{"slug": "organlens-organ-specific-representation-learning-for-ct-foundation-models", "title": "OrganLens: Organ-Specific Representation Learning for CT Foundation Models", "summary": "Researchers introduce OrganLens, a self-supervised method for organ-specific representation learning from CT scans, producing 11 organ-specific representations from a shared encoder without external segmentation masks. In evaluations, heart representations raised CT-RATE cardiomegaly AUROC from 0.910 to 0.953, and lung representations improved the Harrell C-index for NLST lung-cancer mortality by 14.2%. The method offers a scalable framework for organ-specific disease study across cohorts and clinical endpoints.", "body_md": "arXiv:2607.25164v1 Announce Type: new\nAbstract: A CT examination captures multiple organs, but many biomedical questions concern abnormalities, prognosis, or longitudinal change in a specific organ. These questions require a separate representation for each organ within the same CT volume. Existing CT foundation models commonly produce a single volume-level representation, while recent anatomy-aware methods either encode pre-separated organ volumes or explicitly disentangle images into organ token groups. The former may remove clinically relevant surrounding context, while the latter does not condition a shared encoder on a selected organ before its features are formed. We introduce OrganLens for organ-specific representation learning through self-supervision. An organ identity conditions a shared CT encoder, while organ-specific distillation and anatomy-mask supervision shape features for anatomy-weighted pooling into organ-specific representations. At inference, the shared model produces 11 organ-specific representations without external segmentation masks. We evaluate OrganLens on CT-RATE, RAD-ChestCT, INSPECT, and NLST across diverse acquisitions and downstream evaluations. Relative to CT-pretrained DINOv2, heart representations raise CT-RATE cardiomegaly AUROC from 0.910 to 0.953, while lung representations improve the Harrell C-index for NLST lung-cancer mortality by 14.2\\%. The global representation reaches INSPECT Recall@10 of 33.09\\% and 32.04\\% for text-to-image and image-to-text retrieval, respectively. Across organ-related tasks, anatomically matched representations provide stronger task-relevant signal, while the global representation retains broad utility. OrganLens offers a scalable approach to organ-specific CT representation learning with a shared encoder. More broadly, it provides the medical research community with a reusable framework for studying organ-specific disease across cohorts and clinical endpoints.", "url": "https://wpnews.pro/news/organlens-organ-specific-representation-learning-for-ct-foundation-models", "canonical_source": "https://arxiv.org/abs/2607.25164", "published_at": "2026-07-29 04:00:00+00:00", "updated_at": "2026-07-29 04:22:36.259612+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "computer-vision"], "entities": ["OrganLens", "CT-RATE", "RAD-ChestCT", "INSPECT", "NLST", "DINOv2"], "alternates": {"html": "https://wpnews.pro/news/organlens-organ-specific-representation-learning-for-ct-foundation-models", "markdown": "https://wpnews.pro/news/organlens-organ-specific-representation-learning-for-ct-foundation-models.md", "text": "https://wpnews.pro/news/organlens-organ-specific-representation-learning-for-ct-foundation-models.txt", "jsonld": "https://wpnews.pro/news/organlens-organ-specific-representation-learning-for-ct-foundation-models.jsonld"}}