Multi-Source COVID-19 Detection via Variance Risk Extrapolation

2025/06/29 by Runtian Yuan, Yuan, Runtian, Qingqiu Li +11 · 1 citation
Computer Science · Medicine · #COVID-19 Clinical Research Studies #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2506.23208

openalex publication_date 2025/06/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present our solution for the Multi-Source COVID-19 Detection Challenge, which aims to classify chest CT scans into COVID and Non-COVID categories across data collected from four distinct hospitals and medical centers. A major challenge in this task lies in the domain shift caused by variations in imaging protocols, scanners, and patient populations across institutions. To enhance the cross-domain generalization of our model, we incorporate Variance Risk Extrapolation (VREx) into the training process. VREx encourages the model to maintain consistent performance across multiple source domains by explicitly minimizing the variance of empirical risks across environments. This regularization strategy reduces overfitting to center-specific features and promotes learning of domain-invariant representations. We further apply Mixup data augmentation to improve generalization and robustness. Mixup interpolates both the inputs and labels of randomly selected pairs of training samples, encouraging the model to behave linearly between examples and enhancing its resilience to noise and limited data. Our method achieves an average macro F1 score of 0.96 across the four sources on the validation set, demonstrating strong generalization.

Citations

• SAM2CLIP2SAM: Vision Language Model for Segmentation of 3D CT Scans for Covid-19 Detection
• Advancing COVID-19 Detection in 3D CT Scans
• COVID-19 Computer-aided Diagnosis through AI-assisted CT Imaging Analysis: Deploying a Medical AI System
• Domain adaptation, Explainability & Fairness in AI for Medical Image Analysis: Diagnosis of COVID-19 based on 3-D Chest CT-scans
• A Deep Neural Architecture for Harmonizing 3-D Input Data Analysis and Decision Making in Medical Imaging
• Boosting COVID-19 Severity Detection with Infection-aware Contrastive Mixup Classification
• CMC v2: Towards More Accurate COVID-19 Detection with Discriminative Video Priors
• MIA-COV19D: COVID-19 Detection through 3-D Chest CT Image Analysis
• TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation
• Deep Transparent Prediction through Latent Representation Analysis
• Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup
• Adaptive Risk Minimization: Learning to Adapt to Domain Shift
• ResNeSt: Split-Attention Networks
• Out-of-Distribution Generalization via Risk Extrapolation (REx)
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
• RandAugment: Practical automated data augmentation with a reduced search space
• Invariant Risk Minimization
• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
• Unsupervised Data Augmentation for Consistency Training
• mixup: Beyond Empirical Risk Minimization
• Learning Deep Features for Discriminative Localization
• Causal inference using invariant prediction: identification and confidence intervals

Cited by

• Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardization

Related

• Robust Framework for COVID-19 Identification from a Multicenter Dataset of Chest CT Scans
• Multi Source COVID-19 Detection via Kernel-Density-based Slice Sampling
• Intra-model Variability in COVID-19 Classification Using Chest X-ray Images
• High-confidence pseudo-labels for domain adaptation in COVID-19 detection
• FDVTS's Solution for 2nd COV19D Competition on COVID-19 Detection and Severity Analysis