AI Science Tracker
EN

Quantification of Retinal Nerve Fibre Layer Thickness on Optical Coherence Tomography with a Deep Learning Segmentation-Free Approach

University of Pittsburgh; UPMC · 15 Jan 2020 · medicine

Discovery

Quantification of Retinal Nerve Fibre Layer Thickness on Optical Coherence Tomography with a Deep Learning Segmentation-Free Approach

Source check: Source checked. Not independent scientific confirmation.

Finding: A ResNet34 model predicted retinal nerve fibre layer thickness directly from unsegmented OCT scans. In three held-out sets, predictions tracked conventional measurements on clean scans and more closely matched same-day good-quality references on scans with segmentation errors or other artefacts. This retrospective proof of concept did not test patient outcomes.

Technology: ResNet34 deep-learning model predicting retinal nerve fibre layer thickness from unsegmented optical coherence tomography scans

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
A fine-tuned ResNet34 deep-learning model predicts global retinal nerve fibre layer thickness directly from unsegmented OCT B-scans.
Test and result
The full study evaluated 25,285 B-scans from 1,338 eyes of 706 subjects in three test sets. Correlations with reference measurements were 0.983 on clean scans, 0.972 versus 0.829 for conventional segmentation on scans with segmentation errors, and 0.940 versus 0.640 on scans with other artefacts.
Limitation / still unknown
Retrospective test; references were conventional measurements or same-day good-quality scans. No downstream patient benefit was evaluated.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.nature.com/articles/s41598-019-57196-y

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary source full text, including Methods and Results; first result-bearing version checked against primary publication metadata..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.

Related catalog entries

Links use documented relationships where available, plus shared catalog context. A shared topic or model family does not establish a scientific dependency.