Edge detection of retinal OCT image based on complex shearlet transform. Issue 10 (26th June 2019)

• Record Type: Journal Article
• Authors: Xiaoming, Liu; Ke, Xu; Peng, Zhou; Jiannan, Chi
• Is Part Of: IET image processing. Volume 13:Issue 10(2019)
• Page Start: 1686
• Page End: 1693
• Publication Date: 2019-06-26
• Subjects: optical tomography -- biomedical optical imaging -- image denoising -- wavelet transforms -- edge detection -- image resolution -- eye -- vision defects -- medical image processing -- transforms -- diseases; inner plexiform layer -- ganglion cell layer -- layered structures -- normal retinal macula area -- OCT images -- pulse type edge -- step type edge -- merit value -- complex shearlet‐based method -- wavelet methods -- phase congruence method -- multiscale shearlet -- optimal sparse approximation singular curves -- OCT detection method -- layer structure blur -- low contrast -- optical coherence tomography images -- retinal OCT image -- edge detection; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.6634
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Aiming at the problem that optical coherence tomography (OCT) images with low contrast and layer structure blur are difficult to be automatically layered, a new OCT detection method based on complex shearlet transform is proposed. The method utilises nearly optimal sparse approximation singular curves of multi‐scale shearlet transform, and the contrast invariance of the phase congruence method. Compared with the Canny edge detector and wavelet methods, the complex shearlet‐based method achieved the highest Pratt figure of merit (PFOM) value. The PFOM value of a step type edge is 0.92, and that of a pulse type edge is 0.98. Three types of OCT images were tested, including normal retinal macula area, dry age‐related macular degeneration, and Stargardt disease. The experimental results show that the complex shearlet‐based method can detect more layered structures of OCT images, especially the boundary between the ganglion cell layer and the inner plexiform layer that is difficult to detect, and it can detect various types of OCT images. The complex shearlet‐based transform method provides an effective and general way to measure retinal OCT images.