground truth, one radiologist segmented breast dense tissue, and breast area mask in every slice of each DBT volume. We preprocessed each DBT volume slice-by-slice. Finally, we constructed 3-channel images (ground truth masks) by assigning breast area, fatty and dense area into R, G, B channels. Using the DBT images and ground truth, we fine-tuned the SegNet pretrained for segmenting breast density from 2D mammograms to segment both the breast and the fibroglandular areas in digital breast tomosynthesis (DBT) images. Using a test set, we achieved a dice score of 0.84±0.08, where a recent study reported a dice score of 0.76±0.16 for dense tissue segmentation in DBT. Our model performed better than the other models in the DBT.