Automated Breast Ultrasound Lesions Detection Using Convolutional Neural Networks

• Published in: IEEE journal of biomedical and health informatics Vol. 22; no. 4; pp. 1218 - 1226
• Main Authors: Yap, Moi Hoon, Pons, Gerard, Marti, Joan, Ganau, Sergi, Sentis, Melcior, Zwiggelaar, Reyer, Davison, Adrian K., Marti, Robert
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Automation; Benign; Breast; Breast cancer; convolutional neural networks; Datasets; Deformation; Filtering; Formability; Fractals; Image acquisition; Imaging; lesion detection; Lesions; Machine learning; Neural networks; State of the art; Transfer learning; Ultrasonic imaging; Ultrasound; ultrasound imaging
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2017.2731873

Breast lesion detection using ultrasound imaging is considered an important step of computer-aided diagnosis systems. Over the past decade, researchers have demonstrated the possibilities to automate the initial lesion detection. However, the lack of a common dataset impedes research when comparing the performance of such algorithms. This paper proposes the use of deep learning approaches for breast ultrasound lesion detection and investigates three different methods: a Patch-based LeNet, a U-Net, and a transfer learning approach with a pretrained FCN-AlexNet. Their performance is compared against four state-of-the-art lesion detection algorithms (i.e., Radial Gradient Index, Multifractal Filtering, Rule-based Region Ranking, and Deformable Part Models). In addition, this paper compares and contrasts two conventional ultrasound image datasets acquired from two different ultrasound systems. Dataset A comprises 306 (60 malignant and 246 benign) images and Dataset B comprises 163 (53 malignant and 110 benign) images. To overcome the lack of public datasets in this domain, Dataset B will be made available for research purposes. The results demonstrate an overall improvement by the deep learning approaches when assessed on both datasets in terms of True Positive Fraction, False Positives per image, and F-measure.