Validation of Optical Coherence Tomography Retinal Segmentation in Neurodegenerative Disease

Abstract

PurposeThis study assessed agreement between an automated spectral-domain optical coherence tomography (SD-OCT) retinal segmentation software and manually corrected segmentation to validate its use in a prospective clinical study of neurodegenerative diseases (NDD).MethodsThe sample comprised 30 subjects with NDD, including vascular cognitive impairment, frontotemporal dementia, Parkinson's disease, and Alzheimer's disease. Macular SD-OCT scans were acquired and segmented using Heidelberg Spectralis. For the central foveal B scan of each eye, eight segmentation lines were examined to determine the proportion of each line that the software erroneously delineated. Errors in four lines were manually corrected in all B scans spanning a 6-mm circle centered on the foveola. Mean volume and thickness measurements for four retinal layers (total retina, retinal nerve fiber layer [RNFL], inner retinal layers, and outer retinal layers) were obtained before and after correction.ResultsThe outer plexiform layer line had one of the lowest mean error ratios (2%), while RNFL had the highest (23%). Agreement between automated software and trained observer was excellent (ICC > 0.98) for retinal thickness and volume of all layers. Mean volume differences between software and observers for the four layers ranged from −0.003 to 0.006 mm3. Mean thickness differences ranged from −1.855 to 1.859 μm.ConclusionsDespite occasional small errors in software-generated retinal sublayer segmentation, agreement was excellent between software-derived and observer-corrected mean volume and thickness sublayer measurements.Translational RelevanceAutomated SD-OCT segmentation software generates valid measurements of retinal layer volume and thickness in NDD subjects, thereby avoiding the need to manually correct nonobvious delineation errors.

Retinal Boundary Segmentation in Stargardt Disease Optical Coherence Tomography Images Using Automated Deep Learning

“… 27 – 30 Importantly, some of these methods have been applied to OCT images from patients with age-related macular degeneration, 18 , 20 , 24 , 27 diabetic retinopathy, 11 , 25 macular telangiectasia type 2, 29 diabetic macular oedema, 13 , 23 , 24 pigment epithelium detachment, 28 glaucoma, 15 , 30 multiple sclerosis 17 , 26 retinitis pigmentosa, 31 and neurodegenerative diseases. 32 These diseases are characterized by variable thinning of the inner retinal layers (e.g., glaucoma and multiple sclerosis), thickening or cystic changes in the nuclear layers (e.g., macular telangiectasia type 2 and diabetic retinopathy) or focal disruption of the retinal pigment epithelium (RPE, e.g., age-related macular degeneration, macular telangiectasia, and pigment epithelium detachment). However, OCT segmentation algorithms have not been investigated in Stargardt disease despite its unique lesions, including outer retinal or subretinal flecks, 33 outer retinal atrophy with or without RPE loss, and variable loss of choroidal architecture disrupting the Bruch's membrane contour, 34 – 36 which provide challenges for commercial segmentation software.…”

Ontario Neurodegenerative Disease Research Initiative (ONDRI): Structural MRI methods & outcome measures

“…The Ontario Neurodegenerative Research Initiative (ONDRI) is a multi-site prospective cohort study following patients with neurodegenerative diseases including Alzheimer's disease (AD), mild cognitive impairment (MCI), Parkinson's disease (PD), amyotrophic lateral sclerosis (ALS), frontotemporal dementia (FTD), and a vascular patient cohort (VAS) (Farhan et al, 2017). Over the course of 3 years, multiple assessment platforms acquired comprehensive data from the 520 patients including, clinical and demographic assessments, neuroimaging, neuropsychology, genomics, eye movements, retinal layer morphology, gait performance, and neuropathology (Dilliott et al, 2019;Montero-Odasso et al, 2017;Wong et al, 2019). The multi-modal data collected from ONDRI will be used to explore earlier detection, guide development of novel therapy and improving patient care .…”

Comparison of the Iowa Reference Algorithm to the Heidelberg Spectralis optical coherence tomography segmentation algorithm

“…While the literature shows that advances in segmentation algorithms have emerged every few years, the algorithms we evaluated have been used in recently published cross‐sectional and longitudinal studies, and these algorithms will likely continue to be used for some time . However, it is remarkable that our study found no errors to manually correct with IRA 3.8.…”

“…However, these studies used fully automated segmentation methods without manual correction and looked at only specific or aggregate retinal layer thicknesses. More recently, one report suggested that manual correction of non‐obvious Heidelberg Spectralis segmentation errors is not necessary …”