Oral squamous cell carcinoma diagnosis with time and frequency domain features from optical coherence tomography A-scan signals

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Binary classification accuracy: 88.47%, Multi-label classification accuracy: 82.48%

• Primary Outcome: Diagnostic accuracy for oral squamous cell carcinoma classification using OCT A-scan features

• Nnt Or Sensitivity: AUC: 0.9539 (binary), 0.964 (multi-label); F1 scores: 0.8878 (binary), 0.8201 (multi-label)

• Confidence Interval: Not reported

Clinical Application

Limited by requirement for specialized OCT equipment and machine learning infrastructure; ex vivo validation needs in vivo confirmation Could complement existing oral cancer screening programs; would require TGA approval for clinical use; potential integration with specialist oral medicine services in major hospitals Patients undergoing oral cancer screening or diagnostic workup, particularly in specialist oral medicine or maxillofacial surgery settings

Abstract

Optical coherence tomography (OCT) is extremely useful in the screening and detection of oral cancers. But various challenges, such as its subjectivity, operator dependence in interpretation, and lack of quantitative outcomes, have been delaying its adoption in clinical decision-making. The objective of this research is to quantify various A-scan features embedded in the OCT signal through advanced signal processing techniques and machine learning algorithms.Ex vivoimaging of biopsied oral tissues (normal mucosa, carcinomain situ(CIS), well-differentiated, and poorly differentiated oral squamous cell carcinoma) was performed using a spectral domain OCT system. Our A-scan dataset consisted of representative 1D signals obtained from different regions of the tissue bed. A set of 12 time- and 8 frequency-domain features were computed on each A-scan, and ten machine learning models were evaluated for binary and multi-label classification. LightGBM achieved the highest performance in both binary (accuracy: 0.8847,F1: 0.8878, AUC: 0.9539) and multi-label classification (accuracy: 0.8248,F1: 0.8201, AUC: 0.964). LightGBM was selected as the final model based on its superior and consistent performance across both classification paradigms. Our proof-of-concept feasibility study demonstrates good accuracy for differentiating oral mucosal tissues, highlighting the biomarker signature of A-scans.

References

1. 1.Panta, P., Mirza, S., & John, R. (2026). Oral squamous cell carcinoma diagnosis with time and frequency domain features from optical coherence tomography A-scan signals. Biomedical Physics & Engineering Express. https://doi.org/10.1088/2057-1976/ae6aa1