Using Deep Learning Segmentation for Endotracheal Tube Position Assessment.

PURPOSE: The purpose of this study was to determine the efficacy of using deep learning segmentation for endotracheal tube (ETT) position on frontal chest x-rays (CXRs). MATERIALS AND METHODS: This was a retrospective trial involving 936 deidentified frontal CXRs divided into sets for training (676), validation (50), and 2 for testing (210). This included an "internal test" set of 100 CXRs from the same institution, and an "external test" set of 110 CXRs from a different institution. Each image was labeled by 2 radiologists with the ETT-carina distance. On the training images, 1 radiologist manually segmented the ETT tip and inferior wall of the carina. A U-NET architecture was constructed to label each pixel of the CXR as belonging to either the ETT, carina, or neither. This labeling allowed the distance between the ETT and carina to be compared with the average of 2 radiologists. The interclass correlation coefficients, mean, and SDs of the absolute differences between the U-NET and radiologists were calculated. RESULTS: The mean absolute differences between the U-NET and average of radiologist measurements were 0.60±0.61 and 0.48±0.47 cm on the internal and external datasets, respectively. The interclass correlation coefficients were 0.87 (0.82, 0.91) and 0.92 (0.88, 0.94) on the internal and external datasets, respectively. CONCLUSION: The U-NET model had excellent reliability and performance similar to radiologists in assessing ETT-carina distance.

Effect of Taping Face Masks on Quantitative Particle Counts Near the Eye: Implications for Intravitreal Injections in the COVID-19 Era.

PURPOSE: To determine the effect of taping the top of face masks on air particle counts directed toward the eye during simulated intravitreal injections. DESIGN: Prospective observational crossover study. METHODS: Thirteen healthy subjects were recruited. Each wore a cloth, surgical, or N95 mask in randomized order. The number of air particles were quantified by using a particle counter suspended over the right eye while each subject breathed normally, deeply, or spoke using a standardized script. Particle counts were obtained with the top of each mask taped and not taped. The main outcome measurements were particle counts of 0.3, 0.5, 1, 3, 5, and 10 µm and total particle counts. RESULTS: Taping cloth masks while subjects were speaking significantly reduced particle counts for the 0.3- (P = .03), 0.5- (P = .01), and 1-µm (P = .03) particles and total particle counts (P = .008) compared to no taping. Taping the top of cloth masks during normal or deep breathing did not significantly affect particle counts compared to no taping. Taping the top of surgical or N95 masks did not significantly alter particle counts for any breathing condition tested. CONCLUSIONS: Taping the top of cloth masks prior to simulated intravitreal injections significantly reduced air particle counts directed toward the eye when subjects were speaking compared to no taping. This may have implications for decreasing air particles reaching the eye during intravitreal injections, including aerosolized droplets from a patient's mouth that may carry oral pathogens.