Automated and real-time segmentation of suspicious breast masses using convolutional neural network

• Published in: PloS one Vol. 13; no. 5; p. e0195816
• Main Authors: Kumar, Viksit, Webb, Jeremy M., Gregory, Adriana, Denis, Max, Meixner, Duane D., Bayat, Mahdi, Whaley, Dana H., Fatemi, Mostafa, Alizad, Azra
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 16.05.2018; Public Library of Science (PLoS)
• Subjects: Adult; Aged; Aged, 80 and over; Algorithms; Analysis; Artificial intelligence; Artificial neural networks; Automation; Biology; Biomedical engineering; Biopsy; Breast; Breast - diagnostic imaging; Breast cancer; Breast Neoplasms - diagnostic imaging; Carcinoma, Ductal, Breast - diagnostic imaging; Carcinoma, Intraductal, Noninfiltrating - diagnostic imaging; Carcinoma, Lobular - diagnostic imaging; Diagnosis; Female; Humans; Image processing; Image Processing, Computer-Assisted - methods; Image segmentation; Mammography; Mammography - methods; Medical imaging; Medical research; Medical screening; Medicine; Medicine and Health Sciences; Middle Aged; Morphology; Neural networks; Neural Networks, Computer; NMR; Nuclear magnetic resonance; Pattern Recognition, Automated; Physical Sciences; Physiology; Prospective Studies; Real time; Research and Analysis Methods; Risk factors; Segmentation; Software; Therapeutic applications; Tumors; Ultrasonic imaging; Ultrasonography, Mammary - methods; Ultrasound; Young Adult; United States > US; Minnesota
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0195816

In this work, a computer-aided tool for detection was developed to segment breast masses from clinical ultrasound (US) scans. The underlying Multi U-net algorithm is based on convolutional neural networks. Under the Mayo Clinic Institutional Review Board protocol, a prospective study of the automatic segmentation of suspicious breast masses was performed. The cohort consisted of 258 female patients who were clinically identified with suspicious breast masses and underwent clinical US scan and breast biopsy. The computer-aided detection tool effectively segmented the breast masses, achieving a mean Dice coefficient of 0.82, a true positive fraction (TPF) of 0.84, and a false positive fraction (FPF) of 0.01. By avoiding positioning of an initial seed, the algorithm is able to segment images in real time (13-55 ms per image), and can have potential clinical applications. The algorithm is at par with a conventional seeded algorithm, which had a mean Dice coefficient of 0.84 and performs significantly better (P< 0.0001) than the original U-net algorithm.