{"ok":true,"nota":{"id":"991867fa51c203ee","slug":"una-ia-lee-resonancias-de-columna-y-clasifica-el-desgaste-de-los-disco-991867","titulo":"Una IA lee resonancias de columna y clasifica el desgaste de los discos casi como un especialista","resumen":"Desarrollaron un sistema que analiza resonancias magnéticas de columna lumbar y asigna la gravedad de cinco problemas degenerativos en cinco niveles. Lo probaron con estudios de varios hospitales y con datos externos, obteniendo resultados comparables a los de lectores humanos.","fuente":"medrxiv","fuenteNombre":"medRxiv · preprints","color":"#1f7a4d","autor":"Geng, S., Miao, Q., Qin, Q., Guo, H., Wang, X.","url":"https://www.medrxiv.org/content/10.64898/2026.10.20.26366005v1?rss=1","imagen":"/hoy/portada/991867fa51c203ee","tema":"ciencia","subtemas":["inteligencia artificial","resonancia magnética","columna lumbar","diagnóstico por imágenes","radiología"],"entidades":["RSNA","medRxiv"],"formato":"dato","entretenimiento":false,"pubTs":"2026-10-22T00:00:00.000Z","indexTs":"2026-10-22T22:15:09.403Z","hash":"ab78b0d992e2476152c3076071a69bd3452e6921fb53e1663d8f6b9261b79d1d","tsa":{"time":"Oct 22 22:15:54 2026 GMT","provider":"freetsa.org","sobre":"sello"},"stats":{"views":0,"likes":0,"clicks":0,"dwell":0},"tipo":"normal","registro":"hallazgo","porQueImporta":"Leer una resonancia de columna implica unas 25 valoraciones que toman tiempo y que pueden variar mucho entre un médico y otro. Un sistema que las haga de forma consistente podría acortar la espera para el diagnóstico y reducir las diferencias según quién mire la imagen. Eso importa a cualquiera que tenga dolor de espalda crónico y haya recibido informes contradictorios. Todavía falta comprobar que funcione con equipos y pacientes de hospitales argentinos, porque los datos usados vienen de sistemas y poblaciones de otros países.","quienFirma":"Universidad de Wisconsin (investigación sobre resonancia lumbar, datos RSNA 2024)","confianza":"preprint","consulta":null},"sello":{"hash":"ab78b0d992e2476152c3076071a69bd3452e6921fb53e1663d8f6b9261b79d1d","sello":"e70fafd52e5a56b06e5cfcb006ed58b5261bea60b5734be001e4686bd38575df","beacon":{"drand":{"cadena":"8990e7a9aaed2ffed73dbd7092123d6f289930540d7651336225dc172e51b2ce","ronda":6575877,"aleatorio":"8f37ac72f463d512f17e7eb8a85fbb051e22a02b20832cc61f9e99cd899bcc20","tiempo":"2026-10-22T22:15:30.000Z"},"nist":{"cadena":2,"pulso":1995138,"salida":"18500D4D946F3E5BEBC75649FB9B2988974DA4AC1B8418F823282A208CE8DD90C1D97B1374796A643771A12D02A91E9E9CE7C7FA3DCC7A707FC3EE1B862BF5F9","tiempo":"2026-10-22T22:15:00.000Z"},"noAntes":"2026-10-22T22:15:30.000Z"},"verificacion":{"drand":true,"nist":true},"tsa":{"time":"Oct 22 22:15:54 2026 GMT","provider":"freetsa.org","sobre":"sello"},"original":{"titulo":"Ordinal Multi-Instance Learning for Automated Multi-Task Grading of Lumbar Degenerative Conditions on Sagittal MRI, with External Validation","descripcion":"Purpose: Lumbar spine MRI interpretation requires 25 structured severity judgments per examination (five degenerative conditions at five disc levels, each on a three-level ordinal scale), a time-consuming task with substantial inter-reader variability. We developed and externally validated a model that automates this complete scheme. Materials and Methods: A full-sequence multi-instance learning (MIL) model (ResNet34 backbone, bidirectional GRU, attention pooling over 24 uniformly sampled sagittal T2-weighted slices) with 25 cumulative-logit ordinal heads was trained on 1,204 examinations from the multi-institutional RSNA 2024 LumbarDISC dataset and internally validated on 213 held-out exami","pubDate":"2026-10-22","url":"https://www.medrxiv.org/content/10.64898/2026.10.20.26366005v1?rss=1"},"indexado":"2026-10-22T22:15:09.403Z"}}