Headache in Patients with Sellar Disease: Clinicomorphological Predictors of Headache and the Outcome of Endoscopic Transsphenoidal Surgery.

Objectives Sellar pathologies are frequently found on imaging performed to investigate headache. However, both headache and incidental sellar lesions are common. Hence, this study prospectively examined headache prevalence, phenotype, and severity in patients with sellar pathologies and the impact of transsphenoidal surgery on headache. Methods Patients undergoing transsphenoidal resection of sellar lesions were consecutively recruited. At baseline, participants were defined as having headache or not and headache phenotype was characterized using validated questionnaires. Headache severity was assessed at baseline and 6 months postoperatively using the Headache Impact Test-6 (HIT-6) and Migraine Disability Assessment Score (MIDAS). Tumor characteristics were defined using radiological, histological, and endocrine factors. Primary outcomes included baseline headache prevalence and severity and headache severity change at 6 months postoperatively. Correlation between headache and radiological, histological, and endocrine characteristics was also of interest. Results Sixty participants (62% female, 47.1 ± 18.6 years) were recruited. Sixty-three percent possessed baseline headache. HIT-6 scores were higher in patients with primary headache risk factors, including younger age (R 2 = -0.417, p = 0.010), smoking history (63.31 ± 7.93 vs 54.44 ± 9.21, p = 0.0060), and family headache history (68.13 ± 7.01 vs 54.94 ± 9.11, p = 0.0030). Headaches were more common in patients with dural invasion (55.70 ± 12.14 vs 47.18 ± 10.15, p = 0.027) and sphenoid sinus invasion (58.87 ± 8.97 vs 51.29 ± 10.97, p = 0.007). Postoperative severity scores improved more with higher baseline headache severity (HIT-6: R 2 = -0.682, p < 0.001, MIDAS: R 2 = -0.880, p < 0.0010) and dural invasion (MIDAS: -53.00 ± 18.68 vs 12.00 ± 17.54, p = 0.0030). Conclusion Headaches in sellar disease are likely primary disorders triggered or exacerbated by sellar pathology. These may respond to surgery, particularly in patients with severe headache and dural invasion.

Preservation or removal of the lateral nasal wall in endoscopic management of maxillary sinus neoplasia: A comparison of approach related morbidity.

BACKGROUND: The endoscopic modified medial maxillectomy (MMM) and prelacrimal approach (PLA) are two routinely performed endoscopic approaches to the maxillary sinus when access via a middle meatal antrostomy is insufficient. However, there is no data in the literature that has compared outcomes and complication profile between the two procedures to determine which approach is superior. OBJECTIVE: To compare the approach related morbidity of PLA and MMM. METHODS: A retrospective cohort study of all consecutive adult patients undergoing either MMM or PLA from 2009 to 2023 were identified. The primary outcome was development of epistaxis, paraesthesia, lacrimal injury, iatrogenic sinus dysfunction within a minimum of 3 months post-operative follow up. RESULTS: 39 patients (44 sides) underwent PLA and 96 (96 sides) underwent MMM. There were no statistically significant differences between the rates of paraesthesia (9.1 % vs 14.6 %, p = 0.367) or prolonged paraesthesia (2.3 % vs 5.2 %, p = 0.426), iatrogenic maxillary sinus dysfunction (2.3 % vs 5.2 %, p = 0.426) or adhesions requiring removal (4.5 % vs 4.2 %, p = 0.918). No cases of epiphora or nasal cavity stenosis occurred in either arm in our study. CONCLUSIONS: According to our data, the endoscopic modified medial maxillectomy and prelacrimal approach are both equally safe approaches with their own benefits to access.

Predictors of persistent disease in biologic treated type 2 diffuse/eosinophilic chronic rhinosinusitis undergoing surgery.

