{"ok":true,"nota":{"id":"d8a1ef376070c954","slug":"un-metodo-con-imagenes-de-biopsia-comun-distingue-tipos-de-celulas-que-d8a1ef","titulo":"Un método con imágenes de biopsia común distingue tipos de células que antes solo se veían con estudios caros","resumen":"Investigadores crearon CellBridge, un sistema que aprende a relacionar fotos comunes de tejido teñido con datos moleculares detallados. Entrenado con millones de células, logra identificar subtipos celulares que las imágenes tradicionales no distinguían.","fuente":"biorxiv","fuenteNombre":"bioRxiv · preprints","color":"#be2628","autor":"Ogut, S., Merchant, A., Vahidi, A., Jeong, D., Birk, S., Boxall, A., Miraki Feriz, A., Sallese, M. R., Chang, Y., Frossa","url":"https://www.biorxiv.org/content/10.64898/2026.10.20.760347v1?rss=1","imagen":"/hoy/portada/d8a1ef376070c954","tema":"salud","subtemas":["patología digital","cáncer","diagnóstico por imágenes","inteligencia artificial","tumores"],"entidades":["CellBridge"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-24T00:00:00.000Z","indexTs":"2026-10-25T10:38:14.778Z","hash":"e4bbc13456c3573b012b997f3f9e7032201fde677314c84190c3a65bf228090d","tsa":{"time":"Oct 25 10:38:56 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":1,"likes":0,"clicks":0,"dwell":0},"tipo":"normal","registro":"hallazgo","porQueImporta":"Hoy, para saber con precisión qué células forman un tumor, hacen falta análisis moleculares que son caros y no siempre están disponibles en el sistema de salud. Si una imagen de rutina alcanza para identificarlas, el diagnóstico podría llegar a más pacientes y más rápido. Por ahora es una herramienta de investigación y falta validarla en la práctica clínica.","quienFirma":"bioRxiv · preprints","confianza":"preprint","consulta":null},"sello":{"hash":"e4bbc13456c3573b012b997f3f9e7032201fde677314c84190c3a65bf228090d","sello":"61d04496f4f2dd63650c5f34fc5cf4422ea17974d53354a66c965e2a3f1db320","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6583123,"aleatorio":"01c23492917c8158ecd02d4ec7474f29dfb1b980670058951d0f80253dd2e82e","tiempo":"2026-10-25T10:38:30.000Z"},"nist":{"cadena":2,"pulso":1998755,"salida":"28775467E3830FECDCFFFCC12B583FF9E2CBEB95CB2305D52513ECFCE30159A86B42E261262E014B6D2C88558EBC490324F16DEE4150CE176C9AF14BC0C34477","tiempo":"2026-10-25T10:38:00.000Z"},"noAntes":"2026-10-25T10:38:30.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 25 10:38:56 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"Fine-Grained and Reliable Cell Classification from Pathology Images","descripcion":"Molecular assays such as spatial transcriptomics facilitate fine-grained identification of cell types for analyzing tumor microenvironments. However, they are expensive to acquire in routine clinical practice compared to hematoxylin and eosin (H&E) images. With molecular guidance, such images can distinguish cell lineages, yet often fail to resolve closely related subtypes. To overcome this, we introduce CellBridge, a multi-modal contrastive learning framework pretrained on 16M cells with paired H&E and spatial profiles, for transferring molecular information into morphological representations. CellBridge further incorporates a Cell-Ontology-aware conformal prediction module that assigns lab","pubDate":"2026-10-24","url":"https://www.biorxiv.org/content/10.64898/2026.10.20.760347v1?rss=1"},"indexado":"2026-10-25T10:38:14.778Z"}}