Sierra-Franco Cesar A, Hurtado Jan, de A Thomaz Victor, da Cruz Leonardo C, Silva Santiago V, Silva-Calpa Greis Francy M, Raposo Alberto
Tecgraf Institute and Department of Informatics, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, RJ, Brazil.
J Imaging Inform Med. 2024 Dec 11. doi: 10.1007/s10278-024-01364-8.
Mammography images are widely used to detect non-palpable breast lesions or nodules, aiding in cancer prevention and enabling timely intervention when necessary. To support medical analysis, computer-aided detection systems can automate the segmentation of landmark structures, which is helpful in locating abnormalities and evaluating image acquisition adequacy. This paper presents a deep learning-based framework for segmenting the nipple, the pectoral muscle, the fibroglandular tissue, and the fatty tissue in standard-view mammography images. To the best of our knowledge, we introduce the largest dataset dedicated to mammography segmentation of key anatomical structures, specifically designed to train deep learning models for this task. Through comprehensive experiments, we evaluated various deep learning model architectures and training configurations, demonstrating robust segmentation performance across diverse and challenging cases. These results underscore the framework's potential for clinical integration. In our experiments, four semantic segmentation architectures were compared, all showing suitability for the target problem, thereby offering flexibility in model selection. Beyond segmentation, we introduce a suite of applications derived from this framework to assist in clinical assessments. These include automating tasks such as multi-view lesion registration and anatomical position estimation, evaluating image acquisition quality, measuring breast density, and enhancing visualization of breast tissues, thus addressing critical needs in breast cancer screening and diagnosis.
乳腺钼靶图像被广泛用于检测不可触及的乳腺病变或结节，有助于癌症预防，并在必要时进行及时干预。为了支持医学分析，计算机辅助检测系统可以自动分割标志性结构，这有助于定位异常并评估图像采集的充分性。本文提出了一种基于深度学习的框架，用于分割标准视图乳腺钼靶图像中的乳头、胸肌、纤维腺体组织和脂肪组织。据我们所知，我们引入了最大的专门用于关键解剖结构乳腺钼靶分割的数据集，该数据集是专门为训练深度学习模型完成这项任务而设计的。通过全面的实验，我们评估了各种深度学习模型架构和训练配置，在各种具有挑战性的病例中展示了强大的分割性能。这些结果强调了该框架在临床整合方面的潜力。在我们的实验中，比较了四种语义分割架构，所有这些架构都显示出适用于目标问题，从而在模型选择上提供了灵活性。除了分割，我们还引入了一系列源自该框架的应用程序来协助临床评估。这些应用包括自动执行多视图病变配准和解剖位置估计等任务、评估图像采集质量、测量乳腺密度以及增强乳腺组织的可视化，从而满足乳腺癌筛查和诊断中的关键需求。
