Carregant...
Fitxers
Tipus de document
ArticleVersió
Versió publicadaData de publicació
Llicència de publicació
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/207762
Self-supervised out-of-distribution detection in wireless capsule endoscopy images.
Títol de la revista
Director/Tutor
ISSN de la revista
Títol del volum
Recurs relacionat
Resum
While deep learning has displayed excellent performance in a broad spectrum of application areas, neural networks still struggle to recognize what they have not seen, i.e., out-of-distribution (OOD) inputs. In the medical field, building robust models that are able to detect OOD images is highly critical, as these rare images could show diseases or anomalies that should be detected. In this study, we use wireless capsule endoscopy (WCE) images to present a novel patch-based self-supervised approach comprising three stages. First, we train a triplet network to learn vector representations of WCE image patches. Second, we cluster the patch embeddings to group patches in terms of visual similarity. Third, we use the cluster assignments as pseudolabels to train a patch classifier and use the Out-of-Distribution Detector for Neural Networks (ODIN) for OOD detection. The system has been tested on the Kvasir-capsule, a publicly released WCE dataset. Empirical results show an OOD detection improvement compared to baseline methods. Our method can detect unseen pathologies and anomalies such as lymphangiectasia, foreign bodies and blood with 𝐴𝑈 𝑅𝑂𝐶 > 0.6. This work presents an effective solution for OOD detection models without needing labeled images.
Matèries (anglès)
Citació
Citació
QUINDÓS SÁNCHEZ, Arnau, LAIZ TRECEÑO, Pablo, VITRIÀ I MARCA, Jordi, SEGUÍ MESQUIDA, Santi. Self-supervised out-of-distribution detection in wireless capsule endoscopy images.. _Artificial Intelligence in Medicine_. 2023. [consulta: 10 de gener de 2026]. ISSN: 0933-3657. [Disponible a: https://hdl.handle.net/2445/207762]