Training data enhancements for improving colonic polyp detection using deep convolutional neural networks

作者：

Highlights：

• We propose data enhancements for a small dataset.

• A novel method to increase the quantity and variability of training images from a publicly available colonoscopy dataset.

• The results indicating that our method is promising to improve automatic polyp detection.

摘要

•We propose data enhancements for a small dataset.•A novel method to increase the quantity and variability of training images from a publicly available colonoscopy dataset.•The results indicating that our method is promising to improve automatic polyp detection.

论文关键词：Colonoscopy,Polyp detection,Augmentation,Training data,Generative adversarial networks

论文评审过程：Received 18 November 2019, Revised 4 August 2020, Accepted 3 November 2020, Available online 21 November 2020, Version of Record 17 December 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101988