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/2445/193849
Time-based self-supervised learning for Wireless Capsule Endoscopy
Títol de la revista
Director/Tutor
ISSN de la revista
Títol del volum
Recurs relacionat
Resum
State-of-the-art machine learning models, and especially deep learning ones, are significantly data-hungry; they require vast amounts of manually labeled samples to function correctly. However, in most medical imaging fields, obtaining said data can be challenging. Not only the volume of data is a problem, but also the imbalances within its classes; it is common to have many more images of healthy patients than of those with pathology. Computer-aided diagnostic systems suffer from these issues, usually over-designing their models to perform accurately. This work proposes using self-supervised learning for wireless endoscopy videos by introducing a custom-tailored method that does not initially need labels or appropriate balance. We prove that using the inferred inherent structure learned by our method, extracted from the temporal axis, improves the detection rate on several domain-specific applications even under severe imbalance. State-of-the-art results are achieved in polyp detection, with 95.00 ± 2.09% Area Under the Curve, and 92.77 ± 1.20% accuracy in the CAD-CAP dataset.
Matèries (anglès)
Citació
Citació
PASCUAL I GUINOVART, Guillem, LAIZ TRECEÑO, Pablo, GARCÍA, Albert, WENZEK, Hagen, VITRIÀ I MARCA, Jordi, SEGUÍ MESQUIDA, Santi. Time-based self-supervised learning for Wireless Capsule Endoscopy. _Computers in Biology and Medicine_. 2022. Vol. 146. [consulta: 29 de gener de 2026]. ISSN: 0010-4825. [Disponible a: https://hdl.handle.net/2445/193849]