Clinical Ophthalmology (Nov 2017)
Spectropathology-corroborated multimodal quantitative imaging biomarkers for neuroretinal degeneration in diabetic retinopathy
Abstract
Arpan Guha Mazumder,1,2 Swarnadip Chatterjee,3 Saunak Chatterjee,1 Juan Jose Gonzalez,4 Swarnendu Bag,5 Sambuddha Ghosh,6 Anirban Mukherjee,7 Jyotirmoy Chatterjee1 1Multimodal Imaging and Computing for Theranostics Laboratory, School of Medical Science and Technology, Indian Institute of Technology-Kharagpur, Kharagpur, West Bengal, India; 2Johns Hopkins University School of Medicine, Baltimore, MD, USA; 3Advanced Technology Development Centre, Indian Institute of Technology-Kharagpur, Kharagpur, West Bengal, India; 4Department of Computer and Electrical Engineering, Rice University, Houston, TX, USA; 5Department of Biotechnology, National Institute of Technology Sikkim, Ravangla Sub-Division, South Sikkim, 6Department of Ophthalmology, Calcutta National Medical College and Hospital, Kolkata, West Bengal, 7Department of Electrical Engineering, Indian Institute of Technology-Kharagpur, Kharagpur, West Bengal, India Introduction: Image-based early detection for diabetic retinopathy (DR) needs value addition due to lack of well-defined disease-specific quantitative imaging biomarkers (QIBs) for neuroretinal degeneration and spectropathological information at the systemic level. Retinal neurodegeneration is an early event in the pathogenesis of DR. Therefore, development of an integrated assessment method for detecting neuroretinal degeneration using spectropathology and QIBs is necessary for the early diagnosis of DR. Methods: The present work explored the efficacy of intensity and textural features extracted from optical coherence tomography (OCT) images after selecting a specific subset of features for the precise classification of retinal layers using variants of support vector machine (SVM). Fourier transform infrared (FTIR) spectroscopy and nuclear magnetic resonance (NMR) spectroscopy were also performed to confirm the spectropathological attributes of serum for further value addition to the OCT, fundoscopy, and fluorescein angiography (FA) findings. The serum metabolomic findings were also incorporated for characterizing retinal layer thickness alterations and vascular asymmetries.Results: Results suggested that OCT features could differentiate the retinal lesions indicating retinal neurodegeneration with high sensitivity and specificity. OCT, fundoscopy, and FA provided geometrical as well as optical features. NMR revealed elevated levels of ribitol, glycerophosphocholine, and uridine diphosphate N-acetyl glucosamine, while the FTIR of serum samples confirmed the higher expressions of lipids and β-sheet-containing proteins responsible for neoangiogenesis, vascular fragility, vascular asymmetry, and subsequent neuroretinal degeneration in DR.Conclusion: Our data indicated that disease-specific spectropathological alterations could be the major phenomena behind the vascular attenuations observed through fundoscopy and FA, as well as the variations in the intensity and textural features observed in OCT images. Finally, we propose a model that uses spectropathology corroborated with specific QIBs for detecting neuroretinal degeneration in early diagnosis of DR. Keywords: diabetic retinopathy, quantitative imaging biomarkers, QIBs, spectropathology, neuroretinal degeneration, optical coherence tomography, OCT, support vector machine, SVM