BACKGROUND: Biologic therapy targeting type 2 chronic rhinosinusitis with nasal polyps (CRSwNP) has greatly improved disease control but nonresponders exist in a proportion of patients in phase 3 trials and clinical practice. This study explores the serum and histologic changes in biologic treated CRSwNP that predict disease control. METHODS: A cross-sectional study was performed of patients with CRSwNP on biologics for their asthma, who underwent endoscopic sinus surgery while on biologic therapy. At the 6-month postoperative assessment, patients with poorly controlled CRSwNP while on biologic therapy were compared to patients who were controlled. Blood and mucosal samples taken at the time of surgery 6 months prior were assessed to predict disease control. RESULTS: A total of 37 patients were included (age 47.8 ± 12.4 years, 43.2% female). Those with poorly controlled disease had reduced tissue eosinophils (% >100 cells/high-powered field: 8.3% vs. 50.0%, p < 0.001) and increased serum neutrophils (5.2 ± 2.7 vs. 3.7 ± 1.1 × 109 cells/L, p = 0.02). Logistic regression analysis demonstrated that reduced tissue eosinophil was predictive for poorly controlled disease (OR = 0.21, 95% CI [0.05, 0.83], p = 0.03). Receiver-operating characteristic analysis showed that need for rescue systemic corticosteroid was predicted at a serum neutrophil cut-off level of 5.75 × 109 cells/L (sensitivity = 80.0%, specificity = 96.9%, AUC = 0.938, p = 0.002). CONCLUSION: Low tissue eosinophils and increased serum neutrophils while on biologics predict for poor response in the biological treatment of with CRSwNP. A serum neutrophil level of ≥5.75 × 109 cells/L predicts for poor response to current biologic therapy.

A Deep Learning Algorithm to Identify Anatomical Landmarks on Computed Tomography of the Temporal Bone.

BACKGROUND: Petrous temporal bone cone-beam computed tomography scans help aid diagnosis and accurate identification of key operative landmarks in temporal bone and mastoid surgery. Our primary objective was to determine the accuracy of using a deep learning convolutional neural network algorithm to augment identification of structures on petrous temporal bone cone-beam computed tomography. Our secondary objective was to compare the accuracy of convolutional neural network structure identification when trained by a senior versus junior clinician. METHODS: A total of 129 petrous temporal bone cone-beam computed tomography scans were obtained from an Australian public tertiary hospital. Key intraoperative landmarks were labeled in 68 scans using bounding boxes on axial and coronal slices at the level of the malleoincudal joint by an otolaryngology registrar and board-certified otolaryngologist. Automated structure identification was performed on axial and coronal slices of the remaining 61 scans using a convolutional neural network (Microsoft Custom Vision) trained using the labeled dataset. Convolutional neural network structure identification accuracy was manually verified by an otolaryngologist, and accuracy when trained by the registrar and otolaryngologist labeled datasets respectively was compared. RESULTS: The convolutional neural network was able to perform automated structure identification in petrous temporal bone cone-beam computed tomography scans with a high degree of accuracy in both axial (0.958) and coronal (0.924) slices (P < .001). Convolutional neural network accuracy was proportionate to the seniority of the training clinician in structures with features more difficult to distinguish on single slices such as the cochlea, vestibule, and carotid canal. CONCLUSION: Convolutional neural networks can perform automated structure identification in petrous temporal bone cone-beam computed tomography scans with a high degree of accuracy, with the performance being proportionate to the seniority of the training clinician. Training of the convolutional neural network by the most senior clinician is desirable to maximize the accuracy of the results.

A Computer Vision Algorithm to Classify Pneumatization of the Mastoid Process on Temporal Bone Computed Tomography Scans.

