TY - JOUR
T1 - Semantic segmentation of breast ultrasound image with fuzzy deep learning network and breast anatomy constraints
AU - Huang, Kuan
AU - Zhang, Yingtao
AU - Cheng, H. D.
AU - Xing, Ping
AU - Zhang, Boyu
N1 - Publisher Copyright:
© 2021 Elsevier B.V.
PY - 2021/8/25
Y1 - 2021/8/25
N2 - Breast cancer is one of the most serious disease affecting women's health. Due to low cost, portable, no radiation, and high efficiency, breast ultrasound (BUS) imaging is the most popular approach for diagnosing early breast cancer. However, ultrasound images are low resolution and poor quality. Thus, developing accurate detection system is a challenging task. In this paper, we propose a fully automatic segmentation algorithm consisting of two parts: fuzzy fully convolutional network and accurately fine-tuning post-processing based on breast anatomy constraints. In the first part, the image is pre-processed by contrast enhancement, and wavelet features are employed for image augmentation. A fuzzy membership function transforms the augmented BUS images into the fuzzy domain. The features from convolutional layers are processed using fuzzy logic as well. The conditional random fields (CRFs) post-process the segmentation result. The location relation among the breast anatomy layers is utilized to improve the performance. The proposed method is applied to the dataset with 325 BUS images, and achieves state-of-the-art performance compared with that of existing methods with true positive rate 90.33%, false positive rate 9.00%, and intersection over union (IoU) 81.29% on tumor category, and overall intersection over union (mIoU) 80.47% over five categories: fat layer, mammary layer, muscle layer, background, and tumor.
AB - Breast cancer is one of the most serious disease affecting women's health. Due to low cost, portable, no radiation, and high efficiency, breast ultrasound (BUS) imaging is the most popular approach for diagnosing early breast cancer. However, ultrasound images are low resolution and poor quality. Thus, developing accurate detection system is a challenging task. In this paper, we propose a fully automatic segmentation algorithm consisting of two parts: fuzzy fully convolutional network and accurately fine-tuning post-processing based on breast anatomy constraints. In the first part, the image is pre-processed by contrast enhancement, and wavelet features are employed for image augmentation. A fuzzy membership function transforms the augmented BUS images into the fuzzy domain. The features from convolutional layers are processed using fuzzy logic as well. The conditional random fields (CRFs) post-process the segmentation result. The location relation among the breast anatomy layers is utilized to improve the performance. The proposed method is applied to the dataset with 325 BUS images, and achieves state-of-the-art performance compared with that of existing methods with true positive rate 90.33%, false positive rate 9.00%, and intersection over union (IoU) 81.29% on tumor category, and overall intersection over union (mIoU) 80.47% over five categories: fat layer, mammary layer, muscle layer, background, and tumor.
KW - Breast anatomy
KW - Breast ultrasound (BUS) images
KW - Deep convolutional neural network (DCNN)
KW - Fuzzy logic
KW - Semantic segmentation
UR - http://www.scopus.com/inward/record.url?scp=85105028239&partnerID=8YFLogxK
U2 - 10.1016/j.neucom.2021.04.012
DO - 10.1016/j.neucom.2021.04.012
M3 - Article
AN - SCOPUS:85105028239
SN - 0925-2312
VL - 450
SP - 319
EP - 335
JO - Neurocomputing
JF - Neurocomputing
ER -