# Pixel-level Counterfactual Contrastive Learning for Medical Image Segmentation

Source: [Pixel-level Counterfactual Contrastive Learning for Medical Image Segmentation](<https://www.sota2.com/research/paper/69bb82ee0636e5bf4afc18c6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-20T05:00:04.947Z

Authors: Marceau Lafargue-Hauret, Raghav Mehta, Fabio De Sousa Ribeiro, M\\'elanie Roschewitz, Ben Glocker

Published: 2026-03-17T20:07:14.000Z

## Abstract

Image segmentation relies on large annotated datasets, which are expensive and slow to produce. Silver-standard (AI-generated) labels are easier to obtain, but they risk introducing bias. Self-supervised learning, needing only images, has become key for pre-training. Recent work combining contrastive learning with counterfactual generation improves representation learning for classification but does not readily extend to pixel-level tasks. We propose a pipeline combining counterfactual generation with dense contrastive learning via Dual-View (DVD-CL) and Multi-View (MVD-CL) methods, along with supervised variants that utilize available silver-standard annotations. A new visualisation algorithm, the Color-coded High Resolution Overlay map (CHRO-map) is also introduced. Experiments show annotation-free DVD-CL outperforms other dense contrastive learning methods, while supervised variants using silver-standard labels outperform training on the silver-standard labeled data directly, achieving $\\sim$94% DSC on challenging data. These results highlight that pixel-level contrastive learning, enhanced by counterfactuals and silver-standard annotations, improves robustness to acquisition and pathological variations.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Lung Segmentation on PadChest (five-fold cross-validation)](<https://www.sota2.com/research/sota/lung-segmentation-on-padchest-five-fold-cross-validation.md>): Lung Segmentation; PadChest (five-fold cross-validation); DSC (%): 93.93.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.17110>)

[PDF](<https://arxiv.org/pdf/2603.17110.pdf>)