BACKGROUND AND PURPOSE: Defects at the skull base leading to spontaneous CSF rhinorrhea are rare lesions. The purpose of our study was to correlate CT and MR findings regarding the location and content of CSF leaks in 27 patients with endoscopic sinus surgery observations.

Chronic infectious rhinosinusitis with Pseudomonas aeruginosa is common in cystic fibrosis and may result in allograft infection after lung transplantation. Sinus surgery followed by nasal care may reduce these adverse effects. Sinus surgery was performed in 37 patients with cystic fibrosis after transplantation. Bacteriology of sinus aspirates (n=771) and bronchoalveolar lavage (BAL) (n=256) was correlated with clinical data. Sinus surgery was successful in 54% and partially successful in 27% of patients. A significant correlation between negative sinus aspirates and negative BAL and between positive sinus aspirates and positive BAL (P <0.0001) was found. Successful sinus management led to a lower incidence of tracheobronchitis and pneumonia (P =0.009) and a trend toward a lower incidence of bronchiolitis obliterans syndrome (P =0.23). Sinus surgery followed by daily nasal douching may control posttransplant lower airway colonization and infection. In the long term, this concept may lead to less bronchiolitis obliterans syndrome by decreasing bronchiolar inflammation.

Objective: To assess and compare subjective and objective results after bilateral cochlear implantation with a special emphasis on time interval between the first and second implant. Study Design: Clinical trial. Setting: Tertiary referral center. Patients: All consecutively bilaterally implanted adult patients who had used the second implant for more than 6 months were selected for the study. They had to have the mental capacity to answer questions regarding their hearing abilities and fill out a questionnaire (n = 34). Twenty-nine patients (85%) finally could be included in the study (age at first implantation, 31.0 ± 16 yr [mean ± standard deviation {SD}], time to second implantation, 5.6 ± 5.7 yr [mean ± SD]). In all patients, a full insertion (21 electrodes) of the implant was achieved. For the subjective part of the study, the patients were matched with unilaterally implanted subjects selected according to specified criteria. Interventions: Sequential or simultaneous cochlear implantation with a Nucleus device. Main Outcome Measures: Speech comprehension measures were performed using the Oldenburger sentences in quiet and in noise with unilateral and bilateral implant use. Summation effect, head shadow effect, squelch effect, and interaural difference in quiet and noise were calculated. Advantage for binaural stimulation with respect to the unilateral condition was assessed for each individual. Additionally, a localization test was performed using 12 speakers arranged in a circle. Subjective benefit was assessed by a questionnaire (The Speech, Spatial and Qualities of Hearing Scale). Results were analyzed with special emphasis on effects of timing and intervals. Results: There was a statistically significant advantage for the head shadow effect test (p < 0.05) when the sound source was located on the activated side. There was also a statistically significant correlation of the subjective and objective results and a strong correlation of the interaural difference of speech intelligibility in quiet and the time interval between the first and the second implant (p < 0.001; r² = 55%). In the bi-implanted state, an interaural difference of 18 ± 27% and 3 ± 2.2 dB signal-to-noise ratio (mean ± SD) was measured in quiet and noise, respectively. The mean results for the bilateral condition for the summation effect, the squelch effect, and speech discrimination in quiet were better than in the unilateral condition but were not statistically significant. The subjective results of the bilateral group were better in all categories than the results of the unilateral group but were just below statistical significance. Conclusion: Speech understanding in noise is improved with bilateral cochlear implantation with unambiguous evidence that the second implant expands the sound field for effective speech recognition. Communication in daily life is facilitated, as determined by the subjective Speech, Spatial and Qualities of Hearing Scale test. The correlation of the subjective and objective results confirms the practical benefits in daily activities. Although there was improvement with a second Cochlear implant even after a long implantation interval, short intervals lead to better results.

OBJECTIVE: Gross-total resection (GTR) is often the primary surgical goal in transsphenoidal surgery for pituitary adenoma. Existing classifications are effective at predicting GTR but are often hampered by limited discriminatory ability in moderate cases and by poor interrater agreement. Deep learning, a subset of machine learning, has recently established itself as highly effective in forecasting medical outcomes. In this pilot study, the authors aimed to evaluate the utility of using deep learning to predict GTR after transsphenoidal surgery for pituitary adenoma. METHODS: Data from a prospective registry were used. The authors trained a deep neural network to predict GTR from 16 preoperatively available radiological and procedural variables. Class imbalance adjustment, cross-validation, and random dropout were applied to prevent overfitting and ensure robustness of the predictive model. The authors subsequently compared the deep learning model to a conventional logistic regression model and to the Knosp classification as a gold standard. RESULTS: Overall, 140 patients who underwent endoscopic transsphenoidal surgery were included. GTR was achieved in 95 patients (68%), with a mean extent of resection of 96.8% ± 10.6%. Intraoperative high-field MRI was used in 116 (83%) procedures. The deep learning model achieved excellent area under the curve (AUC; 0.96), accuracy (91%), sensitivity (94%), and specificity (89%). This represents an improvement in comparison with the Knosp classification (AUC: 0.87, accuracy: 81%, sensitivity: 92%, specificity: 70%) and a statistically significant improvement in comparison with logistic regression (AUC: 0.86, accuracy: 82%, sensitivity: 81%, specificity: 83%) (all p < 0.001). CONCLUSIONS: In this pilot study, the authors demonstrated the utility of applying deep learning to preoperatively predict the likelihood of GTR with excellent performance. Further training and validation in a prospective multicentric cohort will enable the development of an easy-to-use interface for use in clinical practice.