A hierarchical multi-task approach to gastrointestinal image analysis

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Galdran, Adrian
• dc.contributor.author Carneiro, Gustavo
• dc.contributor.author González Ballester, Miguel Ángel, 1973-
• dc.date.accessioned 2023-02-23T07:12:16Z
• dc.date.available 2023-02-23T07:12:16Z
• dc.date.issued 2021
• dc.description Comunicació presentada a ICPR International Workshops and Challenges, celebrat del 10 al 15 de gener de 2021 de manera virtual.
• dc.description.abstract A large number of different lesions and pathologies can affect the human digestive system, resulting in life-threatening situations. Early detection plays a relevant role in the successful treatment and the increase of current survival rates to, e.g., colorectal cancer. The standard procedure enabling detection, endoscopic video analysis, generates large quantities of visual data that need to be carefully analyzed by an specialist. Due to the wide range of color, shape, and general visual appearance of pathologies, as well as highly varying image quality, such process is greatly dependent on the human operator experience and skill. In this work, we detail our solution to the task of multi-category classification of images from the gastrointestinal (GI) human tract within the 2020 Endotect Challenge. Our approach is based on a Convolutional Neural Network minimizing a hierarchical error function that takes into account not only the finding category, but also its location within the GI tract (lower/upper tract), and the type of finding (pathological finding/therapeutic intervention/anatomical landmark/mucosal views’ quality). We also describe in this paper our solution for the challenge task of polyp segmentation in colonoscopies, which was addressed with a pretrained double encoder-decoder network. Our internal cross-validation results show an average performance of 91.25 Mathews Correlation Coefficient (MCC) and 91.82 Micro-F1 score for the classification task, and a 92.30 F1 score for the polyp segmentation task. The organization provided feedback on the performance in a hidden test set for both tasks, which resulted in 85.61 MCC and 86.96 F1 score for classification, and 91.97 F1 score for polyp segmentation. At the time of writing no public ranking for this challenge had been released.
• dc.format.mimetype application/pdf
• dc.identifier.citation Galdran A, Carneiro G, González Ballester MA. A hierarchical multi-task approach to gastrointestinal image analysis. In: del Bimbo A, Cucchiara R, Sclaroff S, Farinella GM, Mei T, Bertini M, Escalante HJ, Vezzani R, editors. Pattern Recognition: ICPR International Workshops and Challenges; 2021 Jan 10-15; online. Cham: Springer; 2021. p. 275-82. DOI: 10.1007/978-3-030-68793-9_19
• dc.identifier.doi http://dx.doi.org/10.1007/978-3-030-68793-9_19
• dc.identifier.issn 0302-9743
• dc.identifier.uri http://hdl.handle.net/10230/55889
• dc.language.iso eng
• dc.publisher Springer
• dc.relation.ispartof del Bimbo A, Cucchiara R, Sclaroff S, Farinella GM, Mei T, Bertini M, Escalante HJ, Vezzani R, editors. Pattern Recognition: ICPR International Workshops and Challenges; 2021 Jan 10-15; online. Cham: Springer; 2021. p. 275-82.
• dc.rights © Springer This is a author's accepted manuscript of: Galdran A, Carneiro G, González Ballester MA. A hierarchical multi-task approach to gastrointestinal image analysis. In: del Bimbo A, Cucchiara R, Sclaroff S, Farinella GM, Mei T, Bertini M, Escalante HJ, Vezzani R, editors. Pattern Recognition: ICPR International Workshops and Challenges; 2021 Jan 10-15; online. Cham: Springer; 2021. p. 275-82. The final version is available online at: http://dx.doi.org/10.1007/978-3-030-68793-9_19
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Colonoscopy image classification
• dc.subject.keyword Polyp segmentation
• dc.title A hierarchical multi-task approach to gastrointestinal image analysis
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/acceptedVersion