ANT-UNet: Accurate and Noise-Tolerant Segmentation for Pathology Image Processing

Chen, Yufei1; Zhang, Qinming1; Li, Tingtao2; Yu, Hao2; Tian, Mei1; Zhuo, Cheng1

10.1109/BIOCAS.2019.8919150

2019

2163-4025

1550-4840

978-1-5090-0618-2

2019 IEEE Biomedical Circuits and Systems Conference, BioCAS 2019

18

2

1-4

17-19 Oct. 2019

Nara, Japan

345 E 47TH ST, NEW YORK, NY 10017 USA

Institute of Electrical and Electronics Engineers Inc.

Pathology image segmentation is an essential step in early detection and diagnosis for various diseases. Due to its complex nature, precise segmentation is not a trivial task. Recently, deep learning has been proved as an effective option for pathology image processing. However, its efficiency is highly restricted by the inconsistent annotation quality. In this paper, we propose an accurate and noise-Tolerant segmentation approach to overcome the aforementioned issues, which consists of a pre-processing module for data augmentation, a new neural network architecture, ANT-UNet, and a FCCRF inference module. Experimental results demonstrate that, even on a noisy dataset, the proposed approach can achieve more accurate segmentation with 4-23% accuracy improvement than other commonly used segmentation methods. Moreover, the proposed architecture is hardware-friendly and can be incorporated with a GPU acceleration flow to reach 24-128× speed-up.
© 2019 IEEE.

Deep learning neural networks biomedical image segmentation light-weight network

其他

英语

EI ; CPCI-S ; SCI

Zhejiang Provincial Innovation Team Project[2020R01001]

Computer Science ; Engineering

Computer Science, Information Systems ; Engineering, Biomedical ; Engineering, Electrical & Electronic

WOS:000521751500119

20195307946583

Data handling ; Deep learning ; Diagnosis ; Image segmentation ; Network architecture ; Pathology

Medicine and Pharmacology:461.6 ; Data Processing and Image Processing:723.2

EV Compendex

1.Zhejiang University, Hangzhou; 310027, China
2.Southern University of Science and Technology, No. 1088 Xueyuan Avenue, Shenzhen, Guangdong; 518055, China

Chen, Yufei,Zhang, Qinming,Li, Tingtao,et al. ANT-UNet: Accurate and Noise-Tolerant Segmentation for Pathology Image Processing[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:Institute of Electrical and Electronics Engineers Inc.,2019:1-4.