AI-Guided Radiomics for Spectral-Domain OCT Characterization of Acquired Vitelliform Lesions: A Pilot Study
- 1Department of Neurosciences, Reproductive Sciences and Dentistry, University of Naples “Federico II”, 80138 Napoli, Italy
- 2Department of Medicine, Surgery and Dentistry, University of Salerno, 84081 Baronissi, Italy
Abstract
Objective: To evaluate the ability of artificial intelligence (AI)-driven radiomics applied to structural OCT to characterize hypo-reflective subretinal spaces in acquired vitelliform lesions (aVLs), to distinguish reabsorbed material from subretinal fluid, improving diagnostic precision. Methods: In this retrospective monocentric study, patients with aVLs were compared with a control group of acute central serous chorioretinopathy (CSCR) to provide reference OCT patterns for subretinal fluid. All participants underwent multimodal imaging. OCT scans were manually segmented. Radiomic features were extracted using a standardized pipeline, including image preprocessing, robustness assessment, variance and correlation filtering, and feature selection with a WEKA subset evaluator. A ridge-based Logistic Regression classifier was trained on 75% of the dataset and tested on the remaining 25%. Model performance was assessed using accuracy metrics, ROC AUC, and precision–recall curves. Results: A total of 520 radiomics features were extracted, of which nine were selected for training. The classifier achieved an accuracy of 86.5% in the training set (AUC 0.89; PRC 0.86) and 80% in the independent test set, with excellent AUC (0.92) and PRC (0.92). The negative predictive value reached 92%, indicating a high ability to correctly classify the aVL-associated hypo-reflective phenotype. The positive predictive value was 67%. Conclusions: AI-based radiomics demonstrated promising performance in discriminating, on structural OCT, between hypo-reflective subretinal spaces associated with the resorptive phase of aVLs and subretinal fluid. These preliminary findings support the feasibility of quantitative radiomic characterization of these two OCT phenotypes. Further studies are required to determine whether this approach may also be useful in identifying neovascular complications.
Related
- Multimodal preoperative risk stratification of pancreatic mass lesions using clinical variables, imaging radiomics and plasma cfDNA methylation: protocol for an ambispective multicentre diagnostic prediction model study
- Whole-phase DCE-MRI radiomics for differentiating benign and malignant BI-RADS 4 breast lesions: a comparative machine learning study
- Prediction of Claudin18.2 expression in gastric adenocarcinoma by habitat radiomics based on spectral CT
- Multiscale Spatial Characterization of Glioma MRI with MUSE and Radiomics
- Characterization of pulmonary bacterial composition in community-acquired pneumonia depending on sampling methods
BibTeX
@article{concilio2026aiguided,
title = {{AI-Guided Radiomics for Spectral-Domain OCT Characterization of Acquired Vitelliform Lesions: A Pilot Study}},
author = {Marina Concilio and Gilda Cennamo and Renato Cuocolo and Clementina Miele and Michele Rinaldi and Ciro Costagliola},
journal = {Journal of Clinical Medicine},
year = {2026},
month = oct,
doi = {10.3390/jcm15218269},
url = {https://www.mdpi.com/2077-0383/15/21/8269},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - AI-Guided Radiomics for Spectral-Domain OCT Characterization of Acquired Vitelliform Lesions: A Pilot Study
AU - Marina Concilio
AU - Gilda Cennamo
AU - Renato Cuocolo
AU - Clementina Miele
AU - Michele Rinaldi
AU - Ciro Costagliola
PY - 2026
DA - 2026/10/23
JO - Journal of Clinical Medicine
DO - 10.3390/jcm15218269
UR - https://www.mdpi.com/2077-0383/15/21/8269
AB - Objective: To evaluate the ability of artificial intelligence (AI)-driven radiomics applied to structural OCT to characterize hypo-reflective subretinal spaces in acquired vitelliform lesions (aVLs), to distinguish reabsorbed material from subretinal fluid, improving diagnostic precision. Methods: In this retrospective monocentric study, patients with aVLs were compared with a control group of acute central serous chorioretinopathy (CSCR) to provide reference OCT patterns for subretinal fluid. All participants underwent multimodal imaging. OCT scans were manually segmented. Radiomic features were extracted using a standardized pipeline, including image preprocessing, robustness assessment, variance and correlation filtering, and feature selection with a WEKA subset evaluator. A ridge-based Logistic Regression classifier was trained on 75% of the dataset and tested on the remaining 25%. Model performance was assessed using accuracy metrics, ROC AUC, and precision–recall curves. Results: A total of 520 radiomics features were extracted, of which nine were selected for training. The classifier achieved an accuracy of 86.5% in the training set (AUC 0.89; PRC 0.86) and 80% in the independent test set, with excellent AUC (0.92) and PRC (0.92). The negative predictive value reached 92%, indicating a high ability to correctly classify the aVL-associated hypo-reflective phenotype. The positive predictive value was 67%. Conclusions: AI-based radiomics demonstrated promising performance in discriminating, on structural OCT, between hypo-reflective subretinal spaces associated with the resorptive phase of aVLs and subretinal fluid. These preliminary findings support the feasibility of quantitative radiomic characterization of these two OCT phenotypes. Further studies are required to determine whether this approach may also be useful in identifying neovascular complications.
SN - 2077-0383
ER -