Deep learning to find colorectal polyps in colonoscopy: A systematic literature review

作者：

Highlights：

• Convolutional neural networks are the most used architecture.

• End-to-end methods are preferred over hybrid methods.

• Recall is the most used metric for detection and localization tasks.

• Intersection over Union is highly used in segmentation.

• A common validation framework, including dataset and metrics, is missing.

摘要

•Convolutional neural networks are the most used architecture.•End-to-end methods are preferred over hybrid methods.•Recall is the most used metric for detection and localization tasks.•Intersection over Union is highly used in segmentation.•A common validation framework, including dataset and metrics, is missing.

论文关键词：Colorectal cancer,Deep learning,Detection,Localization,Segmentation

论文评审过程：Received 27 August 2019, Revised 3 March 2020, Accepted 1 July 2020, Available online 1 August 2020, Version of Record 9 August 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101923