UMIAD-EGMF: unsupervised medical image anomaly detection based on edge guidance and multi-scale flow fusion

Abstract Medical imaging technology has advanced rapidly in recent years; however, abnormalities in medical images are often rare and complex, making sample labels difficult to obtain for supervised learning of detection models. Existing unsupervised anomaly detection methods, which are the mainstre...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Zhirong Li, Guangfeng Lin, Dou Zhang, Rongxin Huang, Jing Yang
Format:	Artigo
Jezik:	Inglês
Izdano:	SpringerOpen 2026-03-01
Serija:	Visual Computing for Industry, Biomedicine, and Art
Teme:	Medical image analysis Anomaly detection Unsupervised learning Edge guidance Multi-scale flow fusion
Online dostop:	https://doi.org/10.1186/s42492-026-00215-3
Oznake:	Označite Brez oznak, prvi označite!