{"ok":true,"nota":{"id":"69b8b4f0883f5971","slug":"una-version-liviana-de-totalsegmentator-analiza-organos-abdominales-en-69b8b4","titulo":"Una versión liviana de TotalSegmentator analiza órganos abdominales en computadoras sin placa de video","resumen":"Investigadores crearon una versión cuantizada de un software de segmentación de órganos que corre solo en procesador, sin GPU ni Python. Compararon su precisión con la versión original en quince órganos abdominales y midieron el tiempo de ejecución.","fuente":"medrxiv","fuenteNombre":"medRxiv · preprints","color":"#1f7a4d","autor":"Lee, J. H.","url":"https://www.medrxiv.org/content/10.64898/2026.10.23.26366189v1?rss=1","imagen":"/hoy/portada/69b8b4f0883f5971","tema":"tecnologia","subtemas":["inteligencia artificial","imágenes médicas","tomografía","segmentación de órganos","computación sin gpu"],"entidades":["TotalSegmentator","TS-Portable"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-24T00:00:00.000Z","indexTs":"2026-10-24T16:15:25.143Z","hash":"75dc84f71f2f647aaaed315a5698121c19d77156a29a7f71f068336c8c0813ac","tsa":{"time":"Oct 24 16:15:48 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":1,"likes":0,"clicks":0,"dwell":0},"tipo":"normal","registro":"hallazgo","porQueImporta":"Hasta ahora, este tipo de análisis de tomografías necesitaba placas de video caras, que muchos hospitales chicos no tienen. Según el trabajo, la versión liviana logra resultados comparables con la original en quince órganos y se puede correr en computadoras comunes. Eso abre la puerta a que clínicas medianas midan el tamaño del bazo o del hígado sin depender de servidores costosos. Lo que todavía no sabemos es cuánto tarda en un equipo real de un hospital del interior.","quienFirma":"Institución no identificada en el extracto","confianza":"preprint","consulta":null},"sello":{"hash":"75dc84f71f2f647aaaed315a5698121c19d77156a29a7f71f068336c8c0813ac","sello":"9384de872ed7f947e6c530b18215df57dc4fc74ec895a408dcd4cd41320aa1ea","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6580917,"aleatorio":"a7ae54c0fcfc9c8a83fe34d0f9320d7528705afd5812276babb4293af5018488","tiempo":"2026-10-24T16:15:30.000Z"},"nist":{"cadena":2,"pulso":1997652,"salida":"9FC650564FC506D017D213281A32AA6072901F0F4F8883A3D1F9DA96496268E453F30EEB00C0821C4D971088ECA97156340102106DF3CD979C769CA0CDF67C37","tiempo":"2026-10-24T16:15:00.000Z"},"noAntes":"2026-10-24T16:15:30.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 24 16:15:48 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"Quantized TotalSegmentator for Fast Abdominal Organ Segmentation on CPUs","descripcion":"BACKGROUND. TotalSegmentator is designed for a graphics processing unit (GPU), runs slowly on a central processing unit (CPU), and depends on Python, limiting CPU-only clinical deployment. OBJECTIVE. The purpose of this study was to evaluate whether TS-Portable, a self-contained CPU executable running 8-bit integer (INT8)-quantized TotalSegmentator models, is noninferior to the reference implementation across 15 abdominal organs in an external multicenter cohort, quantify CPU-only runtime, and demonstrate spleen volumetry on a picture archiving and communication system (PACS) reading station. METHODS. This retrospective study compared TS-Portable with the reference Python implementation on 1","pubDate":"2026-10-24","url":"https://www.medrxiv.org/content/10.64898/2026.10.23.26366189v1?rss=1"},"indexado":"2026-10-24T16:15:25.143Z"}}