{"ID":2884948,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.04955","arxiv_id":"2508.04955","title":"AdvDINO: Domain-Adversarial Self-Supervised Representation Learning for Spatial Proteomics","abstract":"Self-supervised learning (SSL) has emerged as a powerful approach for learning visual representations without manual annotations. However, the robustness of standard SSL methods to domain shift -- systematic differences across data sources -- remains uncertain, posing an especially critical challenge in biomedical imaging where batch effects can obscure true biological signals. We present AdvDINO, a domain-adversarial SSL framework that integrates a gradient reversal layer into the DINOv2 architecture to promote domain-invariant feature learning. Applied to a real-world cohort of six-channel multiplex immunofluorescence (mIF) whole slide images from lung cancer patients, AdvDINO mitigates slide-specific biases to learn more robust and biologically meaningful representations than non-adversarial baselines. Across more than 5.46 million mIF image tiles, the model uncovers phenotype clusters with differing proteomic profiles and prognostic significance, and enables strong survival prediction performance via attention-based multiple instance learning. The improved robustness also extends to a breast cancer cohort. While demonstrated on mIF data, AdvDINO is broadly applicable to other medical imaging domains, where domain shift is a common challenge.","short_abstract":"Self-supervised learning (SSL) has emerged as a powerful approach for learning visual representations without manual annotations. However, the robustness of standard SSL methods to domain shift -- systematic differences across data sources -- remains uncertain, posing an especially critical challenge in biomedical imag...","url_abs":"https://arxiv.org/abs/2508.04955","url_pdf":"https://arxiv.org/pdf/2508.04955v2","authors":"[\"Stella Su\",\"Marc Harary\",\"Scott J. Rodig\",\"William Lotter\"]","published":"2025-08-07T00:51:54Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false}