Domain-Specific Batch Normalization for Unsupervised Domain Adaptation

IEEE Trans. Med. Imaging

Dou

et al. 2020

209

154

Automated prostate segmentation in MRI is highly demanded for computer-assisted diagnosis. Recently, a variety of deep learning methods have achieved remarkable progress in this task, usually relying on large amounts of training data. Due to the nature of scarcity for medical images, it is important to effectively aggregate data from multiple sites for robust model training, to alleviate the insufficiency of single-site samples. However, the prostate MRIs from different sites present heterogeneity due to the differences in scanners and imaging protocols, raising challenges for effective ways of aggregating multi-site data for network training. In this paper, we propose a novel multisite network (MS-Net) for improving prostate segmentation by learning robust representations, leveraging multiple sources of data. To compensate for the inter-site heterogeneity of different MRI datasets, we develop Domain-Specific Batch Normalization layers in the network backbone, enabling the network to estimate statistics and perform feature normalization for each site separately. Considering the difficulty of capturing the shared knowledge from multiple datasets, a novel learning paradigm, i.e., Multi-site-guided Knowledge Transfer, is proposed to enhance the kernels to extract more generic representations from multi-site data. Extensive experiments on three heterogeneous prostate MRI datasets demonstrate that our MS-Net improves the performance across all datasets consistently, and outperforms state-of-the-art methods for multi-site learning.

Section: Related Work a Multi-site Learningmentioning

confidence: 84%

MS-Net: Multi-Site Network for Improving Prostate Segmentation With Heterogeneous MRI Data

IEEE Trans. Med. Imaging

Dou

et al. 2020

209

154

“…As the performance of DA methods is tightly linked to the network architectures, some works begin to design domainspecialized architectures that process the source and target data separately. Chang et al present domain-specific batch normalization (DSBN) [54] to learn domain-specific information for each domain separately. Later on, Carlucci et al [55] introduce novel domain alignment layers (DAlayers), which automatically learn the degree of good alignment at different levels of the network.…”

Section: Domain-specialized Architecture Based Methodsmentioning

confidence: 99%

Domain Conditioned Adaptation Network

Lin

et al. 2020

AAAI

Tremendous research efforts have been made to thrive deep domain adaptation (DA) by seeking domain-invariant features. Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while integrating a totally shared convolutional architecture for source and target. However, we argue that such strongly-shared convolutional layers might be harmful for domain-specific feature learning when source and target data distribution differs to a large extent. In this paper, we relax a shared-convnets assumption made by previous DA methods and propose a Domain Conditioned Adaptation Network (DCAN), which aims to excite distinct convolutional channels with a domain conditioned channel attention mechanism. As a result, the critical low-level domain-dependent knowledge could be explored appropriately. As far as we know, this is the first work to explore the domain-wise convolutional channel activation for deep DA networks. Moreover, to effectively align high-level feature distributions across two domains, we further deploy domain conditioned feature correction blocks after task-specific layers, which will explicitly correct the domain discrepancy. Extensive experiments on three cross-domain benchmarks demonstrate the proposed approach outperforms existing methods by a large margin, especially on very tough cross-domain learning tasks.

“…During testing phase, the estimated values cannot accurately represent the testing data statistics in each site and hence will lead to performance degradation. In this paper, we employ the domainspecific batch normalization (DSBN) method [9], [33], [34] by assigning an individual BN layer for each site independently to explicitly tackle the statistic discrepancy. As shown in Fig.…”

Section: ) Separate Batch Normalization At Data Heterogeneitymentioning

confidence: 99%

Contrastive Cross-Site Learning With Redesigned Net for COVID-19 CT Classification

Wang

IEEE J. Biomed. Health Inform.

Dou

2020

170

142

The pandemic of coronavirus disease 2019 (COVID-19) has lead to a global public health crisis spreading hundreds of countries. With the continuous growth of new infections, developing automated tools for COVID-19 identification with CT image is highly desired to assist the clinical diagnosis and reduce the tedious workload of image interpretation. To enlarge the datasets for developing machine learning methods, it is essentially helpful to aggregate the cases from different medical systems for learning robust and generalizable models. This paper proposes a novel joint learning framework to perform accurate COVID-19 identification by effectively learning with heterogeneous datasets with distribution discrepancy. We build a powerful backbone by redesigning the recently proposed COVID-Net in aspects of network architecture and learning strategy to improve the prediction accuracy and learning efficiency. On top of our improved backbone, we further explicitly tackle the cross-site domain shift by conducting separate feature normalization in latent space. Moreover, we propose to use a contrastive training objective to enhance the domain invariance of semantic embeddings for boosting the classification performance on each dataset. We develop and evaluate our method with two public large-scale COVID-19 diagnosis datasets made up of CT images. Extensive experiments show that our approach consistently improves the performanceson both datasets, outperforming the original COVID-Net trained on each dataset by 12.16% and 14.23% in AUC respectively, also exceeding existing state-of-the-art multi-site learning methods.