An artificial intelligence algorithm for the classification of sphenoid sinus pneumatisation on sinus computed tomography scans.

BACKGROUND: Classifying sphenoid pneumatisation is an important but often overlooked task in reporting sinus CT scans. Artificial intelligence (AI) and one of its key methods, convolutional neural networks (CNNs), can create algorithms that can learn from data without being programmed with explicit rules and have shown utility in radiological image classification. OBJECTIVE: To determine if a trained CNN can accurately classify sphenoid sinus pneumatisation on CT sinus imaging. METHODS: Sagittal slices through the natural ostium of the sphenoid sinus were extracted from retrospectively collected bone-window CT scans of the paranasal sinuses for consecutive patients over 6 years. Two blinded Otolaryngology residents reviewed each image and classified the sphenoid sinus pneumatisation as either conchal, presellar or sellar. An AI algorithm was developed using the Microsoft Azure Custom Vision deep learning platform to classify the pattern of pneumatisation. RESULTS: Seven hundred eighty images from 400 patients were used to train the algorithm, which was then tested on a further 118 images from 62 patients. The algorithm achieved an accuracy of 93.2% (95% confidence interval [CI] 87.1-97.0), 87.3% (95% CI 79.9-92.7) and 85.6% (95% CI 78.0-91.4) in correctly identifying conchal, presellar and sellar sphenoid pneumatisation, respectively. The overall weighted accuracy of the CNN was 85.9%. CONCLUSION: The CNN described demonstrated a moderately accurate classification of sphenoid pneumatisation subtypes on CT scans. The use of CNN-based assistive tools may enable surgeons to achieve safer operative planning through routine automated reporting allowing greater resources to be directed towards the identification of pathology.

Traumatic Pediatric Tracheal Rupture After Blunt Force Sporting Injury: Case Report and Review of the Literature.

OBJECTIVE: This paper presents the case of a traumatic tracheal rupture in a pediatric patient. The body of literature of the clinical features, evaluation, and management of this uncommon presentation is discussed. CASE: A 13-year-old boy sustained an intrathoracic tracheal rupture whilst playing Australian Rules football. He developed hallmark clinical features of air extravasation and was intubated prior to transfer to a tertiary pediatric center for further management. After a short trial of conservative management, his respiratory status deteriorated and he was taken to the operating theater for open surgical repair of the defect. CONCLUSION: Traumatic rupture of the trachea is a rare injury in children. This case demonstrates the dynamic nature of this serious injury and the need for multidisciplinary care in achieving the optimal outcome.

Does Botulinum Toxin Therapy Improve Quality of Life in Patients with Facial Palsy?

OBJECTIVES: To review the current literature for the efficacy of botulinum toxin therapy to improve quality of life in patients with facial palsy. METHODS: A comprehensive systematic literature search was performed of the Medline, EMBase, PubMed and Cochrane Library databases. The population of interest was patients with facial palsy and the intervention of interest was botulinum toxin injection. The primary outcome of this review was quality of life outcomes before and after treatment. RESULTS: Six studies were included for review. Outcome data were not amenable to meta-analysis due to the heterogeneity of outcome measures. There was an overall trend towards improvement in quality of life after botulinum toxin therapy with the majority of studies demonstrating a statistically significant benefit. The aspects of life in which patients saw benefit varied amongst studies. No patient factors were identified to predict which sub-cohort would likely have the greatest benefit from therapy. Two studies reported adverse effects to be common however minor in nature. CONCLUSION: This review presents contemporary evidence that botulinum toxin is of benefit to the quality of life of patients with facial palsy. Additional larger randomised control trials would aid clinicians in quantifying the benefit of such therapies for patients with facial palsy. LEVEL OF EVIDENCE III: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Validation of the 8th edition UICC/AJCC TNM staging system for HPV associated oropharyngeal cancer patients managed with contemporary chemo-radiotherapy.

BACKGROUND: To compare outcomes of high-risk human papilloma virus-related oropharyngeal squamous cell carcinoma (HPV OPSCC) treated with modern radiation treatment (RT) and daily image-guidance, staged with the 7th versus the 8th Edition (Ed) Union for International Cancer Control (UICC)/American Joint Committee on Cancer (AJCC) TNM staging systems. METHODS: All eligible patients with HPV OPSCC treated definitively over a 10-year period (2007-2016) at a single institution were included. Protocols consisting of either RT or chemo-radiation (CRT) (weekly cisplatin or cetuximab) +/- neoadjuvant chemotherapy for those with bulky disease were used. All patients were Fluorine-18-deoxyglucose positron emission tomography (FDG-PET) staged at baseline and at intervals for up to 2 years post-treatment. Patients received parotid-sparing intensity modulated or volumetric modulated arc therapy with simultaneous integrated boost to either 70Gy in 35 fractions or 66Gy in 30 fractions. The overall survival (OS) was determined for each stage using the 7th Ed and subsequently with the updated 8th Ed staging system. RESULTS: One hundred fifty-three patients were analysed. Patient stage groupings varied between the 7th and 8th Eds respectively; Stage I (0.7% vs 64.7%), Stage II (8.5% vs 22.2%), stage III (21.6% vs 12.4%) and stage IV (69.3% vs 0.7%). In the 7th Ed, the 5 year probability of OS for stages I to III was 90%, versus stage IV 85.5%. There was no statistically significant difference between the staging groups (p = 0.85). In the 8th Ed there was a statistically significant difference in 5 year OS for stage I and stage II disease (96.9% vs 77.1% respectively; p < 0.0001), but not between stage II and III disease (p = 0.98). CONCLUSIONS: The new 8th Ed UICC/AJCC TNM staging system better discriminates between stage I and Stage II HPV OPSCC with respect to OS compared with the 7th Ed staging system. Further investigation is required for stage III or IV patients.