Abstract
Purpose: To investigate the thickness changes of outer retinal layers in subjects with white matter hyperintensities (WMH) and Parkinson's Disease (PD). Methods: 56 eyes from 31 patients with WMH, 11 eyes from 6 PD patients, and 58 eyes from 32 healthy controls (HC) were enrolled in this study. A macular-centered scan was conducted on each participant using a spectral-domain optical coherence tomography (SD-OCT) device. After speckle noise reduction, a state-of-the-art deep learning method (i.e., a context encoder network) was employed to segment the outer retinal layers from OCT B-scans. Thickness quantification of the outer retinal layers was conducted on the basis of the segmentation results. Results: WMH patients had significantly thinner Henle fiber layers, outer nuclear layers (HFL+ONL) and photoreceptor outer segments (OS) than HC (p = 0.031, and p = 0.005), while PD patients showed a significant increase of mean thickness in the interdigitation zone and the retinal pigment epithelium/Bruch complex (IZ+RPE) (19.619 ± 4.626) compared to HC (17.434 ± 1.664). There were no significant differences in the thickness of the outer plexiform layer (OPL), the myoid and ellipsoid zone (MEZ), and the IZ+RPE layer between WMH and HC subjects. Similarly, there were also no obvious differences in the thickness of the OPL, HFL+ONL, MEZ and the OS layer between PD and HC subjects. Conclusion: Thickness changes in HFL+ONL, OS, and IZ+RPE layers may correlate with brain-related diseases such as WMH and PD. Further longitudinal study is needed to confirm HFL+ONL/OS/IZ+RPE layer thickness as potential biomarkers for detecting certain brain-related diseases.
Introduction
Diagnosing and monitoring brain-related diseases like Parkinson’s Disease (PD) or Cerebral Small Vessel Disease (often indicated by White Matter Hyperintensities, or WMH) typically requires expensive or invasive procedures such as MRI or PET scans. However, because the retina develops from the same embryonic tissue as the brain, it shares significant anatomical and physiological traits with the central nervous system. This study explores whether automated thickness measurements of specific outer retinal sub-layers can serve as non-invasive biomarkers for these neurological conditions.
Methods and Materials
The researchers utilized Spectral-Domain Optical Coherence Tomography (SD-OCT) to capture high-resolution macular cross-sections from 31 WMH patients, 6 PD patients, and 32 healthy controls. To ensure precise measurement, the team implemented a sophisticated deep learning pipeline:
- Speckle Noise Reduction: Multi-frame fusion-based super-resolution was used to clean OCT images.
- Automated Segmentation: A Context Encoder Network (CE-Net) was employed to segment five distinct outer layers: the Outer Plexiform Layer (OPL), Henle Fiber Layer + Outer Nuclear Layer (HFL+ONL), Myoid and Ellipsoid Zone (MEZ), Photoreceptor Outer Segments (OS), and the Interdigitation Zone + RPE complex (IZ+RPE).
Key Results
The study revealed distinct structural changes associated with each disease state:
- White Matter Hyperintensity (WMH): Patients showed significantly thinner HFL+ONL and OS layers compared to healthy controls ($p = 0.031$ and $p = 0.005$, respectively). This thinning likely mirrors the axonal damage and white matter degradation occurring in the brain.
- Parkinson’s Disease (PD): Conversely, PD patients exhibited a significant increase in the mean thickness of the IZ+RPE layer ($19.619 \pm 4.626$ µm) compared to healthy controls ($17.434 \pm 1.664$ µm).
- Specificity: No significant differences were found in the OPL or MEZ layers across groups, suggesting that disease-related changes are highly specific to certain retinal structures.
Discussion
The findings support two primary biological hypotheses. First, the Axonal Mirroring Hypothesis suggests that thinning in the Henle fiber layer (unmyelinated axons) in WMH patients reflects systemic neurovascular degradation. Second, the Dopamine Compensation Hypothesis suggests that the thickening of the IZ+RPE in PD patients may be a compensatory response; as brain dopamine neurons die, the RPE—which also produces dopamine precursors—may hypertrophy to offset the shortage.
Conclusion
While limited by a small sample size, this study demonstrates that deep learning-based retinal segmentation can identify specific structural changes linked to WMH and PD. These outer retinal layers show promise as non-invasive biomarkers, though longitudinal studies are required to determine if these changes precede clinical symptoms, potentially enabling earlier screening for neurodegenerative diseases.
Summary updated