CRF-EfficientUNet: An Improved UNet Framework for Polyp Segmentation in Colonoscopy Images With Combined Asymmetric Loss Function and CRF-RNN Layer

Colonoscopy is considered the gold-standard investigation for colorectal cancer screening. However, the polyps miss rate in clinical practice is relatively high due to different factors. This presents an opportunity to use AI models to automatically detect and segment polyps, supporting clinicians t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Le Thi Thu Hong, Nguyen Chi Thanh, Tran Quoc Long
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Polyp segmentation medical image analysis deep learning loss function Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/b8277e09f22b489a93e75b1ff6f8e24d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b8277e09f22b489a93e75b1ff6f8e24d
record_format	dspace
spelling	oai:doaj.org-article:b8277e09f22b489a93e75b1ff6f8e24d2021-12-02T00:00:51ZCRF-EfficientUNet: An Improved UNet Framework for Polyp Segmentation in Colonoscopy Images With Combined Asymmetric Loss Function and CRF-RNN Layer2169-353610.1109/ACCESS.2021.3129480https://doaj.org/article/b8277e09f22b489a93e75b1ff6f8e24d2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9622208/https://doaj.org/toc/2169-3536Colonoscopy is considered the gold-standard investigation for colorectal cancer screening. However, the polyps miss rate in clinical practice is relatively high due to different factors. This presents an opportunity to use AI models to automatically detect and segment polyps, supporting clinicians to reduce the number of polyps missed. Inspired by the success of UNets, a popular strategy for solving medical image segmentation tasks, this article proposes a novel framework for polyp segmentation called CRF-EfficientUNet, which enhances UNet using the EfficientNet encoder, a combined asymmetric loss function, and Conditional Random Field as a Recurrent Neural Network (CRF-RNN) layer on top. A novel loss function that combines pixel-wise cross-entropy loss and asymmetric similarity loss to solve the unbalanced imaging data problem is proposed. Training the proposed network with this loss function can achieve a considerably higher Dice score and better polyp segmentation prediction. In addition, we add the CRF-RNN layer to the proposed framework to improve the quality of semantic segmentation. Experimental results on popular benchmark datasets show that CRF-EfficientUNet achieves state-of-the-art accuracy compared to existing methods. The results of the experiments, which are performed on the CVC-ClinicDB dataset for training and testing, are 95.55% Dice and 92.23% IoU. While the experimental results on cross-dataset using Kvasir-SEG as the training set, CVC-ColonDB as the test set are 85.59% Dice and 76.19% IoU. These results indicate that the proposed method has high generalization capability and learning ability, and it can be a compelling choice for practical applications with considerable data variations. The source code is available at: <uri>https://github.com/lethithuhong1302/CRF-EfficientUNet</uri>Le Thi Thu HongNguyen Chi ThanhTran Quoc LongIEEEarticlePolyp segmentationmedical image analysisdeep learningloss functionElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 156987-157001 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Polyp segmentation medical image analysis deep learning loss function Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Polyp segmentation medical image analysis deep learning loss function Electrical engineering. Electronics. Nuclear engineering TK1-9971 Le Thi Thu Hong Nguyen Chi Thanh Tran Quoc Long CRF-EfficientUNet: An Improved UNet Framework for Polyp Segmentation in Colonoscopy Images With Combined Asymmetric Loss Function and CRF-RNN Layer
description	Colonoscopy is considered the gold-standard investigation for colorectal cancer screening. However, the polyps miss rate in clinical practice is relatively high due to different factors. This presents an opportunity to use AI models to automatically detect and segment polyps, supporting clinicians to reduce the number of polyps missed. Inspired by the success of UNets, a popular strategy for solving medical image segmentation tasks, this article proposes a novel framework for polyp segmentation called CRF-EfficientUNet, which enhances UNet using the EfficientNet encoder, a combined asymmetric loss function, and Conditional Random Field as a Recurrent Neural Network (CRF-RNN) layer on top. A novel loss function that combines pixel-wise cross-entropy loss and asymmetric similarity loss to solve the unbalanced imaging data problem is proposed. Training the proposed network with this loss function can achieve a considerably higher Dice score and better polyp segmentation prediction. In addition, we add the CRF-RNN layer to the proposed framework to improve the quality of semantic segmentation. Experimental results on popular benchmark datasets show that CRF-EfficientUNet achieves state-of-the-art accuracy compared to existing methods. The results of the experiments, which are performed on the CVC-ClinicDB dataset for training and testing, are 95.55% Dice and 92.23% IoU. While the experimental results on cross-dataset using Kvasir-SEG as the training set, CVC-ColonDB as the test set are 85.59% Dice and 76.19% IoU. These results indicate that the proposed method has high generalization capability and learning ability, and it can be a compelling choice for practical applications with considerable data variations. The source code is available at: <uri>https://github.com/lethithuhong1302/CRF-EfficientUNet</uri>
format	article
author	Le Thi Thu Hong Nguyen Chi Thanh Tran Quoc Long
author_facet	Le Thi Thu Hong Nguyen Chi Thanh Tran Quoc Long
author_sort	Le Thi Thu Hong
title	CRF-EfficientUNet: An Improved UNet Framework for Polyp Segmentation in Colonoscopy Images With Combined Asymmetric Loss Function and CRF-RNN Layer
title_short	CRF-EfficientUNet: An Improved UNet Framework for Polyp Segmentation in Colonoscopy Images With Combined Asymmetric Loss Function and CRF-RNN Layer
title_full	CRF-EfficientUNet: An Improved UNet Framework for Polyp Segmentation in Colonoscopy Images With Combined Asymmetric Loss Function and CRF-RNN Layer
title_fullStr	CRF-EfficientUNet: An Improved UNet Framework for Polyp Segmentation in Colonoscopy Images With Combined Asymmetric Loss Function and CRF-RNN Layer
title_full_unstemmed	CRF-EfficientUNet: An Improved UNet Framework for Polyp Segmentation in Colonoscopy Images With Combined Asymmetric Loss Function and CRF-RNN Layer
title_sort	crf-efficientunet: an improved unet framework for polyp segmentation in colonoscopy images with combined asymmetric loss function and crf-rnn layer
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/b8277e09f22b489a93e75b1ff6f8e24d
work_keys_str_mv	AT lethithuhong crfefficientunetanimprovedunetframeworkforpolypsegmentationincolonoscopyimageswithcombinedasymmetriclossfunctionandcrfrnnlayer AT nguyenchithanh crfefficientunetanimprovedunetframeworkforpolypsegmentationincolonoscopyimageswithcombinedasymmetriclossfunctionandcrfrnnlayer AT tranquoclong crfefficientunetanimprovedunetframeworkforpolypsegmentationincolonoscopyimageswithcombinedasymmetriclossfunctionandcrfrnnlayer
_version_	1718404009847422976

CRF-EfficientUNet: An Improved UNet Framework for Polyp Segmentation in Colonoscopy Images With Combined Asymmetric Loss Function and CRF-RNN Layer

Ejemplares similares