BACKGROUND: Pneumatization of the mastoid process is variable and of significance to the operative surgeon. Surgical approaches to the temporal bone require an understanding of pneumatization and its implications for surgical access. This study aims to determine the feasibility of using deep learning convolutional neural network algorithms to classify pneumatization of the mastoid process. METHODS: De-identified petrous temporal bone images were acquired from a tertiary hospital radiology picture archiving and communication system. A binary classification mode in the pretrained convolutional neural network was used to investigate the utility of convolutional neural networks in temporal bone imaging. False positive and negative images were reanalyzed by the investigators and qualitatively assessed to consider reasons for inaccuracy. RESULTS: The overall accuracy of the model was 0.954. At a probability threshold of 65%, the sensitivity of the model was 0.860 (95% CI 0.783-0.934) and the specificity was 0.989 (95% CI 0.960-0.999). The positive predictive value was 0.973 (95% CI 0.904-0.993) and the negative predictive value was 0.935 (95% CI 0.901-0.965). The false positive rate was 0.006. The F1 number was 0.926 demonstrating a high accuracy for the model. CONCLUSION: The temporal bone is a complex anatomical region of interest to otolaryngologists. Surgical planning requires high-resolution computed tomography scans, the interpretation of which can be augmented with machine learning. This initial study demonstrates the feasibility of utilizing machine learning algorithms to discriminate anatomical variation with a high degree of accuracy. It is hoped this will lead to further investigation regarding more complex anatomical structures in the temporal bone.

Modelling the effects of post-FESS middle turbinate synechiae on sinonasal physiology: A computational fluid dynamics study.

OBJECTIVE(S): Chronic rhinosinusitis (CRS) is common and often requires surgical intervention. Surgical failure may lead to persistent symptoms and recalcitrant disease, often secondary to synechiae between the middle turbinate (MT) and lateral nasal wall. Synechiae prevention techniques have been extensively investigated, however evidence for the effect of synechiae on sinonasal physiology is lacking. We aimed to model the effects of MT synechiae on a post-functional endoscopic sinus surgery (FESS) sinonasal cavity using computational fluid dynamics (CFD). METHODS: DICOM data from a CT-sinus of a healthy 25-year-old female was segmented to create a three-dimensional model. Virtual surgery was performed to simulate a "full-house" FESS procedure. Multiple models were created, each with a single unilateral virtual MT synechia of varying extent. CFD analysis was performed on each model and compared with a post-FESS control model without synechiae. Airflow velocity, humidity and mucosal surface and air temperature values were calculated. RESULTS: All synechiae models demonstrated aberrant downstream sinonasal airflow. There was reduced ventilation of the ipsilateral frontal, ethmoid and sphenoid sinuses, with a concentrated central "jet" in the middle meatus region. Effects were proportionate to the size of synechiae. The impact on bulk inspired airflow was negligible. CONCLUSION: Post-FESS synechiae between the MT and lateral nasal wall significantly disrupt local downstream sinus ventilation and nasal airflow. These findings may explain the persistent symptoms seen in post-FESS CRS patients with MT synechiae, reinforcing the importance of prevention and adhesiolysis. Larger cohort studies with multiple models of actual post-FESS patients with synechiae are required to validate these findings.

Endoscopic Endonasal Biopsy for Diagnosis of Undifferentiated Lesions of the Cavernous Sinus.

BACKGROUND: Radiologically undifferentiated lesions of the cavernous sinus can pose a diagnostic challenge. Although radiotherapy is the mainstay for treatment of cavernous sinus lesions, histologic diagnosis allows access to a wide variety of alternative treatment modalities. The region is considered a high-risk area for open transcranial surgical access, and the endoscopic endonasal approach presents an alternative technique for biopsy. METHODS: A retrospective case series was performed of all patients undergoing endoscopic endonasal biopsy of isolated cavernous sinus lesions at 2 tertiary institutions. The primary outcomes were the percentage of patients in whom a histologic diagnosis was achieved and the proportion of patients in whom therapy differed from radiotherapy alone. Secondary outcomes included preoperative and postoperative 22-item Sino-Nasal Outcome Test symptom scores, as well as perioperative adverse outcomes. RESULTS: Eleven patients underwent endoscopic endonasal biopsy, with a diagnosis achieved in 10 patients. The most common diagnosis was perineural spread of squamous cell carcinoma, followed by perineuroma and single cases of metastatic melanoma, metastatic adenoid cystic carcinoma, mycobacterium lepri infection, neurofibroma, and lymphoma. Six patients had treatments other than radiotherapy, including immunotherapy, antibiotics, corticosteroids, chemotherapy, and observation alone. There was no significant difference in prebiopsy and postbiopsy 22-item Sino-Nasal Outcome Test scores. There was 1 case of epistaxis requiring return to theater for cautery of the sphenopalatine artery and there were no mortalities. CONCLUSIONS: In a limited case series, endoscopic endonasal biopsy was safe and effective in obtaining diagnosis for cavernous sinus lesions and had a significant impact on therapeutic decision making.

