Automatic production of synthetic labelled OCT images using an active shape model

作     者：Danesh, Hajar Maghooli, Keivan Dehghani, Alireza Kafieh, Rahele 

作者机构：Islamic Azad Univ Sci & Res Branch Dept Biomed Engn Tehran Iran Isfahan Univ Med Sci Med Image & Signal Proc Res Ctr Sch Adv Technol Med Esfahan Iran Isfahan Univ Med Sci Sch Med Dept Ophthalmol Esfahan Iran 

出 版 物：《IET IMAGE PROCESSING》 (IET影像处理)

年 卷 期：2020年第14卷第15期

页      面：3812-3818页

核心收录：

学科分类：0808[工学-电气工程] 1002[医学-临床医学] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Rahele Kafieh and Keivan Maghooli had equal contribution. The theoretical background is developed by Rahele Kafieh and Keivan Maghooli had the responsiblity as academic supervisor 

主　　题：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 

摘      要：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).