Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Apr 29:8:625487.
doi: 10.3389/fmed.2021.625487. eCollection 2021.

Development and Validation of Automated Visual Field Report Extraction Platform Using Computer Vision Tools

Murtaza Saifee  1 , Jian Wu  1   2 , Yingna Liu  1 , Ping Ma  1   3 , Jutima Patlidanon  1   4 , Yinxi Yu  5 , Gui-Shuang Ying  5 , Ying Han  1   6
Affiliations

Development and Validation of Automated Visual Field Report Extraction Platform Using Computer Vision Tools

Murtaza Saifee et al. Front Med (Lausanne). .

Abstract

Purpose: To introduce and validate hvf_extraction_script, an open-source software script for the automated extraction and structuring of metadata, value plot data, and percentile plot data from Humphrey visual field (HVF) report images. Methods: Validation was performed on 90 HVF reports over three different report layouts, including a total of 1,530 metadata fields, 15,536 value plot data points, and 10,210 percentile data points, between the computer script and four human extractors, compared against DICOM reference data. Computer extraction and human extraction were compared on extraction time as well as accuracy of extraction for metadata, value plot data, and percentile plot data. Results: Computer extraction required 4.9-8.9 s per report, compared to the 6.5-19 min required by human extractors, representing a more than 40-fold difference in extraction speed. Computer metadata extraction error rate varied from an aggregate 1.2-3.5%, compared to 0.2-9.2% for human metadata extraction across all layouts. Computer value data point extraction had an aggregate error rate of 0.9% for version 1, <0.01% in version 2, and 0.15% in version 3, compared to 0.8-9.2% aggregate error rate for human extraction. Computer percentile data point extraction similarly had very low error rates, with no errors occurring in version 1 and 2, and 0.06% error rate in version 3, compared to 0.06-12.2% error rate for human extraction. Conclusions: This study introduces and validates hvf_extraction_script, an open-source tool for fast, accurate, automated data extraction of HVF reports to facilitate analysis of large-volume HVF datasets, and demonstrates the value of image processing tools in facilitating faster and cheaper large-volume data extraction in research settings.

Keywords: computer vision and image processing; glaucoma; neuroophthalmogy; optical character reader; visual field.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Block diagram of extraction software. An input visual field report identifies areas of metadata, value plots and percentile plots, processes and extracts data, and outputs structured data.
Figure 2
Figure 2
Example output text file. Example output text file corresponding to the image report seen in Figure 3C.
Figure 3
Figure 3
Humphrey Visual Field report layout types. (A) Version 1 layout. (B) Version 2 layout. (C) Version 3 layout.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Armstrong GW, Lorch AC. A(eye): a review of current applications of artificial intelligence and machine learning in ophthalmology. Int Ophthalmol Clin. (2020) 60:57-71. 10.1097/IIO.0000000000000298 - DOI - PubMed
    1. Carl Zeiss Meditec AG. DICOM Conformance Statement - Forum Version 3.2. Available online at: https://www.zeiss.com/content/dam/Meditec/downloads/pdf/DICOM/DICOM_Conf... (accessed November 3, 2020).
    1. Norman DA. Design rules based on analyses of human error. Commun ACM. (1983) 26:254-8. 10.1145/2163.358092 - DOI
    1. Soboczenski F. The Effect of Interface Elements on Transcription Tasks to Reduce Number-Entry Errors. (2014). Availble online at: http://etheses.whiterose.ac.uk/11775/1/thesis.pdf (accessed November 3, 2020).
    1. Thimbleby H, Cairns P. Reducing number entry errors: solving a widespread, serious problem. J R Soc Interface. (2010) 7:1429-39. 10.1098/rsif.2010.0112 - DOI - PMC - PubMed