Evaluating the generalizability of deep learning image classification algorithms to detect middle ear disease using otoscopy.

To evaluate the generalizability of artificial intelligence (AI) algorithms that use deep learning methods to identify middle ear disease from otoscopic images, between internal to external performance. 1842 otoscopic images were collected from three independent sources: (a) Van, Turkey, (b) Santiago, Chile, and (c) Ohio, USA. Diagnostic categories consisted of (i) normal or (ii) abnormal. Deep learning methods were used to develop models to evaluate internal and external performance, using area under the curve (AUC) estimates. A pooled assessment was performed by combining all cohorts together with fivefold cross validation. AI-otoscopy algorithms achieved high internal performance (mean AUC: 0.95, 95%CI: 0.80-1.00). However, performance was reduced when tested on external otoscopic images not used for training (mean AUC: 0.76, 95%CI: 0.61-0.91). Overall, external performance was significantly lower than internal performance (mean difference in AUC: -0.19, p ≤ 0.04). Combining cohorts achieved a substantial pooled performance (AUC: 0.96, standard error: 0.01). Internally applied algorithms for otoscopy performed well to identify middle ear disease from otoscopy images. However, external performance was reduced when applied to new test cohorts. Further efforts are required to explore data augmentation and pre-processing techniques that might improve external performance and develop a robust, generalizable algorithm for real-world clinical applications.

Inter-rater agreement between 13 otolaryngologists to diagnose otitis media in Aboriginal and Torres Strait Islander children using a telehealth approach.

INTRODUCTION: Telehealth programs are important to deliver otolaryngology services for Aboriginal and Torres Strait Islander children living in rural and remote areas, where distance and access to specialists is a critical factor. OBJECTIVE: To evaluate the inter-rater agreement and value of increasing levels of clinical data (otoscopy with or without audiometry and in-field nurse impressions) to diagnose otitis media using a telehealth approach. DESIGN: Blinded, inter-rater reliability study. SETTING: Ear health and hearing assessments collected from a statewide telehealth program for Indigenous children living in rural and remote areas of Queensland, Australia. PARTICIPANTS: Thirteen board-certified otolaryngologists independently reviewed 80 telehealth assessments from 65 Indigenous children (mean age 5.7 ± 3.1 years, 33.8% female). INTERVENTIONS: Raters were provided increasing tiers of clinical data to assess concordance to the reference standard diagnosis: Tier A) otoscopic images alone, Tier B) otoscopic images plus tympanometry and category of hearing loss, and Tier C) as B plus static compliance, canal volume, pure-tone audiometry, and nurse impressions (otoscopic findings and presumed diagnosis). For each tier, raters were asked to determine which of the four diagnostic categories applied: normal aerated ear, acute otitis media (AOM), otitis media with effusion (OME), and chronic otitis media (COM). MAIN OUTCOME MEASURES: Proportion of agreement to the reference standard, prevalence-and-bias adjusted κ coefficients, mean difference in accuracy estimates between each tier of clinical data. RESULTS: Accuracy between raters and the reference standard increased with increased provision of clinical data (Tier A: 65% (95%CI: 63-68%), κ = 0.53 (95%CI: 0.48-0.57); Tier B: 77% (95%CI: 74-79%), 0.68 (95%CI: 0.65-0.72); C: 85% (95%CI: 82-87%), 0.79 (95%CI: 0.76-0.82)). Classification accuracy significantly improved between Tier A to B (mean difference:12%, p < 0.001) and between Tier B to C (mean difference: 8%, p < 0.001). The largest improvement in classification accuracy was observed between Tier A and C (mean difference: 20%, p < 0.001). Inter-rater agreement similarly improved with increasing provision of clinical data. CONCLUSIONS: There is substantial agreement between otolaryngologists to diagnose ear disease using electronically stored clinical data collected from telehealth assessments. The addition of audiometry, tympanometry and nurse impressions significantly improved expert accuracy and inter-rater agreement, compared to reviewing otoscopic images alone.

