A deep learning framework for efficient analysis of breast volume and fibroglandular tissue using MR data with strong artifacts

• Published in: International journal for computer assisted radiology and surgery Vol. 14; no. 10; pp. 1627 - 1633
• Main Authors: Ivanovska, Tatyana, Jentschke, Thomas G., Daboul, Amro, Hegenscheid, Katrin, Völzke, Henry, Wörgötter, Florentin
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.10.2019; Springer Nature B.V
• Subjects: Adult; Algorithms; Breast; Breast Density - physiology; Breast Neoplasms - diagnostic imaging; Computer Imaging; Computer Science; Deep Learning; Density; Epidemiology; Female; Health Informatics; Humans; Image segmentation; Imaging; Inhomogeneity; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medicine; Medicine & Public Health; Original Article; Pattern Recognition and Graphics; Radiology; Surgery; Vision; Deep learning; Breast density; Segmentation; MRI
• ISSN: 1861-6410; 1861-6429
• DOI: 10.1007/s11548-019-01928-y

Purpose The main purpose of this work is to develop, apply, and evaluate an efficient approach for breast density estimation in magnetic resonance imaging data, which contain strong artifacts including intensity inhomogeneities. Methods We present a pipeline for breast density estimation, which consists of intensity inhomogeneity correction, breast volume segmentation, nipple extraction, and fibroglandular tissue segmentation. For the segmentation steps, a well-known deep learning architecture is employed. Results The average Dice coefficient for the breast parenchyma is 92.5 % ± 0.011 , which outperforms the classical state-of-the-art approach by a margin of 9 % . Conclusion The proposed solution is accurate and highly efficient and has potential to be applied for big epidemiological data with thousands of participants.