Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy

Abstract

The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest a pathway for clinical translation of technologies. Whilst endoscopy is a widely used diagnostic and treatment tool for hollow-organs, there are several core challenges often faced by endoscopists, mainly: 1) presence of multi-class artefacts that hinder their visual interpretation, and 2) difficulty in identifying subtle precancerous precursors and cancer abnormalities. Artefacts often affect the robustness of deep learning methods applied to the gastrointestinal tract organs as they can be confused with tissue of interest. EndoCV2020 challenges are designed to address research questions in these remits. In this paper, we present a summary of methods developed by the top 17 teams and provide an objective comparison of state-of-the-art methods and methods designed by the participants for two sub-challenges: i) artefact detection and segmentation (EAD2020), and ii) disease detection and segmentation (EDD2020). Multi-center, multi-organ, multi-class, and multi-modal clinical endoscopy datasets were compiled for both EAD2020 and EDD2020 sub-challenges. The out-of-sample generalization ability of detection algorithms was also evaluated. Whilst most teams focused on accuracy improvements, only a few methods hold credibility for clinical usability. The best performing teams provided solutions to tackle class imbalance, and variabilities in size, origin, modality and occurrences by exploring data augmentation, data fusion, and optimal class thresholding techniques.

arXiv comment32 pages

References in corpus (18)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Fully Convolutional Networks for Semantic Segmentation
• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
• Optic Disc and Cup Segmentation Methods for Glaucoma Detection with Modification of U-Net Convolutional Neural Network
• Deep Learning is Robust to Massive Label Noise
• Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Training
• Automatic Colon Polyp Detection using Region based Deep CNN and Post Learning Approaches
• CenterNet: Keypoint Triplets for Object Detection
• CornerNet: Detecting Objects as Paired Keypoints
• A deep learning framework for quality assessment and restoration in video endoscopy
• 2018 Robotic Scene Segmentation Challenge
• The Cinderella Complex: Word Embeddings Reveal Gender Stereotypes in Movies and Books
• Towards a Computed-Aided Diagnosis System in Colonoscopy: Automatic Polyp Segmentation Using Convolution Neural Networks
• Neural Network-Based Automatic Liver Tumor Segmentation With Random Forest-Based Candidate Filtering
• RandAugment: Practical automated data augmentation with a reduced search space
• Endoscopy disease detection challenge 2020
• AFP-Net: Realtime Anchor-Free Polyp Detection in Colonoscopy
• Multi-Plateau Ensemble for Endoscopic Artefact Segmentation and Detection

Cited by in corpus (10)

• Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning
• FCN-Transformer Feature Fusion for Polyp Segmentation
• A multi-centre polyp detection and segmentation dataset for generalisability assessment
• Assessing YOLACT++ for real time and robust instance segmentation of medical instruments in endoscopic procedures
• A Systematic Collection of Medical Image Datasets for Deep Learning
• Frontiers in Intelligent Colonoscopy
• DivergentNets: Medical Image Segmentation by Network Ensemble
• How can we learn (more) from challenges? A statistical approach to driving future algorithm development
• Multi-frame Collaboration for Effective Endoscopic Video Polyp Detection via Spatial-Temporal Feature Transformation
• Evaluation and Analysis of Different Aggregation and Hyperparameter Selection Methods for Federated Brain Tumor Segmentation