SpurCon: Weighted Supervised Contrastive Learning for Mitigating Spurious Cues in Medical Imaging

• URL: http://arxiv.org/abs/2608.17598v1
• Date: Tue, 18 Aug 2026 10:05:47 GMT
• Title: SpurCon: Weighted Supervised Contrastive Learning for Mitigating Spurious Cues in Medical Imaging
• Abstract summary: Models may exploit spurious correlations in medical imaging, where devices or treatment artifacts often co-occur with pathology.<n>We propose SpurCon, a lightweight framework based on a novel supervised contrastive loss formulation.<n>Our approach delivers the best spurious-mitigation performance, balancing well worst-group and overall accuracy on multiple datasets.
• Score: 7.308896004974025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the rapid progress of deep neural networks in visual recognition, their adoption in high-risk medical applications remains limited due to reliability and robustness concerns. Models may exploit spurious correlations, particularly in medical imaging, where devices or treatment artifacts often co-occur with pathology. In small or imbalanced datasets, such cues further reduce worst-group performance and undermine clinical trust. To solve these issues, two major challenges should be addressed: identifying dataset-specific spurious cues, which typically require domain knowledge, and mitigating reliance on them. To tackle both, we propose SpurCon, a lightweight framework based on a novel supervised contrastive loss formulation that leverages available metadata and predicted spurious labels to enhance robustness. We introduce a fast few-shot procedure, without network training, to estimate spurious labels using a small number of expert-annotated samples. We then propose a weighted supervised contrastive objective, WtSupCon, that reshapes the representation geometry by assigning sample-specific weights that depend on the [pathology, spurious, metadata] combination. For example, the highest weight is assigned to samples that differ only in their spurious label. This yields highly similar representations for images with the same metadata and pathology, differing only in the predicted spurious label. Our method operates on pretrained image encoders (such as BiomedCLIP) and trains only a lightweight projection head. We evaluate SpurCon on a synthetic setting and on Waterbirds, CheXpert, a chest X-ray classification dataset, and ISIC 2020, a skin cancer classification dataset. Our approach delivers the best spurious-mitigation performance, balancing well worst-group and overall accuracy on multiple datasets.

Related papers

• MR-CLIP: Efficient Metadata-Guided Learning of MRI Contrast Representations [0.8430273876996414]
  We propose MR-CLIP, a multimodal contrastive learning framework that aligns MR images with their DICOM metadata to learn contrast-aware representations.<n>We demonstrate its effectiveness in cross-modal retrieval and contrast classification, highlighting its scalability and potential for further clinical applications.
  arXiv  Detail & Related papers  (2025-06-23T13:27:31Z)
• How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers? [49.35105290167996]
  Pruning has emerged as a powerful technique for compressing deep neural networks, reducing memory usage and inference time without significantly affecting overall performance. This work represents a first step toward understanding the impact of pruning on model behavior in deep long-tailed, multi-label medical image classification.
  arXiv  Detail & Related papers  (2023-08-17T20:40:30Z)
• Weakly-supervised positional contrastive learning: application to cirrhosis classification [45.63061034568991]
  Large medical imaging datasets can be cheaply annotated with low-confidence, weak labels. Access to high-confidence labels, such as histology-based diagnoses, is rare and costly. We propose an efficient weakly-supervised positional (WSP) contrastive learning strategy.
  arXiv  Detail & Related papers  (2023-07-10T15:02:13Z)
• SPLAL: Similarity-based pseudo-labeling with alignment loss for semi-supervised medical image classification [11.435826510575879]
  Semi-supervised learning (SSL) methods can mitigate challenges by leveraging both labeled and unlabeled data. SSL methods for medical image classification need to address two key challenges: (1) estimating reliable pseudo-labels for the images in the unlabeled dataset and (2) reducing biases caused by class imbalance. In this paper, we propose a novel SSL approach, SPLAL, that effectively addresses these challenges.
  arXiv  Detail & Related papers  (2023-07-10T14:53:24Z)
• An End-to-End Framework For Universal Lesion Detection With Missing Annotations [24.902835211573628]
  We present a novel end-to-end framework for mining unlabeled lesions while simultaneously training the detector. Our framework follows the teacher-student paradigm. High-confidence predictions are combined with partially-labeled ground truth for training the student model.
  arXiv  Detail & Related papers  (2023-03-27T09:16:10Z)
• Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective [51.70661197256033]
  We propose ARCO, a semi-supervised contrastive learning framework with stratified group theory for medical image segmentation. We first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks. We experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings.
  arXiv  Detail & Related papers  (2023-02-03T13:50:25Z)
• Self-Supervised Learning as a Means To Reduce the Need for Labeled Data in Medical Image Analysis [64.4093648042484]
  We use a dataset of chest X-ray images with bounding box labels for 13 different classes of anomalies. We show that it is possible to achieve similar performance to a fully supervised model in terms of mean average precision and accuracy with only 60% of the labeled data.
  arXiv  Detail & Related papers  (2022-06-01T09:20:30Z)
• Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation [79.58311369297635]
  We propose a new weakly-supervised lesions transfer framework, which can explore transferable domain-invariant knowledge across different datasets. A Wasserstein quantified transferability framework is developed to highlight widerange transferable contextual dependencies. A novel self-supervised pseudo label generator is designed to equally provide confident pseudo pixel labels for both hard-to-transfer and easy-to-transfer target samples.
  arXiv  Detail & Related papers  (2020-12-08T02:26:03Z)
• Correcting Data Imbalance for Semi-Supervised Covid-19 Detection Using X-ray Chest Images [4.1950566803514935]
  We evaluate the performance of the semi-supervised deep learning architecture known as MixMatch. A new dataset is included among thetested datasets, composed of chest X-ray images of Costa Rican adult patients.
  arXiv  Detail & Related papers  (2020-08-19T15:16:57Z)
• Multi-label Thoracic Disease Image Classification with Cross-Attention Networks [65.37531731899837]
  We propose a novel scheme of Cross-Attention Networks (CAN) for automated thoracic disease classification from chest x-ray images. We also design a new loss function that beyond cross-entropy loss to help cross-attention process and is able to overcome the imbalance between classes and easy-dominated samples within each class.
  arXiv  Detail & Related papers  (2020-07-21T14:37:00Z)
• Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Model [71.80319052891817]
  We present a relation-driven semi-supervised framework for medical image classification. It exploits the unlabeled data by encouraging the prediction consistency of given input under perturbations. Our method outperforms many state-of-the-art semi-supervised learning methods on both single-label and multi-label image classification scenarios.
  arXiv  Detail & Related papers  (2020-05-15T06:57:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.