Automatic production of synthetic labelled OCT images using an active shape model. Issue 15 (18th February 2021)

• Record Type: Journal Article
• Authors: Danesh, Hajar; Maghooli, Keivan; Dehghani, Alireza; Kafieh, Rahele
• Is Part Of: IET image processing. Volume 14:Issue 15(2020)
• Page Start: 3812
• Page End: 3818
• Publication Date: 2021-02-18
• Subjects: blood vessels -- biomedical optical imaging -- optical tomography -- image segmentation -- image processing -- medical image processing -- learning (artificial intelligence) -- eye -- speckle; modified active shape model -- available images -- retinal blood vessels -- retinal images -- automatic production -- synthetic labelled OCT images -- medical imaging -- machine learning algorithms -- image processing algorithms -- synthetic coherence tomography -- labelled optical coherence tomography -- accurately labelled data; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2020.0075
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Limited labelled data is a challenge in the field of medical imaging and the need for a large number of them is paramount for the training of machine learning algorithms, as well as measuring the performance of image processing algorithms. The purpose of this study is to construct synthetic and labelled optical coherence tomography (OCT) data to solve the problems of having access to accurately labelled data and evaluating the processing algorithms. In this study, a modified active shape model is used which considers the anatomical features of available images such as the number and thickness of the layers as well as their associated brightness, the location of retinal blood vessels and shadow information with respect to speckle noise. The algorithm is also able to provide different data sets with the varying noise level. The validity of the proposed method for the synthesis of retinal images is measured by two methods (qualitative assessment and quantitative analysis).