Spaide T, Wu Y, Yanagihara RT, Feng S, Ghabra O, Yi JS, Chen PP, Moses F, Lee AY, Wen JC. Using Deep Learning to Automate Goldmann Applanation Tonometry Readings.
Ophthalmology 2020;
127:1498-1506. [PMID:
32344074 DOI:
10.1016/j.ophtha.2020.04.033]
[Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/11/2020] [Revised: 04/16/2020] [Accepted: 04/20/2020] [Indexed: 11/18/2022] Open
Abstract
PURPOSE
To develop an objective and automated method for measuring intraocular pressure using deep learning and fixed-force Goldmann applanation tonometry (GAT) techniques.
DESIGN
Prospective cross-sectional study.
PARTICIPANTS
Patients from an academic glaucoma practice.
METHODS
Intraocular pressure was estimated by analyzing videos recorded using a standard slit-lamp microscope and fixed-force GAT. Video frames were labeled to identify the outline of the reference tonometer and the applanation mires. A deep learning model was trained to localize and segment the tonometer and mires. Intraocular pressure values were calculated from the deep learning-predicted tonometer and mire diameters using the Imbert-Fick formula. A separate test set was collected prospectively in which standard and automated GAT measurements were collected in random order by 2 independent masked observers to assess the deep learning model as well as interobserver variability.
MAIN OUTCOME MEASURES
Intraocular pressure measurements between standard and automated methods were compared.
RESULTS
Two hundred sixty-three eyes of 135 patients were included in the training and validation videos. For the test set, 50 eyes from 25 participants were included. Each eye was measured by 2 observers, resulting in 100 videos. Within the test set, the mean difference between automated and standard GAT results was -0.9 mmHg (95% limits of agreement [LoA], -5.4 to 3.6 mmHg). Mean difference between the 2 observers using standard GAT was 0.09 mmHg (LoA,-3.8 to 4.0 mmHg). Mean difference between the 2 observers using automated GAT videos was -0.3 mmHg (LoA, -4.1 to 3.5 mmHg). The coefficients of repeatability for automated and standard GAT were 3.8 and 3.9 mmHg, respectively. The bias for even-numbered measurements was reduced when using automated GAT.
CONCLUSIONS
Preliminary measurements using deep learning to automate GAT demonstrate results comparable with those of standard GAT. Automated GAT has the potential to improve on our current GAT measurement standards significantly by reducing bias and improving repeatability. In addition, ocular pulse amplitudes could be observed using this technique.
Collapse