Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning
Computer-aided detection, localization, and segmentation methods can help improve colonoscopy procedures. Even though many methods have been built to tackle automatic detection and segmentation of polyps, benchmarking of state-of-the-art methods still remains an open problem. This is due to the incr...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9369308/ |
id |
doaj-7b984445ae78422b905e17d5f8aad21e |
---|---|
record_format |
Article |
spelling |
doaj-7b984445ae78422b905e17d5f8aad21e2021-05-27T23:02:26ZengIEEEIEEE Access2169-35362021-01-019404964051010.1109/ACCESS.2021.30637169369308Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep LearningDebesh Jha0https://orcid.org/0000-0002-8078-6730Sharib Ali1https://orcid.org/0000-0003-1313-3542Nikhil Kumar Tomar2Havard D. Johansen3https://orcid.org/0000-0002-1637-7262Dag Johansen4https://orcid.org/0000-0001-7067-6477Jens Rittscher5Michael A. Riegler6https://orcid.org/0000-0002-3153-2064Pal Halvorsen7SimulaMet, Oslo, NorwayDepartment of Engineering Science, Big Data Institute, University of Oxford, Oxford, U.K.SimulaMet, Oslo, NorwayDepartment of Computer Science, UiT–The Arctic University of Norway, Tromsø, NorwayDepartment of Computer Science, UiT–The Arctic University of Norway, Tromsø, NorwayDepartment of Engineering Science, Big Data Institute, University of Oxford, Oxford, U.K.SimulaMet, Oslo, NorwaySimulaMet, Oslo, NorwayComputer-aided detection, localization, and segmentation methods can help improve colonoscopy procedures. Even though many methods have been built to tackle automatic detection and segmentation of polyps, benchmarking of state-of-the-art methods still remains an open problem. This is due to the increasing number of researched computer vision methods that can be applied to polyp datasets. Benchmarking of novel methods can provide a direction to the development of automated polyp detection and segmentation tasks. Furthermore, it ensures that the produced results in the community are reproducible and provide a fair comparison of developed methods. In this paper, we benchmark several recent state-of-the-art methods using Kvasir-SEG, an open-access dataset of colonoscopy images for polyp detection, localization, and segmentation evaluating both method accuracy and speed. Whilst, most methods in literature have competitive performance over accuracy, we show that the proposed ColonSegNet achieved a better trade-off between an average precision of 0.8000 and mean IoU of 0.8100, and the fastest speed of 180 frames per second for the detection and localization task. Likewise, the proposed ColonSegNet achieved a competitive dice coefficient of 0.8206 and the best average speed of 182.38 frames per second for the segmentation task. Our comprehensive comparison with various state-of-the-art methods reveals the importance of benchmarking the deep learning methods for automated real-time polyp identification and delineations that can potentially transform current clinical practices and minimise miss-detection rates.https://ieeexplore.ieee.org/document/9369308/Medical image segmentationColonSegNetcolonoscopypolypsdeep learningdetection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Debesh Jha Sharib Ali Nikhil Kumar Tomar Havard D. Johansen Dag Johansen Jens Rittscher Michael A. Riegler Pal Halvorsen |
spellingShingle |
Debesh Jha Sharib Ali Nikhil Kumar Tomar Havard D. Johansen Dag Johansen Jens Rittscher Michael A. Riegler Pal Halvorsen Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning IEEE Access Medical image segmentation ColonSegNet colonoscopy polyps deep learning detection |
author_facet |
Debesh Jha Sharib Ali Nikhil Kumar Tomar Havard D. Johansen Dag Johansen Jens Rittscher Michael A. Riegler Pal Halvorsen |
author_sort |
Debesh Jha |
title |
Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning |
title_short |
Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning |
title_full |
Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning |
title_fullStr |
Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning |
title_full_unstemmed |
Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning |
title_sort |
real-time polyp detection, localization and segmentation in colonoscopy using deep learning |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2021-01-01 |
description |
Computer-aided detection, localization, and segmentation methods can help improve colonoscopy procedures. Even though many methods have been built to tackle automatic detection and segmentation of polyps, benchmarking of state-of-the-art methods still remains an open problem. This is due to the increasing number of researched computer vision methods that can be applied to polyp datasets. Benchmarking of novel methods can provide a direction to the development of automated polyp detection and segmentation tasks. Furthermore, it ensures that the produced results in the community are reproducible and provide a fair comparison of developed methods. In this paper, we benchmark several recent state-of-the-art methods using Kvasir-SEG, an open-access dataset of colonoscopy images for polyp detection, localization, and segmentation evaluating both method accuracy and speed. Whilst, most methods in literature have competitive performance over accuracy, we show that the proposed ColonSegNet achieved a better trade-off between an average precision of 0.8000 and mean IoU of 0.8100, and the fastest speed of 180 frames per second for the detection and localization task. Likewise, the proposed ColonSegNet achieved a competitive dice coefficient of 0.8206 and the best average speed of 182.38 frames per second for the segmentation task. Our comprehensive comparison with various state-of-the-art methods reveals the importance of benchmarking the deep learning methods for automated real-time polyp identification and delineations that can potentially transform current clinical practices and minimise miss-detection rates. |
topic |
Medical image segmentation ColonSegNet colonoscopy polyps deep learning detection |
url |
https://ieeexplore.ieee.org/document/9369308/ |
work_keys_str_mv |
AT debeshjha realtimepolypdetectionlocalizationandsegmentationincolonoscopyusingdeeplearning AT sharibali realtimepolypdetectionlocalizationandsegmentationincolonoscopyusingdeeplearning AT nikhilkumartomar realtimepolypdetectionlocalizationandsegmentationincolonoscopyusingdeeplearning AT havarddjohansen realtimepolypdetectionlocalizationandsegmentationincolonoscopyusingdeeplearning AT dagjohansen realtimepolypdetectionlocalizationandsegmentationincolonoscopyusingdeeplearning AT jensrittscher realtimepolypdetectionlocalizationandsegmentationincolonoscopyusingdeeplearning AT michaelariegler realtimepolypdetectionlocalizationandsegmentationincolonoscopyusingdeeplearning AT palhalvorsen realtimepolypdetectionlocalizationandsegmentationincolonoscopyusingdeeplearning |
_version_ |
1721425219712712704 |