Introduction Using ultrasound to measure optic nerve sheath diameter (ONSD) has been shown to be a useful modality to detect elevated intracranial pressure. However, manual assessment of ONSD by a human operator is cumbersome and prone to human error. We aimed to develop and test an automated algorithm for ONSD measurement using ultrasound images and compare it to measurements performed by physicians. Materials and Methods Patients were recruited from the Neurological Intensive Care Unit. Ultrasound images of the optic nerve sheath from both eyes were obtained using an ultrasound unit with an ocular preset. Images were processed by two attending physicians to calculate ONSD manually. The images were processed as well using a novel computerized algorithm that automatically analyzes ultrasound images and calculates ONSD. Algorithm-measured ONSD was compared to manually measured ONSD using multiple statistical measures. Results Forty-Four patients with an average/standard deviation (SD) intracranial pressure of 14(9.7) mm Hg were recruited and tested (with a range between 1 and 57 mm Hg). A t-test showed no statistical difference between the ONSD from left and right eyes (P > 0.05). Furthermore, a paired t-test showed no significant difference between the manual and algorithm measure ONSD with a mean difference (SD) of 0.012(0.046) cm (P > 0.05) and percentage error of difference of 6.43% (P = 0.15). Agreement between the two operators was highly correlated (Interclass Correlation coefficient = 0.8, P = 0.26). Bland-Altman analysis revealed mean difference (SD) of 0.012 (0.046) (P = 0.303) and limits of agreement between −0.1 and 0.08. Receiver operator curve analysis yielded an area under the curve of 0.965 (P < 0.0001) with high sensitivity and specificity. Conclusions The automated image-analysis algorithm calculates ONSD reliably and with high precision when compared to measurements obtained by expert physicians. The algorithm may have a role in computer-aided decision support systems in acute brain injury.

Background: In this study, we examined the ability of resonance Raman spectroscopy to measure tissue hemoglobin oxygenation (R-StO 2 ) noninvasively in critically ill patients and compared its performance with conventional central venous hemoglobin oxygen saturation (ScvO 2 ). Methods: Critically ill patients (n ¼ 138) with an indwelling central venous or pulmonary artery catheter in place were consented and recruited. R-StO 2 measurements were obtained by placing a sensor inside the mouth on the buccal mucosa. R-StO 2 was measured continuously for 5 min. Blood samples were drawn from the distal port of the indwelling central venous catheter or proximal port of the pulmonary artery catheter at the end of the test period to measure ScvO 2 using standard co-oximetry analyzer. A regression algorithm was used to calculate the R-StO 2 based on the observed spectra. Results: Mean (SD) of pooled R-StO 2 and ScvO 2 were 64(7.6) % and 65(9.2) % respectively. A paired t test showed no significant difference between R-StO 2 and ScvO 2 with a mean(SD) difference of À1(7.5) % (95% CI: À2.2, 0.3%) with a Clarke Error Grid demonstrating 84.8% of the data residing within the accurate and acceptable grids. Area under the receiver operator curve for R-StO 2 's was 0.8(0.029) (95% CI: 0.7, 0.9 P < 0.0001) at different thresholds of ScvO 2 ( 60%, 65%, and 70%). Clinical adjudication by five clinicians to assess the utility of R-StO 2 and ScvO 2 yielded Fleiss' Kappa agreement of 0.45 (P < 0.00001). Conclusions: R-StO 2 has the potential to predict ScvO 2 with high precision and might serve as a faster, safer, and noninvasive surrogate to these measures.