EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ReticularNet: Automated Pixel-Level Segmentation of Reticular Pseudodrusen on Near-Infrared Reflectance Images by Deep Learning

Souvick Mukherjee, Dylan Wu, Leon von der Emde, Emily Vance, Marco Ji, Mehdi Emamverdi, Tharindu De Silva, Alisa T Thavikulwat, Jayashree Kalpathy-Cramer, Amitha Domalpally, Catherine A Cukras, Tiarnán D L Keenan

Ophthalmology Science · 2026-02 · 6 (2) · 101038

DOI: 10.1016/j.xops.2025.101038 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ophthalmology Science, 2026-02. Verfasst von Souvick Mukherjee und 11 weiteren Autor:innen. Beteiligte Einrichtung: Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, Maryland. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Eye Institute, Research to Prevent Blindness, Johnson and Johnson.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Reticular pseudodrusen (RPD) represent an important biomarker in age-related macular degeneration (AMD) but are difficult to grade and often assessed only for presence or absence, without quantitative or spatial analysis of RPD burden. The objective was to develop and validate a deep learning model for pixel-level RPD grading on near-infrared reflectance (NIR) images, which are commonly acquired in clinical practice and the most accurate en face detection modality.

Design

Deep learning model development study.

Participants

Five hundred eight images of 117 eyes (70 participants) with or without RPD, over a wide range of AMD severities.

Methods

The ground truth grading pipeline comprised reading center multimodal grading for RPD presence and NIR annotation with RPD contours, followed by pixel-level NIR annotation of all individual RPD lesions. The data set was split 80:20 into training and test sets. A DeepLabv3-ResNet-18 segmentation deep learning model ("ReticularNet") was trained to perform pixel-level grading of RPD on NIR images. Its performance was compared with that of 4 ophthalmologists. Main Outcome Measures: Dice similarity coefficient (DSC); intraclass correlation coefficient (ICC) for RPD lesion number, pixel area, and contour area.

Results

For pixel-level grading, ReticularNet achieved a mean DSC of 0.36 (standard deviation 0.16). This was significantly higher than the mean DSC of each ophthalmologist (0.03, 0.13, 0.19, and 0.23; P ≤ 0.02 for each) and of all ophthalmologists together (P < 0.0001). ReticularNet had ICCs of 0.44 (lesion number), 0.56 (pixel area), and 0.61 (contour area), with no significant underestimation or overestimation (P ≥ 0.24). These values were numerically higher than the ICCs of each ophthalmologist, who had ICC ranges of -0.08 to 0.23, -0.05 to 0.40, and -0.09 to 0.58, respectively, and significant underestimation in almost all cases. For all 3 parameters, ReticularNet's ICC was significantly higher than that of all specialists considered together (P ≤ 0.02).

Conclusions

ReticularNet achieved automated pixel-level grading of RPD on NIR images. Its grading was superior to that of 4 ophthalmologists, across a variety of metrics. We are making the code/models available for research use. Improved access to quantitative and spatial RPD grading should lead to improved understanding of these lesions as important biomarkers of retinal disease. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Schlagwörter

Stichwörter der Autor:innen

Age-related macular degenerationDeep learningNear-infrared reflectance imagingReticular pseudodrusenSubretinal drusenoid deposits

Autor:innen und Institutionen

  • Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, Maryland.
  • Department of Ophthalmology, University of Colorado Anschutz Medical Campus, Aurora, Colorado.
  • Wisconsin Reading Center, University of Wisconsin-Madison, Madison, Wisconsin.
  • Roche Pharmaceuticals, Basel, Switzerland.

Förderung

  • National Eye Institute
  • Research to Prevent Blindness
  • Johnson and Johnson
  • National Institutes of Health
  • European Commission

Zitieren

APA

Mukherjee, S., Wu, D., Emde, L. V., Vance, E., Ji, M., Emamverdi, M., De Silva, T., Thavikulwat, A. T., Kalpathy-Cramer, J., Domalpally, A., Cukras, C. A., & Keenan, T. D. L. (2026). ReticularNet: Automated Pixel-Level Segmentation of Reticular Pseudodrusen on Near-Infrared Reflectance Images by Deep Learning. Ophthalmology Science, 6(2), 101038. https://doi.org/10.1016/j.xops.2025.101038

Vancouver

Mukherjee S, Wu D, Emde LV, Vance E, Ji M, Emamverdi M, et al. ReticularNet: Automated Pixel-Level Segmentation of Reticular Pseudodrusen on Near-Infrared Reflectance Images by Deep Learning. Ophthalmology Science. 2026;6(2):101038. doi:10.1016/j.xops.2025.101038

BibTeX
@article{Mukherjee2026,
  author = {Mukherjee, Souvick and Wu, Dylan and Emde, Leon von der and Vance, Emily and Ji, Marco and Emamverdi, Mehdi and De Silva, Tharindu and Thavikulwat, Alisa T and Kalpathy-Cramer, Jayashree and Domalpally, Amitha and Cukras, Catherine A and Keenan, Tiarnán D L},
  title = {ReticularNet: Automated Pixel-Level Segmentation of Reticular Pseudodrusen on Near-Infrared Reflectance Images by Deep Learning},
  journal = {Ophthalmology Science},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {101038},
  doi = {10.1016/j.xops.2025.101038}
}
Kostenlos starten →