The Modified Medial Maxillectomy as a Radical or Extended,-yet Still Functional,-Technique in Sinus Surgery.

BACKGROUND: Endoscopic sinus surgery with a middle meatal antrostomy is a common intervention in the treatment algorithm for maxillary sinus pathologies. However, this procedure has its origins in a time when simple ventilation of the sinus cavity was the primary (and only often) goal of surgery. In some patients, persistent mucociliary dysfunction occurs despite ventilatory surgery. Although the endoscopic modified medial maxillectomy (MMM) was originally described for tumour surgery, it provides a radical yet still functional option to overcome chronic sinus dysfunction. OBJECTIVE: The goal of this study was to describe the functional status of a post-MMM sinus cavity. METHODS: A consecutive series of patients who underwent at least a unilateral MMM by three tertiary rhinologists were retrospectively reviewed. Prospectively collected data included patient demographics (including age, gender, smoking status and comorbidities), disease-specific factors, microbiology, and preoperative patient-reported symptoms based on the 22-item Sinonasal Outcome Test-22 (SNOT-22) and radiology. The primary outcome of the study was the presence of sinus dysfunction, defined by mucostasis or pooling on endoscopic examination at the last follow-up. Secondary outcomes included the need for revision surgery as a result of sinus dysfunction and the improvement in SNOT-22 score. RESULTS: A total of 551 medial maxillectomies (47.0% female, 52.9 ± 16.8 years) were performed. Very few patients experienced post-operative sustained mucostasis following MMM (10.2%) and even fewer required revision surgery (5.0%). Chronic obstructive pulmonary disease (odds ratio (OR) = 6.82, P < 0.002.) and asthma (OR = 2.48, P = 0.03) were associated with mucostasis. Patients who underwent an MMM experienced a notable postoperative improvement in SNOT-22 score (45.9 ± 23.7 (pre-op) vs. 23.6 ± 19.4 (post-op); paired t-test, P < 0.0001). CONCLUSION: The MMM, whether performed for access to pathology or with the intent to avoid mucous 'sumping' with the sinus, can provide a long-term functional maxillary sinus cavity with minimal morbidity.

Bacterial colonization differences between central compartment atopic disease and eosinophilic chronic rhinosinusitis.

KEY POINTS: Culturable bacterial colonization is similar between type 2 CRS phenotypes Staphylococcus aureus coinfection is similar between eosinophilic CRS and CCAD Patients with CCAD were younger, consistent with current knowledge of the disease.

A Scoping Review of Artificial Intelligence Research in Rhinology.

