Clinical Validation and Extension of an Automated, Deep Learning-Based Algorithm for Quantitative Sinus CT Analysis.

BACKGROUND AND PURPOSE: Sinus CT is critically important for the diagnosis of chronic rhinosinusitis. While CT is sensitive for detecting mucosal disease, automated methods for objective quantification of sinus opacification are lacking. We describe new measurements and further clinical validation of automated CT analysis using a convolutional neural network in a chronic rhinosinusitis population. This technology produces volumetric segmentations that permit calculation of percentage sinus opacification, mean Hounsfield units of opacities, and percentage of osteitis. MATERIALS AND METHODS: Demographic and clinical data were collected retrospectively from adult patients with chronic rhinosinusitis, including serum eosinophil count, Lund-Kennedy endoscopic scores, and the SinoNasal Outcomes Test-22. CT scans were scored using the Lund-Mackay score and the Global Osteitis Scoring Scale. CT images were automatically segmented and analyzed for percentage opacification, mean Hounsfield unit of opacities, and percentage osteitis. These readouts were correlated with visual scoring systems and with disease parameters using the Spearman ρ. RESULTS: Eighty-eight subjects were included. The algorithm successfully segmented 100% of scans and calculated features in a diverse population with CT images obtained on different scanners. A strong correlation existed between percentage opacification and the Lund-Mackay score (ρ = 0.85, P < .001). Both percentage opacification and the Lund-Mackay score exhibited moderate correlations with the Lund-Kennedy score (ρ = 0.58, P < .001, and ρ = 0.58, P < .001, respectively). The percentage osteitis correlated moderately with the Global Osteitis Scoring Scale (ρ = 0.48, P < .001). CONCLUSIONS: Our quantitative processing of sinus CT images provides objective measures that correspond well to established visual scoring methods. While automation is a clear benefit here, validation may be needed in a prospective, multi-institutional setting.

Statewide demonstration of not on tobacco: a gender-sensitive teen smoking cessation program.

This study represented the largest statewide demonstration (n = 346) of the teen smoking cessation program Not On Tobacco (N-O-T) to date and one of the few systematically controlled teen smoking cessation trials reported in the literature. Results showed that N-O-T female teens were 4 times more likely to quit smoking almost 6 months after the program ended than female teens who received a brief intervention (BI). The quit rate for the N-O-T female groups was significantly higher than that for female brief intervention comparison groups. The study demonstrated that 2 times more N-O-T than BI teens quit smoking overall. Differences in the biochemically validated quit rate between the N-O-T groups and the brief intervention groups overall and for male participants were not statistically different, however. Furthermore, findings showed that N-O-T was more effective than the brief intervention in assisting youth with cigarette reduction. There was a significant difference in the reduction rate between the N-O-T and the BI groups on weekdays and weekends 6 months after the program ended. Overall, approximately 84% of N-O-T teens either quit or reduced smoking, compared with approximately 55% of BI teens. This study is 1 phase of an ongoing multiphase evaluation of N-O-T. This study resulted in several important findings that will help guide future teen cessation studies and tobacco cessation efforts of school health professionals.