Towards Automated Semantic Segmentation in Mammography Images
This work addresses the need for automated computer-aided detection to assist medical interpretation in mammography, though it appears incremental as it applies existing deep learning methods to a new dataset.
The paper tackles the problem of segmenting key anatomical structures in mammography images, such as the nipple and pectoral muscle, using a deep learning framework, and reports accurate segmentation performance on a large private dataset.
Mammography images are widely used to detect non-palpable breast lesions or nodules, preventing cancer and providing the opportunity to plan interventions when necessary. The identification of some structures of interest is essential to make a diagnosis and evaluate image adequacy. Thus, computer-aided detection systems can be helpful in assisting medical interpretation by automatically segmenting these landmark structures. In this paper, we propose a deep learning-based framework for the segmentation of the nipple, the pectoral muscle, the fibroglandular tissue, and the fatty tissue on standard-view mammography images. We introduce a large private segmentation dataset and extensive experiments considering different deep-learning model architectures. Our experiments demonstrate accurate segmentation performance on variate and challenging cases, showing that this framework can be integrated into clinical practice.