BACKGROUND: A considerable volume of possible applications of artificial intelligence (AI) in the field of rhinology exists, and research in the area is rapidly evolving. OBJECTIVE: This scoping review aims to provide a brief overview of all current literature on AI in the field of rhinology. Further, it aims to highlight gaps in the literature for future rhinology researchers. METHODS: OVID MEDLINE (1946-2022) and EMBASE (1974-2022) were searched from January 1, 2017 until May 14, 2022 to identify all relevant articles. The Preferred Reporting Items for Systematic Reviews and Meta-analyses Extension for Scoping Reviews checklist was used to guide the review. RESULTS: A total of 2420 results were identified of which 62 met the eligibility criteria. A further 17 articles were included through bibliography searching, for a total of 79 articles on AI in rhinology. Each year resulted in an increase in the number of publications, from 3 articles published in 2017 to 31 articles published in 2021. Articles were produced by authors from 22 countries with a relative majority coming from the USA (19%), China (19%), and South Korea (13%). Articles were placed into 1 of 5 categories: phenotyping/endotyping (n = 12), radiological diagnostics (n = 42), prognostication (n = 10), non-radiological diagnostics (n = 7), surgical assessment/planning (n = 8). Diagnostic or prognostic utility of the AI algorithms were rated as excellent (n = 29), very good (n = 25), good (n = 7), sufficient (n = 1), bad (n = 2), or was not reported/not applicable (n = 15). CONCLUSIONS: AI is experiencing an increasingly significant role in rhinology research. Articles are showing high rates of diagnostic accuracy and are being published at an almost exponential rate around the world. Utilizing AI in radiological diagnosis was the most published topic of research, however, AI in rhinology is still in its infancy and there are several topics yet to be thoroughly explored.

Orbital resection by intranasal technique (ORBIT): A new classification system for reporting endoscopically resectable primary benign orbital tumors.

BACKGROUND: The Cavernous Hemangioma Exclusively Endonasal Resection (CHEER) staging system has become the gold standard for outcomes reporting in endoscopic orbital surgery for orbital cavernous hemangiomas (OCHs). A recent systematic review demonstrated similar outcomes between OCHs and other primary benign orbital tumors (PBOTs). Therefore, we hypothesized that a simplified and more comprehensive classification system could be developed to predict surgical outcomes of other PBOTs. METHODS: Patient and tumor characteristics as well as surgical outcomes from 11 international centers were recorded. All tumors were retrospectively assigned an Orbital Resection by Intranasal Technique (ORBIT) class and stratified based on surgical approach as either exclusively endoscopic or combined (endoscopic and open). Outcomes based on approach were compared using chi-squared or Fisher's exact tests. The Cochrane-Armitage test for trend was used to analyze outcomes by class. RESULTS: Findings from 110 PBOTs from 110 patients (age 49.0 ± 15.0 years, 51.9% female) were included in the analysis. Higher ORBIT class was associated with a lower likelihood of gross total resection (GTR). GTR was more likely to be achieved when an exclusively endoscopic approach was utilized (p < 0.05). Tumors resected using a combined approach tended to be larger, to present with diplopia, and to have an immediate postoperative cranial nerve palsy (p < 0.05). CONCLUSION: Endoscopic treatment of PBOTs is an effective approach, with favorable short-term and long-term postoperative outcomes as well as low rate of adverse events. The ORBIT classification system is an anatomic-based framework that effectively facilitates high-quality outcomes reporting for all PBOTs.

Convolutional Neural Networks in ENT Radiology: Systematic Review of the Literature.

INTRODUCTION: Convolutional neural networks (CNNs) represent a state-of-the-art methodological technique in AI and deep learning, and were specifically created for image classification and computer vision tasks. CNNs have been applied in radiology in a number of different disciplines, mostly outside otolaryngology, potentially due to a lack of familiarity with this technology within the otolaryngology community. CNNs have the potential to revolutionize clinical practice by reducing the time required to perform manual tasks. This literature search aims to present a comprehensive systematic review of the published literature with regard to CNNs and their utility to date in ENT radiology. METHODS: Data were extracted from a variety of databases including PubMED, Proquest, MEDLINE Open Knowledge Maps, and Gale OneFile Computer Science. Medical subject headings (MeSH) terms and keywords were used to extract related literature from each databases inception to October 2020. Inclusion criteria were studies where CNNs were used as the main intervention and CNNs focusing on radiology relevant to ENT. Titles and abstracts were reviewed followed by the contents. Once the final list of articles was obtained, their reference lists were also searched to identify further articles. RESULTS: Thirty articles were identified for inclusion in this study. Studies utilizing CNNs in most ENT subspecialties were identified. Studies utilized CNNs for a number of tasks including identification of structures, presence of pathology, and segmentation of tumors for radiotherapy planning. All studies reported a high degree of accuracy of CNNs in performing the chosen task. CONCLUSION: This study provides a better understanding of CNN methodology used in ENT radiology demonstrating a myriad of potential uses for this exciting technology including nodule and tumor identification, identification of anatomical variation, and segmentation of tumors. It is anticipated that this field will continue to evolve and these technologies and methodologies will become more entrenched in our everyday practice.

