dc.description.abstract | 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. | en_US |