3D gonioscopy detects eyes with suspected glaucoma

The 3-dimensional (3D) deep learning-based automated digital gonioscopy system (DGS) effectively identifies eyes with suspected primary angle-closure glaucoma (PACG), demonstrating its potential for wide use in the primary eye care community for screening of patients at high risk of developing PACG, suggests a study.

This cross-sectional, multicentre study was conducted to develop and evaluate the performance of 3D DGS in detecting two major characteristics in eyes with suspected PACG: narrow iridocorneal angles (static gonioscopy, Task I) and peripheral anterior synechiae (PAS) (dynamic gonioscopy, Task II) on optical coherence tomography scans.

The investigators analysed 1.112 million images of 8,694 volume scans (2,294 patients) from three centres (Task I, training/internal validation/external testing: 4,515, 1,101, and 2,222 volume scans, respectively; Task II, training/internal validation/external testing: 378, 376, and 102 volume scans, respectively).

“For Task I, a narrow angle was defined as an eye in which the posterior pigmented trabecular meshwork was not visible in more than 180° without indentation in the primary position captured in the dark room from the scans,” the investigators said. “For Task II, PAS was defined as the adhesion of the iris to the trabecular meshwork.”

Of the patients, 29.4 percent had a narrow angle in Task I. The area under the curve (AUC), sensitivity, and specificity of 3D DGS on the external testing datasets were 0.943 (0.933–0.953), 0.867 (0.838–0.895), and 0.878 (0.859–0.896), respectively.

In Task II, 13.8 percent of patients had PAS. The AUC, sensitivity, and specificity of 3D DGS were 0.902 (0.818–0.985), 0.900 (0.714–1.000), and 0.890 (0.841–0.938), respectively, on the external testing set at quadrant level following normal clinical practice, and 0.885 (0.836–0.933), 0.912 (0.816–1.000), and 0.700 (0.660–0.741), respectively, on the external testing set at clock-hour level.