Prognostic factors and outcomes in minimal access resections of skull base and sinonasal epithelial malignancy.

BACKGROUND: Sinonasal epithelial malignancies are uncommon tumours but represent a challenge to treatment given their close proximity to the orbit, brain and cranial nerves. Traditional external surgical approaches have potential for significant functional and cosmetic morbidity. An endoscopic approach provides the surgeon with good access for tumour removal and enables surveillance postoperatively. This study aimed to assess outcomes of an endoscopic approach to sinonasal epithelial malignancy and evaluate factors that may influence its utility. METHODS: A case series was performed involving consecutive patients treated with endoscopic or endoscopic-assisted surgery for epithelial sinonasal malignancy. Stratification included TNM staging, histopathology, surgical approach, margin status, perineural involvement and adjuvant or neoadjuvant therapy. At follow-up, complications, local control, nodal status and evidence of distant metastases were recorded. Statistical analyses to identify risk factors for developing recurrence and survival differences were performed. RESULTS: Thirty-five patients were assessed in this study (59.2 ± 11.4 years, 42.9% female). T stage at presentation was T1 in 11.4%, T2 in 17.1%, T3 in 22.9% and T4 in 48.6%. The 3 and 5 year disease specific survival were 91.3% (SE 5) and 71.1% (SE 10). The only factors to influence survival outcomes were perineural invasion of tumour and positive margins at the time of initial surgery. Large tumours did not limit the utility of an endoscopic approach. CONCLUSION: Endoscopic approach is a safe and oncologically equitable treatment approach to external approaches in the management of epithelial sinonasal malignancy. As with external approaches, perineural invasion of malignance is a poor prognostic factor.

Mepolizumab decreases tissue eosinophils while increasing type-2 cytokines in eosinophilic chronic rhinosinusitis.

BACKGROUND: Eosinophilic chronic rhinosinusitis is an often treatment-resistant inflammatory disease mediated by type-2 cytokines, including interleukin (IL)-5. Mepolizumab, a monoclonal antibody drug targeting IL-5, has demonstrated efficacy and safety in inflammatory airway disease, but there is negligible evidence on direct tissue response. The study's aim was to determine the local effect of mepolizumab on inflammatory biomarkers in sinonasal tissue of eosinophilic chronic rhinosinusitis patients. METHODS: Adult patients with eosinophilic chronic rhinosinusitis received 100mg mepolizumab subcutaneously at four-weekly intervals for 24 weeks in this prospective phase 2 clinical trial. Tissue eosinophil counts, eosinophil degranulation (assessed as submucosal eosinophil peroxidase deposition by immunohistochemistry) and cytokine levels (measured in homogenates by immunoassay) were evaluated in ethmoid sinus tissue biopsies collected at baseline and at weeks 4, 8, 16 and 24. RESULTS: Twenty patients (47.7 ± 11.7 years, 50% female) were included. Sinonasal tissue eosinophil counts decreased after 24 weeks of treatment with mepolizumab (101.64 ± 93.80 vs 41.74 ± 53.76 cells per 0.1 mm2 ; p = .035), eosinophil degranulation remained unchanged (5.79 ± 2.08 vs 6.07 ± 1.20, p = .662), and type-2 cytokine levels increased in sinonasal tissue for IL-5 (10.84 ± 18.65 vs 63.98 ± 50.66, p = .001), IL-4 (4.48 ± 3.77 vs 9.38 ± 7.56, p = .004), IL-13 (4.02 ± 2.57 vs 6.46 ± 3.99, p = .024) and GM-CSF (1.51 ± 1.74 vs 4.50 ± 2.97, p = .001). CONCLUSION: Mepolizumab reduced eosinophils in sinonasal tissue, demonstrating that antagonism of IL-5 suppresses eosinophil trafficking. With reduced tissue eosinophils, a local type-2 inflammatory feedback loop may occur. The study exposes mechanistic factors which may explain incomplete treatment response.

