OCT Radiomics and Machine Learning Enable Accurate Detection of Forme Fruste Keratoconus.
To evaluate the diagnostic performance of a radiomics-based machine learning approach applied to corneal optical coherence tomography (OCT) images for detecting forme fruste keratoconus (FFKC).
Evaluation of machine learning diagnostic algorithms.
OCT images from 307 eyes (234 normal, 73 FFKC) were acquired along eight meridians (M1-M8). All images underwent preprocessing before texture-based radiomics feature extraction. Three machine learning classifiers-Random Forest, C5.0, and XGBoost-were trained using a feature subset selected by Recursive Feature Elimination (RFE). Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy.
A total of 3,752 features were extracted per eye, of which 41 were selected for model training. All three models demonstrated strong diagnostic performance in the test set (AUCs > 0.92), with no significant differences between models (p > 0.05). The XGBoost model achieved the highest performance (AUC = 0.93, 95% CI: 0.829-1.0, sensitivity 0.857, specificity = 0.978, accuracy = 0.950). Among the top 10 XGBoost features ranked by importance, a preferred meridional distribution was observed, with most features concentrated along M1-M3, corresponding to the inferotemporal corneal region.
Radiomics analysis of corneal OCT images combined with machine learning enables accurate FFKC detection using a single imaging device, providing diagnostic information beyond conventional morphological assessment and suggesting a potential imaging biomarker for early keratoconus screening.
Radiomics analysis of optical coherence tomography images captures microscopic corneal texture features that complement routine clinical examinations. Integrating these features into machine learning models enables accurate identification of forme fruste keratoconus. This single device, noninvasive approach supports earlier detection and introduces a new perspective for characterizing subclinical corneal ectasia based on corneal microstructural texture.
Evaluation of machine learning diagnostic algorithms.
OCT images from 307 eyes (234 normal, 73 FFKC) were acquired along eight meridians (M1-M8). All images underwent preprocessing before texture-based radiomics feature extraction. Three machine learning classifiers-Random Forest, C5.0, and XGBoost-were trained using a feature subset selected by Recursive Feature Elimination (RFE). Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy.
A total of 3,752 features were extracted per eye, of which 41 were selected for model training. All three models demonstrated strong diagnostic performance in the test set (AUCs > 0.92), with no significant differences between models (p > 0.05). The XGBoost model achieved the highest performance (AUC = 0.93, 95% CI: 0.829-1.0, sensitivity 0.857, specificity = 0.978, accuracy = 0.950). Among the top 10 XGBoost features ranked by importance, a preferred meridional distribution was observed, with most features concentrated along M1-M3, corresponding to the inferotemporal corneal region.
Radiomics analysis of corneal OCT images combined with machine learning enables accurate FFKC detection using a single imaging device, providing diagnostic information beyond conventional morphological assessment and suggesting a potential imaging biomarker for early keratoconus screening.
Radiomics analysis of optical coherence tomography images captures microscopic corneal texture features that complement routine clinical examinations. Integrating these features into machine learning models enables accurate identification of forme fruste keratoconus. This single device, noninvasive approach supports earlier detection and introduces a new perspective for characterizing subclinical corneal ectasia based on corneal microstructural texture.