Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Efficient Chest X-ray Representation Learning via Semantic-Partitioned Contrastive Learning

About

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.

Wangyu Feng, Shawn Young, Lijian Xu• 2026

Related benchmarks

TaskDatasetResultRank
Medical Semantic SegmentationSIIM Pneumothorax
Dice Score65.1
46
Disease ClassificationCheXpert 100% labels
Macro-Averaged AUC89.1
6
Disease ClassificationRSNA Pneu. (100% labels)
Macro-Averaged AUC91.2
6
Disease ClassificationChestX-ray14 100% labels
Macro AUC84.1
5
Disease ClassificationRSNA Pneu. (1% labels)
Macro AUC86.6
5
Disease ClassificationRSNA Pneu. 10% labels
Macro AUC89.2
5
Disease ClassificationCheXpert (10% labels)
Macro AUC88.4
4
Disease ClassificationCheXpert (1% labels)
Macro AUC86.7
4
Disease ClassificationChestX-ray14 (1% labels)
Macro-Averaged AUC78.2
3
Disease ClassificationChestX-ray14 (10% labels)
Macro-Averaged AUC82.1
3
Showing 10 of 10 rows

Other info

Follow for update