Artificial intelligence to classify ear disease from otoscopy: A systematic review and meta-analysis.

OBJECTIVES: To summarise the accuracy of artificial intelligence (AI) computer vision algorithms to classify ear disease from otoscopy. DESIGN: Systematic review and meta-analysis. METHODS: Using the PRISMA guidelines, nine online databases were searched for articles that used AI computer vision algorithms developed from various methods (convolutional neural networks, artificial neural networks, support vector machines, decision trees and k-nearest neighbours) to classify otoscopic images. Diagnostic classes of interest: normal tympanic membrane, acute otitis media (AOM), otitis media with effusion (OME), chronic otitis media (COM) with or without perforation, cholesteatoma and canal obstruction. MAIN OUTCOME MEASURES: Accuracy to correctly classify otoscopic images compared to otolaryngologists (ground truth). The Quality Assessment of Diagnostic Accuracy Studies Version 2 tool was used to assess the quality of methodology and risk of bias. RESULTS: Thirty-nine articles were included. Algorithms achieved 90.7% (95%CI: 90.1-91.3%) accuracy to difference between normal or abnormal otoscopy images in 14 studies. The most common multiclassification algorithm (3 or more diagnostic classes) achieved 97.6% (95%CI: 97.3-97.9%) accuracy to differentiate between normal, AOM and OME in three studies. AI algorithms outperformed human assessors to classify otoscopy images achieving 93.4% (95%CI: 90.5-96.4%) versus 73.2% (95%CI: 67.9-78.5%) accuracy in three studies. Convolutional neural networks achieved the highest accuracy compared to other classification methods. CONCLUSION: AI can classify ear disease from otoscopy. A concerted effort is required to establish a comprehensive and reliable otoscopy database for algorithm training. An AI-supported otoscopy system may assist health care workers, trainees and primary care practitioners with less otology experience identify ear disease.

An Artificial Intelligence Computer-vision Algorithm to Triage Otoscopic Images From Australian Aboriginal and Torres Strait Islander Children.

OBJECTIVE: To develop an artificial intelligence image classification algorithm to triage otoscopic images from rural and remote Australian Aboriginal and Torres Strait Islander children. STUDY DESIGN: Retrospective observational study. SETTING: Tertiary referral center. PATIENTS: Rural and remote Aboriginal and Torres Strait Islander children who underwent tele-otology ear health screening in the Northern Territory, Australia between 2010 and 2018. INTERVENTIONS: Otoscopic images were labeled by otolaryngologists to classify the ground truth. Deep and transfer learning methods were used to develop an image classification algorithm. MAIN OUTCOME MEASURES: Accuracy, sensitivity, specificity, positive predictive value, negative predictive value, area under the curve (AUC) of the resultant algorithm compared with the ground truth. RESULTS: Six thousand five hundred twenty seven images were used (5927 images for training and 600 for testing). The algorithm achieved an accuracy of 99.3% for acute otitis media, 96.3% for chronic otitis media, 77.8% for otitis media with effusion (OME), and 98.2% to classify wax/obstructed canal. To differentiate between multiple diagnoses, the algorithm achieved 74.4 to 92.8% accuracy and an AUC of 0.963 to 0.997. The most common incorrect classification pattern was OME misclassified as normal tympanic membranes. CONCLUSIONS: The paucity of access to tertiary otolaryngology care for rural and remote Aboriginal and Torres Strait Islander communities may contribute to an under-identification of ear disease. Computer vision image classification algorithms can accurately classify ear disease from otoscopic images of Indigenous Australian children. In the future, a validated algorithm may integrate with existing telemedicine initiatives to support effective triage and facilitate early treatment and referral.