3D CSFA-UNet: a unified attention-driven deep learning framework for accurate knee MRI segmentation and osteoarthritis severity classification

Abstract Although several recent multi-task deep learning methods already perform segmentation and classification jointly, many still face limitations in clinical applicability such as restricted multi-scale context modeling, insufficient attention to clinically relevant spatial–channel cues, or hea...

Descrizione completa

Dettagli Bibliografici

Autori principali:	C. Moorthy, A. Shafeek, V. Gurunathan, R. Sudhakar
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	Nature Portfolio 2026-02-01
Serie:	Scientific Reports
Soggetti:	3D knee Total knee replacement Channel feature attention Spatial feature attention Desert scorpion feature selector Falcon hunting optimization
Accesso online:	https://doi.org/10.1038/s41598-026-37847-7
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!