Polyps segmentation using synthetic images generated by GAN
MetadataShow full item record
Early identification of polyps in the lower gastrointestinal (GI) tract can lead to prevention of life-threatening colorectal cancer. Multiple studies have shown that up to 28% of polyps might be missed during colonoscopy procedures [19, 47]. Developing computer-aided diagnosis (CAD) systems to detect polyps can improve detection accuracy and efficiency, assist examiners, and help to prevent the development of colorectal cancer. However, lack of annotated data is a common challenge when building CAD systems. Generating synthetic medical data is an active research area to overcome the problem of having relatively few true positive cases in the medical domain. To be able to efficiently train machine learning (ML) models, which are the core of CAD systems, a considerable amount of data should be used. This thesis has experimented with state-of-theart generative adversarial networks (GAN) to generate usable synthetic polyp data. In this respect, we propose the PolypConnect pipeline, which can convert non-polyp images into polyp images to increase the size of training datasets for training. We present the whole pipeline with quantitative and qualitative evaluations involving endoscopists. The polyp segmentation model trained using synthetic data, and real data shows a 5.1% improvement of mean intersection over union (mIOU), compared to the model trained only using real data.