Stratified Multisource Optical Coherence Tomography Integration and Cross-Pathology Validation Framework for Automated Retinal Diagnostics

This study presents a clinical utility-driven machine learning framework for retinal Optical Coherence Tomography classification, addressing challenges posed by manual interpretation variability and dataset heterogeneity. The methodology integrates biomimetic data partitioning, deep biomarker extrac...

Full description

Saved in:
Bibliographic Details
Main Authors: Michael Sher, Riah Sharma, David Remyes, Daniel Nasef, Demarcus Nasef, Milan Toma
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/9/4985
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849312910463991808
author Michael Sher
Riah Sharma
David Remyes
Daniel Nasef
Demarcus Nasef
Milan Toma
author_facet Michael Sher
Riah Sharma
David Remyes
Daniel Nasef
Demarcus Nasef
Milan Toma
author_sort Michael Sher
collection DOAJ
description This study presents a clinical utility-driven machine learning framework for retinal Optical Coherence Tomography classification, addressing challenges posed by manual interpretation variability and dataset heterogeneity. The methodology integrates biomimetic data partitioning, deep biomarker extraction via pretrained VGG16 networks, and automated model selection optimized for clinical decision-making. Stratified data curation preserved pathological distributions across training, validation, and testing subsets, while SMOTE optimization mitigated class imbalance. Cross-pathology testing evaluated generalizability on anatomically distinct retinal conditions excluded from training, assessing the framework’s robustness to unseen pathologies. Clinical utility metrics prioritized alignment with ophthalmological imperatives, emphasizing negative predictive value to minimize false negatives and enhance diagnostic reliability. The framework advances AI-driven Optical Coherence Tomography diagnostics by harmonizing computational performance with patient-centered outcomes, enabling standardized disease detection across diverse clinical datasets through robust feature generalization.
format Article
id doaj-art-abb39ee2f26e4f53be98f09f23efc8a0
institution Kabale University
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-abb39ee2f26e4f53be98f09f23efc8a02025-08-20T03:52:56ZengMDPI AGApplied Sciences2076-34172025-04-01159498510.3390/app15094985Stratified Multisource Optical Coherence Tomography Integration and Cross-Pathology Validation Framework for Automated Retinal DiagnosticsMichael Sher0Riah Sharma1David Remyes2Daniel Nasef3Demarcus Nasef4Milan Toma5Department of Osteopathic Manipulative Medicine, College of Osteopathic Medicine, New York Institute of Technology, Old Westbury, Nassau County, Long Island, NY 11568, USADepartment of Osteopathic Manipulative Medicine, College of Osteopathic Medicine, New York Institute of Technology, Old Westbury, Nassau County, Long Island, NY 11568, USADepartment of Osteopathic Manipulative Medicine, College of Osteopathic Medicine, New York Institute of Technology, Old Westbury, Nassau County, Long Island, NY 11568, USADepartment of Osteopathic Manipulative Medicine, College of Osteopathic Medicine, New York Institute of Technology, Old Westbury, Nassau County, Long Island, NY 11568, USADepartment of Osteopathic Manipulative Medicine, College of Osteopathic Medicine, New York Institute of Technology, Old Westbury, Nassau County, Long Island, NY 11568, USADepartment of Osteopathic Manipulative Medicine, College of Osteopathic Medicine, New York Institute of Technology, Old Westbury, Nassau County, Long Island, NY 11568, USAThis study presents a clinical utility-driven machine learning framework for retinal Optical Coherence Tomography classification, addressing challenges posed by manual interpretation variability and dataset heterogeneity. The methodology integrates biomimetic data partitioning, deep biomarker extraction via pretrained VGG16 networks, and automated model selection optimized for clinical decision-making. Stratified data curation preserved pathological distributions across training, validation, and testing subsets, while SMOTE optimization mitigated class imbalance. Cross-pathology testing evaluated generalizability on anatomically distinct retinal conditions excluded from training, assessing the framework’s robustness to unseen pathologies. Clinical utility metrics prioritized alignment with ophthalmological imperatives, emphasizing negative predictive value to minimize false negatives and enhance diagnostic reliability. The framework advances AI-driven Optical Coherence Tomography diagnostics by harmonizing computational performance with patient-centered outcomes, enabling standardized disease detection across diverse clinical datasets through robust feature generalization.https://www.mdpi.com/2076-3417/15/9/4985retinal OCT classificationmachine learningclinical utilitySMOTE optimizationlogistic regression
spellingShingle Michael Sher
Riah Sharma
David Remyes
Daniel Nasef
Demarcus Nasef
Milan Toma
Stratified Multisource Optical Coherence Tomography Integration and Cross-Pathology Validation Framework for Automated Retinal Diagnostics
Applied Sciences
retinal OCT classification
machine learning
clinical utility
SMOTE optimization
logistic regression
title Stratified Multisource Optical Coherence Tomography Integration and Cross-Pathology Validation Framework for Automated Retinal Diagnostics
title_full Stratified Multisource Optical Coherence Tomography Integration and Cross-Pathology Validation Framework for Automated Retinal Diagnostics
title_fullStr Stratified Multisource Optical Coherence Tomography Integration and Cross-Pathology Validation Framework for Automated Retinal Diagnostics
title_full_unstemmed Stratified Multisource Optical Coherence Tomography Integration and Cross-Pathology Validation Framework for Automated Retinal Diagnostics
title_short Stratified Multisource Optical Coherence Tomography Integration and Cross-Pathology Validation Framework for Automated Retinal Diagnostics
title_sort stratified multisource optical coherence tomography integration and cross pathology validation framework for automated retinal diagnostics
topic retinal OCT classification
machine learning
clinical utility
SMOTE optimization
logistic regression
url https://www.mdpi.com/2076-3417/15/9/4985
work_keys_str_mv AT michaelsher stratifiedmultisourceopticalcoherencetomographyintegrationandcrosspathologyvalidationframeworkforautomatedretinaldiagnostics
AT riahsharma stratifiedmultisourceopticalcoherencetomographyintegrationandcrosspathologyvalidationframeworkforautomatedretinaldiagnostics
AT davidremyes stratifiedmultisourceopticalcoherencetomographyintegrationandcrosspathologyvalidationframeworkforautomatedretinaldiagnostics
AT danielnasef stratifiedmultisourceopticalcoherencetomographyintegrationandcrosspathologyvalidationframeworkforautomatedretinaldiagnostics
AT demarcusnasef stratifiedmultisourceopticalcoherencetomographyintegrationandcrosspathologyvalidationframeworkforautomatedretinaldiagnostics
AT milantoma stratifiedmultisourceopticalcoherencetomographyintegrationandcrosspathologyvalidationframeworkforautomatedretinaldiagnostics