However, no method has been developed to accurately predict the VF sensitivity from OCT-measured retinal layer thicknesses thus far. Because glaucoma is characterized by irreversible GCC loss, abnormal VF sensitivity might be predicted from the GCC thickness 15. The current approach to evaluate GCC thickness is by spectral domain optical coherence tomography (SD-OCT) that measures the thicknesses of the ganglion cell and inner plexiform layers of the GCC 7, 8, 9, 10, 11, 12, 13, 14. Importantly, measurable structural alterations, such as ganglion cell complex (GCC) loss often precede detectable VF damage 3, 4, 5, 6. The scope of the visual field (VF) is the principal measurement made when diagnosing and monitoring glaucoma progression. Here, vision loss is progressive and irreversible and ultimately impacts on the quality-of-life of affected patients 2. Glaucoma is one of the leading causes of blindness worldwide 1. In conclusion, HFA 10-2 test results can be predicted with a OCT images using a trained CNN model with adjustment using HFA 24-2 test. These values reduced to 5.5 dB on average, when the data were corrected using the HFA 24-2 test. Mean absolute error derived from the CNN models ranged between 9.4 and 9.5 B. Then, the predicted TD values were corrected using the TD values of the innermost four points from the HFA 24-2 test. During CNN model training, the total deviation (TD) values of the HFA 10-2 test point were predicted from the combined OCT-measured macular retinal layers’ thicknesses. All eyes were analyzed by the HFA 10-2 test and OCT eyes in the testing dataset were additionally analyzed by the HFA 24-2 test. The testing dataset included 105 eyes from 72 glaucoma patients. The training dataset included 558 eyes from 312 glaucoma patients and 90 eyes from 46 normal subjects. We aimed to develop a model to predict visual field (VF) in the central 10 degrees in patients with glaucoma, by training a convolutional neural network (CNN) with optical coherence tomography (OCT) images and adjusting the values with Humphrey Field Analyzer (HFA) 24–2 test.
0 kommentar(er)
