Segmentation of Masses on Mammograms Using Data Augmentation and Deep Learning

• Published in: Journal of digital imaging Vol. 33; no. 4; pp. 858 - 868
• Main Authors: Zeiser, Felipe André, da Costa, Cristiano André, Zonta, Tiago, Marques, Nuno M. C., Roehe, Adriana Vial, Moreno, Marcelo, da Rosa Righi, Rodrigo
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01-08-2020; Springer Nature B.V
• Subjects: Accuracy; Breast cancer; Data augmentation; Deep learning; Diagnosis; Digital imaging; Digitization; Image contrast; Image enhancement; Image segmentation; Imaging; Lesions; Mammography; Medical imaging; Medicine; Medicine & Public Health; Original Paper; Parameter sensitivity; Radiology; Zooming; Deep learning; Breast cancer; Fully convolutional network; Segmentation; Computer-aided detection; U-Net
• ISSN: 0897-1889; 1618-727X
• DOI: 10.1007/s10278-020-00330-4

The diagnosis of breast cancer in early stage is essential for successful treatment. Detection can be performed in several ways, the most common being through mammograms. The projections acquired by this type of examination are directly affected by the composition of the breast, which density can be similar to the suspicious masses, being a challenge the identification of malignant lesions. In this article, we propose a computer-aided detection (CAD) system to aid in the diagnosis of masses in digitized mammograms using a model based in the U-Net, allowing specialists to monitor the lesion over time. Unlike most of the studies, we propose the use of an entire base of digitized mammograms using normal, benign, and malignant cases. Our research is divided into four stages: (1) pre-processing, with the removal of irrelevant information, enhancement of the contrast of 7989 images of the Digital Database for Screening Mammography (DDSM), and obtaining regions of interest. (2) Data augmentation, with horizontal mirroring, zooming, and resizing of images; (3) training, with tests of six-based U-Net models, with different characteristics; (4) testing, evaluating four metrics, accuracy, sensitivity, specificity, and Dice Index. The tested models obtained different results regarding the assessed parameters. The best model achieved a sensitivity of 92.32%, specificity of 80.47%, accuracy of 85.95% Dice Index of 79.39%, and AUC of 86.40%. Even using a full base without case selection bias, the results obtained demonstrate that the use of a complete database can provide knowledge to the CAD expert.