Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning

被引:190
作者
Jha, Debesh [1 ,2 ]
Ali, Sharib [2 ,4 ]
Tomar, Nikhil Kumar [1 ]
Johansen, Havard D. [3 ]
Johansen, Dag [3 ]
Rittscher, Jens [2 ,4 ]
Riegler, Michael A. [1 ]
Halvorsen, Pal [1 ,5 ]
机构
[1] SimulaMet, N-0167 Oslo, Norway
[2] Univ Oxford, Big Data Inst, Dept Engn Sci, Oxford OX3 7XF, England
[3] UiT Arctic Univ Norway, Dept Comp Sci, N-9037 Tromso, Norway
[4] Oxford NIHR Biomed Res Ctr, Oxford OX4 2PGV, England
[5] Oslo Metropolitan Univ, Dept Comp Sci, N-0167 Oslo, Norway
基金
英国惠康基金;
关键词
Colonoscopy; Image segmentation; Benchmark testing; Real-time systems; Cancer; Videos; Biomedical imaging; Medical image segmentation; ColonSegNet; colonoscopy; polyps; deep learning; detection; localisation; benchmarking; Kvasir-SEG; CONVOLUTIONAL NEURAL-NETWORKS; COLORECTAL POLYPS; CANCER; RISK; CNN;
D O I
10.1109/ACCESS.2021.3063716
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Computer-aided detection, localisation, 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, localisation, 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 localisation 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.
引用
收藏
页码:40496 / 40510
页数:15
相关论文
共 65 条
[1]  
Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
[2]  
Ali S, 2019, arXiv:1905.03209
[3]   Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy ? [J].
Ali, Sharib ;
Dmitrieva, Mariia ;
Ghatwary, Noha ;
Bano, Sophia ;
Polat, Gorkem ;
Temizel, Alptekin ;
Krenzer, Adrian ;
Hekalo, Amar ;
Guo, Yun Bo ;
Matuszewski, Bogdan ;
Gridach, Mourad ;
Voiculescu, Irina ;
Yoganand, Vishnusai ;
Chavan, Arnav ;
Raj, Aryan ;
Nguyen, Nhan T. ;
Tran, Dat Q. ;
Huynh, Le Duy ;
Boutry, Nicolas ;
Rezvy, Shahadate ;
Chen, Haijian ;
Choi, Yoon Ho ;
Subramanian, Anand ;
Balasubramanian, Velmurugan ;
Gao, Xiaohong W. ;
Hu, Hongyu ;
Liao, Yusheng ;
Stoyanov, Danail ;
Daul, Christian ;
Realdon, Stefano ;
Cannizzaro, Renato ;
Lamarque, Dominique ;
Tran-Nguyen, Terry ;
Bailey, Adam ;
Braden, Barbara ;
East, James E. ;
Rittscher, Jens .
MEDICAL IMAGE ANALYSIS, 2021, 70 (70)
[4]   A deep learning framework for quality assessment and restoration in video endoscopy [J].
Ali, Sharib ;
Zhou, Felix ;
Bailey, Adam ;
Braden, Barbara ;
East, James E. ;
Lu, Xin ;
Rittscher, Jens .
MEDICAL IMAGE ANALYSIS, 2021, 68
[5]   An objective comparison of detection and segmentation algorithms for artefacts in clinical endoscopy [J].
Ali, Sharib ;
Zhou, Felix ;
Braden, Barbara ;
Bailey, Adam ;
Yang, Suhui ;
Cheng, Guanju ;
Zhang, Pengyi ;
Li, Xiaoqiong ;
Kayser, Maxime ;
Soberanis-Mukul, Roger D. ;
Albarqouni, Shadi ;
Wang, Xiaokang ;
Wang, Chunqing ;
Watanabe, Seiryo ;
Oksuz, Ilkay ;
Ning, Qingtian ;
Yang, Shufan ;
Khan, Mohammad Azam ;
Gao, Xiaohong W. ;
Realdon, Stefano ;
Loshchenov, Maxim ;
Schnabel, Julia A. ;
East, James E. ;
Wagnieres, Georges ;
Loschenov, Victor B. ;
Grisan, Enrico ;
Daul, Christian ;
Blondel, Walter ;
Rittscher, Jens .
SCIENTIFIC REPORTS, 2020, 10 (01)
[6]  
[Anonymous], 2015, Tech. Rep.
[7]  
[Anonymous], 2009, BILDVERARBEITUNG MED
[8]   Survival Trends in Gastric Adenocarcinoma: A Population-Based Study in Sweden [J].
Asplund, Johannes ;
Kauppila, Joonas H. ;
Mattsson, Fredrik ;
Lagergren, Jesper .
ANNALS OF SURGICAL ONCOLOGY, 2018, 25 (09) :2693-2702
[9]   SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation [J].
Badrinarayanan, Vijay ;
Kendall, Alex ;
Cipolla, Roberto .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (12) :2481-2495
[10]   AdaResU-Net: Multiobjective adaptive convolutional neural network for medical image segmentation [J].
Baldeon-Calisto, Maria ;
Lai-Yuen, Susana K. .
NEUROCOMPUTING, 2020, 392 :325-340