TY - JOUR
T1 - Consolidated domain adaptive detection and localization framework for cross-device colonoscopic images
AU - Liu, Xinyu
AU - Guo, Xiaoqing
AU - Liu, Yajie
AU - Yuan, Yixuan
N1 - Funding Information:
This work was supported by Hong Kong Research Grants Council (RGC) Early Career Scheme grant 21207420 (CityU 9048179), Hong Kong RGC Collaborative Research Fund grant C4063-18G (CityU 8739029), and Shenzhen-Hong Kong Innovation Circle Category D Project SGDX2019081623300177 (CityU 9240008).
Publisher Copyright:
© 2021 Elsevier B.V. All rights reserved.
PY - 2021/7
Y1 - 2021/7
N2 - Automatic polyp detection has been proven to be crucial in improving the diagnosis accuracy and reducing colorectal cancer mortality during the precancerous stage. However, the performance of deep neural networks may degrade severely when being deployed to polyp data in a distinct domain. This domain distinction can be caused by different scanners, hospitals, or imaging protocols. In this paper, we propose a consolidated domain adaptive detection and localization framework to bridge the domain gap between different colonosopic datasets effectively, consisting of two parts: the pixel-level adaptation and the hierarchical feature-level adaptation. For the pixel-level adaptation part, we propose a Gaussian Fourier Domain Adaptation (GFDA) method to sample the matched source and target image pairs from Gaussian distributions then unify their styles via the low-level spectrum replacement, which can reduce the domain discrepancy of the cross-device polyp datasets in appearance level without distorting their contents. The hierarchical feature-level adaptation part comprising a Hierarchical Attentive Adaptation (HAA) module to minimize the domain discrepancy in high-level semantics and an Iconic Concentrative Adaptation (ICA) module to perform reliable instance alignment. These two modules are regularized by a Generalized Consistency Regularizer (GCR) for maintaining the consistency of their domain predictions. We further extend our framework to the polyp localization task and present a Centre Besiegement (CB) loss for better location optimization. Experimental results show that our framework outperforms other domain adaptation detectors by a large margin in the detection task meanwhile achieves the state-of-the-art recall rate of 87.5% in the localization task. The source code is available at https://github.com/CityU-AIM-Group/ConsolidatedPolypDA.
AB - Automatic polyp detection has been proven to be crucial in improving the diagnosis accuracy and reducing colorectal cancer mortality during the precancerous stage. However, the performance of deep neural networks may degrade severely when being deployed to polyp data in a distinct domain. This domain distinction can be caused by different scanners, hospitals, or imaging protocols. In this paper, we propose a consolidated domain adaptive detection and localization framework to bridge the domain gap between different colonosopic datasets effectively, consisting of two parts: the pixel-level adaptation and the hierarchical feature-level adaptation. For the pixel-level adaptation part, we propose a Gaussian Fourier Domain Adaptation (GFDA) method to sample the matched source and target image pairs from Gaussian distributions then unify their styles via the low-level spectrum replacement, which can reduce the domain discrepancy of the cross-device polyp datasets in appearance level without distorting their contents. The hierarchical feature-level adaptation part comprising a Hierarchical Attentive Adaptation (HAA) module to minimize the domain discrepancy in high-level semantics and an Iconic Concentrative Adaptation (ICA) module to perform reliable instance alignment. These two modules are regularized by a Generalized Consistency Regularizer (GCR) for maintaining the consistency of their domain predictions. We further extend our framework to the polyp localization task and present a Centre Besiegement (CB) loss for better location optimization. Experimental results show that our framework outperforms other domain adaptation detectors by a large margin in the detection task meanwhile achieves the state-of-the-art recall rate of 87.5% in the localization task. The source code is available at https://github.com/CityU-AIM-Group/ConsolidatedPolypDA.
KW - Adversarial training
KW - Colonoscopic polyp detection
KW - Domain adaptation
KW - Style transfer
UR - http://www.scopus.com/inward/record.url?scp=85104691752&partnerID=8YFLogxK
U2 - 10.1016/j.media.2021.102052
DO - 10.1016/j.media.2021.102052
M3 - Journal article
C2 - 33895616
AN - SCOPUS:85104691752
SN - 1361-8415
VL - 71
JO - Medical Image Analysis
JF - Medical Image Analysis
M1 - 102052
ER -