Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
Automated Extraction of Visual Fields Using FOSS OCR Engines from Scanned Report Images
Author Affiliations & Notes
  • LOK HIN LEE
    Vanderbilt University Medical Center, Nashville, Tennessee, United States
  • Jibril Hirbo
    Vanderbilt University, Nashville, Tennessee, United States
  • Karen M Joos
    Vanderbilt University Medical Center, Nashville, Tennessee, United States
  • Eric N Brown
    Vanderbilt University Medical Center, Nashville, Tennessee, United States
  • Footnotes
    Commercial Relationships   LOK HIN LEE None; Jibril Hirbo None; Karen Joos None; Eric Brown None
  • Footnotes
    Support  Funded by an unrestricted departmental grant to the Vanderbilt Eye Institute by Research to Prevent Blindness INC New York and a grant from the Croucher Foundation
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 5945. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      LOK HIN LEE, Jibril Hirbo, Karen M Joos, Eric N Brown; Automated Extraction of Visual Fields Using FOSS OCR Engines from Scanned Report Images. Invest. Ophthalmol. Vis. Sci. 2024;65(7):5945.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Faxed and scanned visual field (VF) reports are ubiquitous in clinical settings due to the lack of interoperability between electronic health records (EHR). Aiming to reduce clinician workload, we developed and validated a machine learning-based optical character recognition (OCR) system to automate the extraction of VF and VF measures from scanned images and PDFs.

Methods : Humphrey 24-2 SITA Standard VF reports were extracted from the EHR for 472 glaucoma patients with multiple visual field reports from 2015 to 2023, comprising 1806 Zeiss Humphrey Field Analyzer 3 (HFA3) reports and 168 earlier from HFA2.

Using OpenCV, a free and open-source software (FOSS) for image analysis, we preprocessed these images to detect VF reports. We then used image morphological transformations with Sobel filters to detect the locations of key textual information from this report including patient identifiers, VF thresholds and VF statistics. We developed two OCR systems using two FOSS OCR engines: Tesseract and PaddleOCR to extract textual information from detected locations as reported by OpenCV (Figure 1). Tesseract is based on a machine-learning long short-term memory (LSTM) and support vector model ensemble, whereas PaddleOCR is based on a residual attention based convolutional neural network backbone. Their character recognition accuracy was compared against human recognition using a random subset of 50 VF reports from both HFA2 and HFA3 reports.

Results : Tesseract showed better accuracy on the OpenCV post-processed HFA3 reports (98% ± 2%) than HFA2 reports (95% ± 2%) on VFs and VF statistics. PaddleOCR performed better on HFA2 reports (98% ± 1%) than HFA3 reports (96% ± 2%). PaddleOCR and Tesseract performed similarly on patient information (96% ± 2% vs. 95% ± 1%). We found that the cause of most errors in OCR was due to font kerning and character or axis overlapping on VFs (Figure 2).

Conclusions : Automated FOSS OCR engines effectively convert scanned VF reports to structured textual data, enhancing clinical workflow and research capabilities. This technology can aid in clinical trend analysis by facilitating access to previously hard-to-extract data, representing an advancement in the management and analysis of visual field information in healthcare settings.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

 

Figure 1: Overall pipeline for automated VF extraction

Figure 1: Overall pipeline for automated VF extraction

 

Figure 2: Examples from HFA2 and HFA3 of mis-identified characters due to axis overlap or font kerning

Figure 2: Examples from HFA2 and HFA3 of mis-identified characters due to axis overlap or font kerning

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×