Most Read Articles
4 days ago
A recent study reports a mean growth rate of proximal aorta of about 0.1 mm/year in hypertensive patients with known aortic dilatation. In addition, those with increased rather than normal aortic z score have slower dilatation over time.
Tristan Manalac, 3 days ago
The coronavirus disease 2019 (COVID-19) appears to be more dangerous among cancer patients, who tend suffer more severe complications and faster disease progression, according to a new study.
Roshini Claire Anthony, 2 days ago

Among patients with nonvalvular atrial fibrillation (AF), treatment with apixaban was associated with a lower rate of ischaemic stroke, systemic embolism, and major bleeding compared with rivaroxaban, according to a large study assessing patients in routine care.

21 hours ago
Exposure to sunlight appears to increase the risk of vulvovaginal candidiasis (VVC) development, reveals a recent study in an African population.

Deep learning predicts glaucomatous visual field damage from OCT optic nerve head images

11 Mar 2020

Deep learning models accurately identify eyes with glaucomatous visual field damage (GVFD) and predict functional loss severity from spectral domain optical coherence tomography (SD OCT) images, reports a study.

These deep learning approaches can help clinicians more effectively individualize the frequency of visual field testing to the individual patient, the authors said.

In this evaluation of a diagnostic technology, a total of 9,765 visual field SD OCT pairs were collected from 1,194 participants with and without GVFD (1,909 eyes).

SD OCT retinal nerve fibre layer (RNFL) thickness maps, RNFL en-face images and confocal scanning laser ophthalmoscopy images were used to train the deep learning models in identifying eyes with GVFD and predicting quantitative visual field mean deviation, pattern standard deviation and mean visual field sectoral pattern deviation from SD OCT data.

Deep learning models based on RNFL en-face images achieved an area under the curve (AUC) of 0.88 for identifying eyes with GVFD and 0.82 for significantly detecting mild GVFD (p<0.001), which was better than the use of mean RNFL thickness measurements (AUC, 0.82 and 0.73, respectively), in the independent test dataset.

Moreover, deep learning models were better than standard RNFL thickness measurements in predicting all quantitative visual field metrics.

In predicting mean deviation, deep learning models based on RNFL en-face images achieved an R2 of 0.70 and mean absolute error (MAE) of 2.5 decibels (dB), while the corresponding values for RNFL thickness measurements were 0.45 and 3.7 dB.

In predicting mean visual field sectoral pattern deviation, deep learning models achieved high accuracy in the inferior (R2, 0.60) and superior nasal (R2, 0.67) sectors, moderate accuracy in inferior (R2, 0.26) and superior (R2, 0.35) sectors, and lower accuracy in the central (R2, 0.15) and temporal (R2, 0.12) sectors.

Digital Edition
Asia's trusted medical magazine for healthcare professionals. Get your MIMS Doctor - Malaysia digital copy today!
Sign In To Download
Editor's Recommendations
Most Read Articles
4 days ago
A recent study reports a mean growth rate of proximal aorta of about 0.1 mm/year in hypertensive patients with known aortic dilatation. In addition, those with increased rather than normal aortic z score have slower dilatation over time.
Tristan Manalac, 3 days ago
The coronavirus disease 2019 (COVID-19) appears to be more dangerous among cancer patients, who tend suffer more severe complications and faster disease progression, according to a new study.
Roshini Claire Anthony, 2 days ago

Among patients with nonvalvular atrial fibrillation (AF), treatment with apixaban was associated with a lower rate of ischaemic stroke, systemic embolism, and major bleeding compared with rivaroxaban, according to a large study assessing patients in routine care.

21 hours ago
Exposure to sunlight appears to increase the risk of vulvovaginal candidiasis (VVC) development, reveals a recent study in an African population.