Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis

Abstract

Deep learning based medical image diagnosis has shown great potential in clinical medicine. However, it often suffers two major difficulties in real-world applications: 1) only limited labels are available for model training, due to expensive annotation costs over medical images; 2) labeled images may contain considerable label noise (e.g., mislabeling labels) due to diagnostic difficulties of diseases. To address these, we seek to exploit rich labeled data from relevant domains to help the learning in the target task via {Unsupervised Domain Adaptation} (UDA). Unlike most UDA methods that rely on clean labeled data or assume samples are equally transferable, we innovatively propose a Collaborative Unsupervised Domain Adaptation algorithm, which conducts transferability-aware adaptation and conquers label noise in a collaborative way. We theoretically analyze the generalization performance of the proposed method, and also empirically evaluate it on both medical and general images. Promising experimental results demonstrate the superiority and generalization of the proposed method.

IEEE Transactions on Image Processing

References in corpus (7)

• Unsupervised Domain Adaptation by Backpropagation
• Deep Domain Confusion: Maximizing for Domain Invariance
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• Unsupervised Label Noise Modeling and Loss Correction
• Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
• COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19
• Multi-marginal Wasserstein GAN

Cited by in corpus (12)

• Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
• Self-Attentive Spatial Adaptive Normalization for Cross-Modality Domain Adaptation
• COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19
• Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
• Dense Regression Network for Video Grounding
• Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data
• Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation
• Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only
• Online Adaptive Asymmetric Active Learning with Limited Budgets
• Towards Robust Cross-domain Image Understanding with Unsupervised Noise Removal
• An Empirical Framework for Domain Generalization in Clinical Settings
• Retinal Image Segmentation with a Structure-Texture Demixing Network