Look-up in Google Scholar
Full metadata record
Montoya Zegarra, Javier Alexander
Mandujano Cornejo, Vittorino
2023-11-27T15:00:28Z
2023-11-27T15:00:28Z
2023
1080233
https://hdl.handle.net/20.500.12590/17849
Colorectal cancer (CRC) is the third most common type of cancer worldwide. It can be prevented by screening the colon and detecting polyps which might become malign. Therefore, an accurate diagnosis of polyps in colonoscopy images is crucial for CRC prevention. The introduction of computational techniques, well known as Computed Aided Diagnosis, facilitates diffusion and improves early recognition of potentially cancerous tissues. In this work, we propose a novel hybrid deep learning architecture for polyp image segmentation named Polyp2Seg. The model adopts a transformer architecture as its encoder to extract multi-hierarchical features. Additionally, a novel Feature Aggregation Module (FAM) merges progressively the multilevel features from the encoder to better localise polyps by adding semantic information. Next, a Multi-Context Attention Module (MCAM) removes noise and other artifacts, while incorporating a multi-scale attention mechanism to further improve polyp detection. Quantitative and qualitative experiments on five challenging datasets and over 5 different SOTAs demonstrate that our method significantly improves the segmentation accuracy of Polyps under different evaluation metrics. Our model achieves a new state-of the-art over most of the datasets.
Tesis de maestría
application/pdf
eng
Universidad Católica San Pablo
info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc/4.0/
Deep learning
Computer visión
Colo-rectal cancer
Image Segmentation
Medical data
Polyp image segmentation with polyp2seg
info:eu-repo/semantics/masterThesis
Universidad Católica San Pablo. Departamento de Ciencia de la Computación
Ciencia de la Computación
Maestría
Maestro en Ciencia de la Computación
PE
http://purl.org/pe-repo/ocde/ford#1.02.01
Escuela Profesional Ciencia de la Computación
https://purl.org/pe-repo/renati/level#maestro
41312254
https://orcid.org/0000-0002-3652-1954
70512168
611017
Ochoa Luna, José Eduardo
Dou, Qi
Yang, Guang
https://purl.org/pe-repo/renati/type#tesis
Privada asociativa
info:eu-repo/semantics/publishedVersion



This item is licensed under a Creative Commons License Creative Commons