Comparative Validation of Polyp Detection Methods in Video Colonoscopy: Results From the MICCAI 2015 Endoscopic Vision Challenge

By Jorge Bernal, Nima Tajkbaksh, F. Sánchez, B. Matuszewski, Hao Chen, Lequan Yu, Quentin Angermann, O. Romain, Bjørn Rustad, Ilangko Balasingham and 14 more. IEEE Transactions on Medical Imaging, 2017

414 citations recorded by the source corpus.

Colonoscopy is the gold standard for colon cancer screening though some polyps are still missed, thus preventing early disease detection and treatment. Several computational systems have been proposed to assist polyp detection during colonoscopy but so far without consistent evaluation. The lack of publicly available annotated databases has made it difficult to compare methods and to assess if they achieve performance levels acceptable for clinical use. The Automatic Polyp Detection sub-challenge, conducted as part of the Endoscopic Vision Challenge (http://endovis.grand-challenge.org) at the international conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2015, was an effort to address this need. In this paper, we report the results of this comparative evaluation of polyp detection methods, as well as describe additional experiments to further explore differences between methods. We define performance metrics and provide evaluation databases that allow comparison of multiple methodologies. Results show that convolutional neural networks are the state of the art. Nevertheless, it is also demonstrated that combining different methodologies can lead to an improved overall performance.

Subfields: Computer Vision and Pattern Recognition, Oncology

View Paper: https://www.semanticscholar.org/paper/fdf0586fee56ee8a1b2fefea2600d86140382c5b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Oncology

Citations in the corpus

Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study (2019, background): “40 41 In order for an automatic polyp detection system to be considered for real-world clinical application, it must have a very high sensitivity and specificity, a sufficient real-time standard processing time and an onscreen alerting system.”
Surgical data science – from concepts toward clinical translation (2020, methodology): “EndoVis-GIANA (Bernal et al., 2017) colonoscopy, wireless capsule endoscopy in-vivo, human video, images segmentation and classification of polyps / angiodysplasia / bowel lesions 2015 – 2018”
INet: Convolutional Networks for Biomedical Image Segmentation (2021, methodology): “…of the proposed method in the segmentation of biomedical images, we carried out experiments on nine public imaging datasets: three brain (BraTS2013, LMS, BTD) one heart MRI [42]–[44], one liver one spleen CT [44], [45], one lung X-ray [9], one colon endoscopic [46], and one nerve ultrasonic [47].”
Deep Learning Localizes and Identifies Polyps in Real Time with 96% Accuracy in Screening Colonoscopy (2018, neutral): “In comparison, the fastest polyp localization model presented in prior work 47 , among eight, can process only 7 frames per second, and the slowest one merely 0.1 frames per second.”
A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images (2016, background): “org) [28], we introduce a benchmark for endoluminal scene object segmentation.”
DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation (2020, methodology): “• The 2015 MICCAI sub-challenge on automatic polyp detection [22] used the CVC-ClinicDB [19] for training and ETIS-Larib [23] for testing in the case of polyp detection task.”
MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation (2019, neutral): “distinguish even for a trained operator (Bernal et al., 2017).”
Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Training (2017, background): “Recent advances in machine learning have led to significant progress on detection [4], [37], [38], segmentation [39] and classification [40] of lesions in endoscopy images.”
A Comprehensive Study on Colorectal Polyp Segmentation With ResUNet++, Conditional Random Field and Test-Time Augmentation (2021, methodology): “[18] hosted the automatic polyp detection in colonoscopy videos sub-challenge, and later on, they presented a comparative validation of different methods for automatic polyp detection and concluded that the SOTA CNN based methods provide the most promising results.”