Efficient Chest X-ray Representation Learning via Semantic-Partitioned Contrastive Learning
This method addresses the problem of inefficient and suboptimal self-supervised learning for medical imaging, specifically Chest X-ray analysis, by providing a streamlined and computationally efficient pre-training framework for researchers and practitioners.
This paper introduces Semantic-Partitioned Contrastive Learning (S-PCL) for Chest X-ray (CXR) representation learning, which partitions patch tokens from a single CXR into two semantic subsets and maximizes agreement between them. S-PCL achieves competitive performance on large-scale CXR benchmarks with the lowest GFLOPs and superior accuracy compared to existing self-supervised learning methods.
Self-supervised learning (SSL) has emerged as a powerful paradigm for Chest X-ray (CXR) analysis under limited annotations. Yet, existing SSL strategies remain suboptimal for medical imaging. Masked image modeling allocates substantial computation to reconstructing high-frequency background details with limited diagnostic value. Contrastive learning, on the other hand, often depends on aggressive augmentations that risk altering clinically meaningful structures. We introduce Semantic-Partitioned Contrastive Learning (S-PCL), an efficient pre-training framework tailored for CXR representation learning. Instead of reconstructing pixels or relying on heavy augmentations, S-PCL randomly partitions patch tokens from a single CXR into two non-overlapping semantic subsets. Each subset provides a complementary but incomplete view. The encoder must maximize agreement between these partitions, implicitly inferring global anatomical layout and local pathological cues from partial evidence. This semantic partitioning forms an internal bottleneck that enforces long-range dependency modeling and structural coherence. S-PCL eliminates the need for hand-crafted augmentations, auxiliary decoders, and momentum encoders. The resulting architecture is streamlined, computationally efficient, and easy to scale. Extensive experiments on large-scale CXR benchmarks, including ChestX-ray14, CheXpert, RSNA Pneumonia and SIIM-ACR Pneumothorax, show that S-PCL achieves competitive performance while attaining the lowest GFLOPs and superior accuracy among existing SSL approaches.