Colonoscopy polyp detection and classification: Dataset creation and comparative evaluations

Autor: Mohammad I. Fathan, Jean S. Wang, Krushi Patel, Ajay Bansal, Kaidong Li, Amit Rastogi, Tianxiao Zhang, Cuncong Zhong, Guanghui Wang
Jazyk: angličtina
Rok vydání: 2021
Předmět:
FOS: Computer and information sciences
Colorectal cancer
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
Colonoscopy
computer.software_genre
Lung and Intrathoracic Tumors
Machine Learning
Breast Tumors
Medicine and Health Sciences
Ground truth
Deep cnn
Multidisciplinary
medicine.diagnostic_test
Crc screening
Oncology
Medicine
Anatomy
Colorectal Neoplasms
Research Article
Computer and Information Sciences
Computer Science - Artificial Intelligence
Colon
Death Rates
Science
Colonic Polyps
Surgical and Invasive Medical Procedures
Machine learning
Digestive System Procedures
Deep Learning
Population Metrics
Artificial Intelligence
Breast Cancer
medicine
Humans
neoplasms
Colorectal Cancer
Population Biology
business.industry
Deep learning
Cancers and Neoplasms
Biology and Life Sciences
Endoscopy
medicine.disease
Object detection
digestive system diseases
Gastrointestinal Tract
Artificial Intelligence (cs.AI)
Neural Networks
Computer
Gastrointestinal imaging
Artificial intelligence
business
Digestive System
computer
Zdroj: PLoS ONE, Vol 16, Iss 8, p e0255809 (2021)
PLoS ONE
ISSN: 1932-6203
Popis: Colorectal cancer (CRC) is one of the most common types of cancer with a high mortality rate. Colonoscopy is the preferred procedure for CRC screening and has proven to be effective in reducing CRC mortality. Thus, a reliable computer-aided polyp detection and classification system can significantly increase the effectiveness of colonoscopy. In this paper, we create an endoscopic dataset collected from various sources and annotate the ground truth of polyp location and classification results with the help of experienced gastroenterologists. The dataset can serve as a benchmark platform to train and evaluate the machine learning models for polyp classification. We have also compared the performance of eight state-of-the-art deep learning-based object detection models. The results demonstrate that deep CNN models are promising in CRC screening. This work can serve as a baseline for future research in polyp detection and classification.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje