OCTess: An Optical Character Recognition Algorithm for Automated Data Extraction of Spectral Domain Optical Coherence Tomography Reports

Abstract

Purpose: Manual extraction of spectral domain optical coherence tomography (SD-OCT) reports is time- and resource-intensive. This study aimed to develop an optical character recognition (OCR) algorithm for automated data extraction from Cirrus SD-OCT macular cube reports. Methods: SD-OCT monocular macular cube reports (n=675) were randomly selected from a single-center database of patients from 2020-2023. Image processing and bounding box operations were performed, and Tesseract (an OCR library) was used to develop the algorithm, OCTess. The algorithm was validated using a separate test dataset. Results: The long short-term memory (LSTM) deep learning version of Tesseract achieved the best performance. After re-verifying all discrepancies between human and algorithmic data extractions, OCTess achieved accuracies of 100.00% and 99.98% in the training (n=125) and testing (n=550) datasets, while the human error rate was 1.11% (98.89% accuracy) and 0.49% (99.51% accuracy) in each, respectively. OCTess extracted data in 3.1 seconds, compared to 94.3 seconds for human evaluators. Conclusion: We developed an OCR and machine learning algorithm that extracts SD-OCT data with near-perfect accuracy, which is more accurate and efficient compared to a human. This algorithm can be used for efficient construction of large-scale SD-OCT datasets for researchers and clinicians.