{"version":"1","article":{"id":"slide-context-ai-pathology-segmentation-canada-2026","slug":"slide-context-ai-pathology-segmentation-canada-2026","language":"en","url":"https://haberpaper.com/en/news/slide-context-ai-pathology-segmentation-canada-2026","api_url":"https://haberpaper.com/api/v1/articles/slide-context-ai-pathology-segmentation-canada-2026?lang=en","title":"Ottawa team reports pathology AI that segments slides with fewer labels","summary":"SlideFiLM feeds whole-slide context into tissue-image tiles to segment kidney and vascular structures. Supplementary tables report results when using just 20% of labeled training data.","category":"business","region":"world","topics":["ai"],"published_at":"2026-10-13T20:11:53+03:00","modified_at":"2026-10-13T20:11:53+03:00","publication_basis":"publication-record","event_period":"2026-10-12","event_period_basis":"event-or-reference-period","sources":[{"name":"npj Imaging, Data-efficient pathology whole-slide image segmentation with slide-level conditioning","url":"https://www.nature.com/articles/s44303-026-00201-7","checkedAt":"2026-10-13","publishedAt":"2026-10-12"}],"translations":[{"language":"tr","url":"https://haberpaper.com/tr/news/slide-context-ai-pathology-segmentation-canada-2026","api_url":"https://haberpaper.com/api/v1/articles/slide-context-ai-pathology-segmentation-canada-2026?lang=tr"},{"language":"en","url":"https://haberpaper.com/en/news/slide-context-ai-pathology-segmentation-canada-2026","api_url":"https://haberpaper.com/api/v1/articles/slide-context-ai-pathology-segmentation-canada-2026?lang=en"},{"language":"ar","url":"https://haberpaper.com/ar/news/slide-context-ai-pathology-segmentation-canada-2026","api_url":"https://haberpaper.com/api/v1/articles/slide-context-ai-pathology-segmentation-canada-2026?lang=ar"},{"language":"fr","url":"https://haberpaper.com/fr/news/slide-context-ai-pathology-segmentation-canada-2026","api_url":"https://haberpaper.com/api/v1/articles/slide-context-ai-pathology-segmentation-canada-2026?lang=fr"},{"language":"es","url":"https://haberpaper.com/es/news/slide-context-ai-pathology-segmentation-canada-2026","api_url":"https://haberpaper.com/api/v1/articles/slide-context-ai-pathology-segmentation-canada-2026?lang=es"}],"data_types":[],"data":null,"data_compilations":[],"data_downloads":[],"content":{"paragraphs":["A study published on 12 October in npj Imaging by University of Ottawa researchers introduces SlideFiLM, a method designed to segment gigapixel pathology slides with fewer pixel-level labels. It passes context from an entire slide into the processing of each image tile through a shared modulation layer. The authors evaluated it on glomeruli in PAS-stained kidney slides and atherosclerotic plaque lesions in mouse aortic-root sections.","In the published supplementary tables, using 20% of labeled training data produced whole-slide Dice scores of 87.19% on the KPIs kidney dataset and 86.48% on the MARA vascular dataset; the compared HookNet scores were 75.36% and 79.52%, respectively. The results are limited to these benchmark datasets and the authors’ training setup; the method is not presented as a diagnostic system validated in clinical workflows or independent hospitals. The journal marks the paper as an accepted early version."],"key_points":[],"sections":[]},"text":"SlideFiLM feeds whole-slide context into tissue-image tiles to segment kidney and vascular structures. Supplementary tables report results when using just 20% of labeled training data.\n\nA study published on 12 October in npj Imaging by University of Ottawa researchers introduces SlideFiLM, a method designed to segment gigapixel pathology slides with fewer pixel-level labels. It passes context from an entire slide into the processing of each image tile through a shared modulation layer. The authors evaluated it on glomeruli in PAS-stained kidney slides and atherosclerotic plaque lesions in mouse aortic-root sections.\n\nIn the published supplementary tables, using 20% of labeled training data produced whole-slide Dice scores of 87.19% on the KPIs kidney dataset and 86.48% on the MARA vascular dataset; the compared HookNet scores were 75.36% and 79.52%, respectively. The results are limited to these benchmark datasets and the authors’ training setup; the method is not presented as a diagnostic system validated in clinical workflows or independent hospitals. The journal marks the paper as an accepted early version.","corrections":[],"editorial_illustration":{"kind":"symbolic-editorial-illustration","documentary":false,"scope":"section","asset_id":"business","url":"https://haberpaper.com/assets/illustrations/business-1536.webp","width":1536,"height":1024,"alt":"Symbolic industrial workshop with machinery, a warehouse and a crane.","language":"en"},"section_illustration":{"kind":"symbolic-editorial-illustration","documentary":false,"scope":"section","asset_id":"business","url":"https://haberpaper.com/assets/illustrations/business-1536.webp","width":1536,"height":1024,"alt":"Symbolic industrial workshop with machinery, a warehouse and a crane.","language":"en"}}}