Task-Specific Quality Gating for Retinal Optical Coherence Tomography B-Scans: Learned Representations Over Scalar Metrics in Choroid Segmentation
- 1University of Pittsburgh
Abstract
Automated segmentation of Optical Coherence Tomography (OCT) images is a critical component of structural biomarker extraction for retinal diagnostics. Deep learning models achieve state-of-the-art performance on controlled datasets, yet exhibit unpredictable failures on real-world data. Current quality gates rely on device-reported scan quality scores, which have been shown to be unreliable predictors of segmentation performance. We define scan quality in a task-specific sense that is, whether a given B-scan will yield a reliable segmentation from a particular trained model. Under this definition, we perform a systematic evaluation of No-Reference Image Quality Assessment (NR-IQA) metrics, general-purpose and domain-specific pretrained representations as alternative quality gates. To this end, we use choroid segmentation as the prototype task, with a dataset of 6,076 OCT B-scans from 80 subjects. These quality gate candidates are evaluated at three levels: scalar metrics (BRISQUE, NIQE, PIQE, SNR, PSNR), supervised linear probing, and unsupervised partitioning (K-Means) of the feature vectors and the learned representations. All scalar NR-IQA metrics proved inadequate (|r| < 0.20). General-purpose ImageNet-based pretrained representations (EfficientNet-b0, ResNet-50, ViT-B/16) improve upon NR-IQA, achieving ROC-AUC up to 0.77, indicating that learned representations are better suited to task-specific quality gating than hand-crafted scalar statistics. Retinal foundation models (FMs) further close the gap: RETFound (OCT-specific FM) achieves ROC-AUC {approx} 0.81. Unsupervised K-Means partitioning indicates that general-purpose ImageNet-pretrained embeddings, despite carrying a linearly decodable quality signal, do not reliably organize scans by quality geometrically, whereas the retinal FMs produce quality-aligned clusters that exceed a patient-level permutation null, suggesting that domain-specific pretraining provides additional, complementary benefit on top of general-purpose learned representations.
Related
- Evaluating the real-world accessibility of open-source deep learning models for retinal vessel segmentation in optical coherence tomography angiography
- Automated segmentation and clinical characterization of layered plaque in intracoronary optical coherence tomography
- Lesion-Specific Prediction of Segmental Fractional Flow Reserve Using Deep Learning and Optical Coherence Tomography-Derived Features
- Layer-specific retinal microvascular redistribution in children with severe adenotonsillar hypertrophy assessed by optical coherence tomography angiography.
- Anterior Scleral Thickness in Young Saudi Adults Measured Using Swept-Source Optical Coherence Tomography: Sex- and Quadrant-Specific Variations
BibTeX
@misc{hiras2026taskspecific,
title = {{Task-Specific Quality Gating for Retinal Optical Coherence Tomography B-Scans: Learned Representations Over Scalar Metrics in Choroid Segmentation}},
author = {A. Hiras and A. Gadari and A. Jayaraman and A. S. Mankumare and A. Mynampati and J. K. Chhablani and S. C. Bollepalli and K. K. Vupparaboina},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.14.26363079},
url = {https://www.medrxiv.org/content/10.64898/2026.09.14.26363079v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Task-Specific Quality Gating for Retinal Optical Coherence Tomography B-Scans: Learned Representations Over Scalar Metrics in Choroid Segmentation
AU - A. Hiras
AU - A. Gadari
AU - A. Jayaraman
AU - A. S. Mankumare
AU - A. Mynampati
AU - J. K. Chhablani
AU - S. C. Bollepalli
AU - K. K. Vupparaboina
PY - 2026
DA - 2026/09/14
PB - medRxiv
DO - 10.64898/2026.09.14.26363079
UR - https://www.medrxiv.org/content/10.64898/2026.09.14.26363079v1
AB - Automated segmentation of Optical Coherence Tomography (OCT) images is a critical component of structural biomarker extraction for retinal diagnostics. Deep learning models achieve state-of-the-art performance on controlled datasets, yet exhibit unpredictable failures on real-world data. Current quality gates rely on device-reported scan quality scores, which have been shown to be unreliable predictors of segmentation performance. We define scan quality in a task-specific sense that is, whether a given B-scan will yield a reliable segmentation from a particular trained model. Under this definition, we perform a systematic evaluation of No-Reference Image Quality Assessment (NR-IQA) metrics, general-purpose and domain-specific pretrained representations as alternative quality gates. To this end, we use choroid segmentation as the prototype task, with a dataset of 6,076 OCT B-scans from 80 subjects. These quality gate candidates are evaluated at three levels: scalar metrics (BRISQUE, NIQE, PIQE, SNR, PSNR), supervised linear probing, and unsupervised partitioning (K-Means) of the feature vectors and the learned representations. All scalar NR-IQA metrics proved inadequate (|r| < 0.20). General-purpose ImageNet-based pretrained representations (EfficientNet-b0, ResNet-50, ViT-B/16) improve upon NR-IQA, achieving ROC-AUC up to 0.77, indicating that learned representations are better suited to task-specific quality gating than hand-crafted scalar statistics. Retinal foundation models (FMs) further close the gap: RETFound (OCT-specific FM) achieves ROC-AUC {approx} 0.81. Unsupervised K-Means partitioning indicates that general-purpose ImageNet-pretrained embeddings, despite carrying a linearly decodable quality signal, do not reliably organize scans by quality geometrically, whereas the retinal FMs produce quality-aligned clusters that exceed a patient-level permutation null, suggesting that domain-specific pretraining provides additional, complementary benefit on top of general-purpose learned representations.
ER -