Tumor Detection in Automated Breast Ultrasound Using 3-D CNN and Prioritized Candidate Aggregation

• Published in: IEEE transactions on medical imaging Vol. 38; no. 1; pp. 240 - 249
• Main Authors: Chiang, Tsung-Chen, Huang, Yao-Sian, Chen, Rong-Tai, Huang, Chiun-Sheng, Chang, Ruey-Feng
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Abnormalities; Agglomeration; Algorithms; Artificial neural networks; Automated whole breast ultrasound; Automation; Breast; Breast - diagnostic imaging; Breast cancer; Breast Neoplasms - diagnostic imaging; Candidates; computer-aided detection; convolutional neural networks; Feature extraction; Female; Humans; Image edge detection; Image Interpretation, Computer-Assisted - methods; Imaging, Three-Dimensional - methods; Lesions; Neural networks; Neural Networks, Computer; Reviewing; Tumors; Ultrasonic imaging; Ultrasonography, Mammary - methods; Ultrasound
• ISSN: 0278-0062; 1558-254X; 1558-254X
• DOI: 10.1109/TMI.2018.2860257

Automated whole breast ultrasound (ABUS) has been widely used as a screening modality for examination of breast abnormalities. Reviewing hundreds of slices produced by ABUS, however, is time consuming. Therefore, in this paper, a fast and effective computer-aided detection system based on 3-D convolutional neural networks (CNNs) and prioritized candidate aggregation is proposed to accelerate this reviewing. First, an efficient sliding window method is used to extract volumes of interest (VOIs). Then, each VOI is estimated the tumor probability with a 3-D CNN, and VOIs with higher estimated probability are selected as tumor candidates. Since the candidates may overlap each other, a novel scheme is designed to aggregate the overlapped candidates. During the aggregation, candidates are prioritized based on estimated tumor probability to alleviate over-aggregation issue. The relationship between the sizes of VOI and target tumor is optimally exploited to effectively perform each stage of our detection algorithm. On evaluation with a test set of 171 tumors, our method achieved sensitivities of 95% (162/171), 90% (154/171), 85% (145/171), and 80% (137/171) with 14.03, 6.92, 4.91, and 3.62 false positives per patient (with six passes), respectively. In summary, our method is more general and much faster than preliminary works and demonstrates promising results.