A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation

Colonoscopy is considered the gold standard for detection of colorectal cancer and its precursors. Existing examination methods are, however, hampered by high overall miss-rate, and many abnormalities are left undetected. Computer-Aided Diagnosis systems based on advanced machine learning algorithms...

Full description

Bibliographic Details
Main Authors:	De Lange, T. (Author), Halvorsen, P. (Author), Jha, D. (Author), Johansen, D. (Author), Johansen, H.D (Author), Riegler, M.A (Author), Smedsrud, P.H (Author)
Format:	Article
Language:	English
Published:	Institute of Electrical and Electronics Engineers Inc. 2021
Subjects:	algorithm Algorithms Article Buffer storage colon polyp Colonic Polyps colonoscopy Colonoscopy colorectal polyp computer aided design Computer aided diagnosis Computer aided diagnosis systems Computer aided instruction computer assisted diagnosis Computer games conditional random field Conditional random field controlled study convolutional neural network Cross-dataset evaluation Diagnosis, Computer-Assisted diagnostic imaging Diseases Endoscopic examination Endoscopy gastroenterologist generalization Generalization capability human Humans image segmentation intestine preparation learning learning algorithm Learning algorithms machine learning Machine learning mathematical model Neural Networks, Computer polyp segmentation prediction Prediction performance Proposed architectures Random processes receiver operating characteristic ResUNet++ sampling State-of-the-art methods support vector machine test-time augmentation training validation process videorecording
Online Access:	View Fulltext in Publisher

Internet

View Fulltext in Publisher

A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation

Internet

Similar Items