Interpretable polyp classification via end-to-end Concept Bottleneck Models with vision-language concept alignment

Background and objectiveArtificial intelligence has improved adenoma detection during colonoscopy, but most models remain black boxes, limiting clinical trust, especially for sessile serrated lesions (SSLs). Concept Bottleneck Models (CBMs) route predictions through human-understandable concepts. We...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Qiunan Ji, Zihe Feng, Xinjuan Liu, Jianyu Hao
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	Frontiers Media S.A. 2026-07-01
Saila:	Frontiers in Artificial Intelligence
Gaiak:	colonoscopy Concept Bottleneck Model explainable AI polyp classification sessile serrated lesion vision-language model
Sarrera elektronikoa:	https://www.frontiersin.org/articles/10.3389/frai.2026.1853584/full
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!