Deep Learning Estimation of 10-2 Visual Field Map Based on Macular Optical Coherence Tomography Angiography Measurements.

PURPOSE: To develop deep learning (DL) models estimating the central visual field (VF) from optical coherence tomography angiography (OCTA) vessel density (VD) measurements. DESIGN: Development and validation of a deep learning model. METHODS: A total of 1051 10-2 VF OCTA pairs from healthy, glaucoma suspects, and glaucoma eyes were included. DL models were trained on en face macula VD images from OCTA to estimate 10-2 mean deviation (MD), pattern standard deviation (PSD), 68 total deviation (TD) and pattern deviation (PD) values and compared with a linear regression (LR) model with the same input. Accuracy of the models was evaluated by calculating the average mean absolute error (MAE) and the R2 (squared Pearson correlation coefficients) of the estimated and actual VF values. RESULTS: DL models predicting 10-2 MD achieved R2 of 0.85 (95% confidence interval [CI], 74-0.92) for 10-2 MD and MAEs of 1.76 dB (95% CI, 1.39-2.17 dB) for MD. This was significantly better than mean linear estimates for 10-2 MD. The DL model outperformed the LR model for the estimation of pointwise TD values with an average MAE of 2.48 dB (95% CI, 1.99-3.02) and R2 of 0.69 (95% CI, 0.57-0.76) over all test points. The DL model outperformed the LR model for the estimation of all sectors. CONCLUSIONS: DL models enable the estimation of VF loss from OCTA images with high accuracy. Applying DL to the OCTA images may enhance clinical decision making. It also may improve individualized patient care and risk stratification of patients who are at risk for central VF damage.

Direct comparison of the effects of nebulized nitroprusside versus inhaled nitric oxide on pulmonary and systemic hemodynamics during hypoxia-induced pulmonary hypertension in piglets.

OBJECTIVE: To test the hypothesis that nebulized nitroprusside and inhaled nitric oxide would not differ in producing selective pulmonary vasodilation during hypoxia-induced pulmonary hypertension in piglets. SETTING: University laboratory. SUBJECTS: Five piglets. INTERVENTIONS: Piglets (n = 5) were anesthetized and instrumented to monitor systemic arterial pressure, pulmonary artery pressure, and cardiac output continuously. Hypoxia was induced (DeltaFio2 from 0.5 to 0.08), and either nebulized nitroprusside (5 mg/mL at 4 L/min flow; total dose 25 mg) or inhaled nitric oxide (20 ppm) was introduced into the ventilator circuit for 15 mins. Normoxia was then restored, and a repeat cycle of hypoxia followed by the alternate vasodilator treatment was initiated. MEASUREMENTS AND MAIN RESULTS: Hypoxia significantly reduced Pao2 (from 206 to 30 torr) and elevated pulmonary artery pressure (from 18 to 33 torr) while not significantly affecting systemic arterial pressure or cardiac output. During hypoxia, inhaled nitric oxide reduced pulmonary artery pressure from 33 to 21 torr (p <.01), whereas systemic arterial pressure and cardiac output were unchanged. During hypoxia, nebulized nitroprusside also reduced pulmonary artery pressure from 33 to 23 mm Hg (p <.01; p = nonsignificant vs. inhaled nitric oxide), whereas systemic arterial pressure and cardiac output again remained constant. The time course of the reduction in pulmonary artery pressure during inhaled nitric oxide was roughly ten-fold more rapid (<5 secs) than during nebulized nitroprusside ( approximately 1 min). Neither inhaled nitric oxide nor nebulized nitroprusside altered pH, Pao2, or Paco2. CONCLUSION: Both inhaled nitric oxide and nebulized nitroprusside produced prompt, significant, selective reduction of pulmonary artery pressure and pulmonary vascular resistance in piglets with hypoxia-induced pulmonary hypertension, without apparent effects on systemic hemodynamics or pulmonary gas exchange. The equivalence of the two effects in this animal model suggests that cautious extrapolation of the use of nebulized nitroprusside as a convenient bridge to inhaled nitric oxide in selected clinical contexts for human infants may be warranted.