Direct prediction of Homologous Recombination Deficiency from routine histology in ten different tumor types with attention-based Multiple Instance Learning: a development and validation study.
Chiara Maria Lavinia LoefflerOmar S M El NahhasHannah Sophie MutiTobias SeibelDidem CifciMarko van TreeckMarco GustavZunamys Itzell CarreroNadine Therese GaisaKjong-van LehmannAlexandra LearyPier SelenicaJorge Sergio Reis-FilhoNadina Ortiz BruechleJakob Nikolas KatherPublished in: medRxiv : the preprint server for health sciences (2023)
In this study, we show that HRD is directly predictable from H&E slides using attMIL within and across ten different tumor types.