Objective:Compare Eustachian tube balloon dilation versus continued medical therapy (control) for treating persistent Eustachian tube dysfunction (ETD).Study Design:Prospective, multicenter, randomized controlled trial.Setting:Tertiary care academic center and private practice.Patients:Diagnosed with medically refractory persistent ETD.Interventions:1:1 Randomization to balloon dilation or control. After 6 weeks, control participants had the option to undergo balloon dilation if symptoms persisted.Main Outcome Measures:Primary efficacy endpoint was the comparison between treatment arms in the mean change from baseline in the 7-item Eustachian Tube Dysfunction Questionnaire (ETDQ-7) score. Primary safety endpoint was complication rate.Results:Sixty participants were randomized (31 balloon dilation, 29 control). Mean (SD) change in overall ETDQ-7 score at 6 weeks was −2.9 (1.4) for balloon dilation compared with −0.6 (1.0) for control: balloon dilation was superior to control (p < 0.0001). No complications were reported in either study arm. Among participants with abnormal baseline assessments, improvements in tympanogram type (p < 0.006) and tympanic membrane position (p < 0.001) were significantly better for balloon dilation than control. Technical success was 100% (91 successful dilations/91 attempts) and most procedures (72%) were completed in the office under local anesthesia. Improvements in the ETDQ-7 scores were maintained through 12 months after balloon dilation.Conclusions:Balloon dilation is a safe and effective treatment for persistent ETD. Based on improved ETDQ-7 scores, balloon dilation is superior to continued medical management for persistent ETD. Symptom improvement is durable through a minimum of 12 months. Procedures are well tolerated in the office setting under local anesthesia.

No abstract

No abstract

No abstract

No abstract

To develop a deep learning model that segments intracranial structures on head CT scans. Materials and Methods:In this retrospective study, a primary dataset containing 62 normal noncontrast head CT scans from 62 patients (mean age, 73 years; age range, 27-95 years) acquired between August and December 2018 was used for model development. Eleven intracranial structures were manually annotated on the axial oblique series. The dataset was split into 40 scans for training, 10 for validation, and 12 for testing. After initial training, eight model configurations were evaluated on the validation dataset and the highest performing model was evaluated on the test dataset. Interobserver variability was reported using multirater consensus labels obtained from the test dataset. To ensure that the model learned generalizable features, it was further evaluated on two secondary datasets containing 12 volumes with idiopathic normal pressure hydrocephalus (iNPH) and 30 normal volumes from a publicly available source. Statistical significance was determined using categorical linear regression with P , .05.Results: Overall Dice coefficient on the primary test dataset was 0.84 6 0.05 (standard deviation). Performance ranged from 0.96 6 0.01 (brainstem and cerebrum) to 0.74 6 0.06 (internal capsule). Dice coefficients were comparable to expert annotations and exceeded those of existing segmentation methods. The model remained robust on external CT scans and scans demonstrating ventricular enlargement. The use of within-network normalization and class weighting facilitated learning of underrepresented classes. Conclusion:Automated segmentation of CT neuroanatomy is feasible with a high degree of accuracy. The model generalized to external CT scans as well as scans demonstrating iNPH.

No abstract

Imaging-based measurements form the basis of surgical decision making in patients with aortic aneurysm. Unfortunately, manual measurement suffer from suboptimal temporal reproducibility, which can lead to delayed or unnecessary intervention. We tested the hypothesis that deep learning could improve upon the temporal reproducibility of CT angiography-derived thoracic aortic measurements in the setting of imperfect ground-truth training data. To this end, we trained a standard deep learning segmentation model from which measurements of aortic volume and diameter could be extracted. First, three blinded cardiothoracic radiologists visually confirmed non-inferiority of deep learning segmentation maps with respect to manual segmentation on a 50-patient hold-out test cohort, demonstrating a slight preference for the deep learning method (p < 1e-5). Next, reproducibility was assessed by evaluating measured change (coefficient of reproducibility and standard deviation) in volume and diameter values extracted from segmentation maps in patients for whom multiple scans were available and whose aortas had been deemed stable over time by visual assessment (n = 57 patients, 206 scans). Deep learning temporal reproducibility was superior for measures of both volume (p < 0.008) and diameter (p < 1e-5) and reproducibility metrics compared favorably with previously reported values of manual inter-rater variability. Our work motivates future efforts to apply deep learning to aortic evaluation.