RepViT-CXR: A Channel Replication Strategy for Vision Transformers in Chest X-ray Tuberculosis and Pneumonia Classification

2025-09-09

AI Summary

To address the incompatibility between single-channel chest X-ray (CXR) images and standard three-channel Vision Transformer (ViT) architectures pretrained on natural images, this paper proposes RepViT-CXR—a lossless channel replication strategy that maps grayscale CXRs directly to three-channel inputs, enabling seamless transfer of ImageNet-pretrained ViT weights. Unlike heuristic approaches such as pseudo-coloring or zero-padding, RepViT-CXR preserves original intensity distributions without introducing bias, thereby enhancing medical image representation learning. Evaluated on three benchmark datasets—TB-CXR, Shenzhen TB, and pediatric pneumonia—RepViT-CXR achieves state-of-the-art accuracy of 99.9% (AUC 99.9%), 91.1%, and 99.0% (AUC 99.0%), respectively. This work establishes a novel, efficient paradigm for lightweight ViT adaptation to single-channel medical imaging, demonstrating superior generalization and clinical applicability.

Technology Category

• Computer Vision: Representation Learning for Vision
• Machine Learning: Representation Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Security and Privacy: Privacy-enhancing technologies

Abstract

Chest X-ray (CXR) imaging remains one of the most widely used diagnostic tools for detecting pulmonary diseases such as tuberculosis (TB) and pneumonia. Recent advances in deep learning, particularly Vision Transformers (ViTs), have shown strong potential for automated medical image analysis. However, most ViT architectures are pretrained on natural images and require three-channel inputs, while CXR scans are inherently grayscale. To address this gap, we propose RepViT-CXR, a channel replication strategy that adapts single-channel CXR images into a ViT-compatible format without introducing additional information loss. We evaluate RepViT-CXR on three benchmark datasets. On the TB-CXR dataset,our method achieved an accuracy of 99.9% and an AUC of 99.9%, surpassing prior state-of-the-art methods such as Topo-CXR (99.3% accuracy, 99.8% AUC). For the Pediatric Pneumonia dataset, RepViT-CXR obtained 99.0% accuracy, with 99.2% recall, 99.3% precision, and an AUC of 99.0%, outperforming strong baselines including DCNN and VGG16. On the Shenzhen TB dataset, our approach achieved 91.1% accuracy and an AUC of 91.2%, marking a performance improvement over previously reported CNN-based methods. These results demonstrate that a simple yet effective channel replication strategy allows ViTs to fully leverage their representational power on grayscale medical imaging tasks. RepViT-CXR establishes a new state of the art for TB and pneumonia detection from chest X-rays, showing strong potential for deployment in real-world clinical screening systems.

Problem

• Adapting single-channel CXR images for ViT input
• Improving tuberculosis and pneumonia classification accuracy
• Addressing information loss in grayscale medical imaging

Innovation

• Channel replication adapts single-channel CXR for ViTs
• Converts grayscale images to three-channel ViT format
• Maintains original information without data loss