Zubair Hasan

Purpose Training and refining both custom and pre-trained convolutional neural network (CNN) models for calculation of intracochlear positional index (ICPI) is as effective as manual calculation. The ICPI is a position factor that is known to influence cochlear implant performance, however manual calculation on computed tomography (CT) imaging is labour-intensive and prone to calculation errors. Automation of this process with machine learning via a custom built CNN model aims to reduce the difficulty in obtaining this position factor. Increasing the number of training epochs will improve accuracy. Our study aims to develop a validated CNN for ICPI calculation, which may improve surgical electrode positioning. Methods Custom built CNN model and pre-trained ResNet 50 model trained and validated on 34 images, and tested on eight CT images of temporal bones with cochlear implants. The ground truth was manually established by calculating the distance from modiolus to electrode (DE) and lateral wall (DL), and applied to derive the ICPI. Results The pre-trained ResNet-50 model outperformed the custom-built CNN, with improvement statistically significant on evaluation metrics. The ResNet-50 model has lower mean absolute error and root mean squared error (RMSE). In both models, increasing the number of training epochs from ten to 100 improves accuracy of the ICPI calculation. Conclusion Our machine learning models successfully achieved automation of ICPI calculation, with increasing accuracy increasing training epochs to 100 iterations. Future studies should explore optimizing these models and validating them on broader datasets to enhance their applicability in real-world scenarios by comparison to speech and audiometric outcomes.

Background: The nasoseptal flap is commonly used in the reconstruction of the anterior skull base following sinonasal tumor resection, but has limitations in its use. Methods: A retrospective case series at a quaternary referral center involved 13 consecutive anterior skull base resections reconstructed with a pericranial flap. Data collection included patient demographics, type of resection (endoscopic/open/combined), length of stay, follow‐up and complications. The primary outcome was the cerebrospinal fluid (CSF) leakage rate and the secondary outcome was the overall complication rate. Results: The median age was 64 years (range: 32–75 years), and median follow‐up was 24.8 months. Four patients (30.8%) had prior radiotherapy, and 10 patients (76.9%) had adjuvant radiotherapy. Eight patients (61.5%) underwent pure endoscopic resection, while the remaining five (38.5%) had a combined endoscopic resection with an open approach required for an orbital exenteration. None of the patients had an open craniotomy. Post‐operative CSF leakage was 7.7% ( n = 1) and the overall complication rate was 23.1% ( n = 3). In addition to the CSF leak, one patient (7.7%) experienced a tension pneumocephalus and another (7.7%) had a delayed presentation of an ascending intracranial infection. Conclusions: The pericranial flap is a useful extranasal pedicled flap for reconstruction of the anterior skull base when the nasoseptal flap is not available or inadequate. Complications such as CSF leakage, tension pneumocephalus and ascending intracranial infections are uncommon, though they can be adequately managed when present.

Objective: Quality and adequacy of the electrode neuron interface (ENI) is postulated to be a determining factor in affecting auditory outcomes after cochlear implantation. This study aims to review radiological parameters affecting ENI, including angular insertion (AngI), wrapping factor (WF), scalar translocation (ScaT), and electrode–modiolar distance (EMD) and their effect on auditory outcomes. Databases Reviewed: PubMed, MEDLINE, Embase, Scopus, OpenGrey, and Google Scholar from inception to 01 September 2022. Methods: Inclusion criteria were (i) all humans with any cochlear implant (CI); (ii) postoperative cross-sectional imaging with electrode position factors of AngI, ScaT, EMD, and/or WF; and (iii) associated auditory outcomes. Search was restricted to English-language literature. Two independent reviewers performed title and abstract screening, data extraction, and ROBINS-I risk of bias assessment. Formal statistical analysis not performed due to data heterogeneity. PROSPERO (CRD42022359198). Results: Thirty-one studies (n = 2,887 patients, 3,091 electrodes) underwent qualitative synthesis. Higher AngI (n = 1921 patients) demonstrated positive correlation in 11 studies, no correlation in eight studies, and negative correlation in four studies. ScaT (n = 2,115 patients) demonstrated negative correlation in 12 studies, none in six studies, and one unclear correlation. Larger EMD (n = 240 patients) showed negative correlation in two studies, no correlation in one, and unclear correlation in one study. Smaller WF (n = 369 patients) demonstrated no correlation in three studies and positive correlation in one study. Conclusions: Our study finds variable reported relationship between AngI and auditory outcomes. CI electrodes with a ScaT or larger EMD are more likely to exhibit poorer outcomes, and WF does not correlate with outcomes.

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. Cite this article as: Hasan Z, Key S, Lee M, et al. A deep learning algorithm to identify anatomical landmarks on computed tomography of the temporal bone. J Int Adv Otol. 2023;19(5):360-367.

Objective: This review aims to quantify the pooled functional gain (FG) in different types of hearing loss with the transcutaneous hearing device, Osia (Cochlear, Sydney, Australia) in comparison with the unaided state. Secondary outcomes are patient‐reported outcomes measures (PROMs) and complication rates.Data Sources: Medline, Embase, SCOPUS, Cochrane CENTRAL, PROSPERO and Cochrane Library.Review Methods: Systematic review and meta‐analysis of indexed search terms relating to “Osia,” “Osseointegration,” “Cochlear Implant,” and “Bone‐Anchored Prosthesis” was performed from database inception to September 20, 2022.Results: Of the 168 studies identified, 14 studies with 15 patient cohorts (n = 314) met inclusion criteria for meta‐analysis. Pooled overall mean FG for all types of hearing loss was 35.0 dB sound pressure level (SPL) (95% confidence interval [CI] 29.12–40.97) compared against unaided hearing. Pooled FG for conductive/mixed hearing loss was 37.7 dB SPL (95% CI 26.1–49.3). Pooled single‐sided deafness (SSD) FG could not be calculated due to the small patient cohort for whom SSD data was reported. There is a trend toward improvements in speech receptiveness threshold, signal to noise ratio, and some PROMs compared with baseline hearing. Early complication rates demonstrate risks similar to other transcutaneous implants, with a low predicted explantation (0.11%, 95% CI 0.00%–1.90%) and wound infection rate (1.92% [95% CI 0.00%–6.17%]). No articles directly comparing transcutaneous devices were identified.Conclusion: The Osia devices demonstrate clear audiologic benefits and a good safety profile for the included patient population. Our study results indicate that frequency‐specific gain, PROMs, and the audiological benefit in single‐sided deafness may be areas for future prospective research. Laryngoscope, 134:1531–1539, 2024

Objective: Carcinoma ex pleomorphic adenoma (CXPA) is a rare malignant salivary gland tumor. Although multiple reviews have been published on salivary gland malignancies, it has been a decade since the last dedicated systematic review pertaining to CXPA alone was published. This study examines molecular factors in CXPA diagnosis.Data Sources: MEDLINE, CINAHL, Embase, Scopus, Web of Science (BIOSIS), Cochrane CENTRAL, Health Collection (Informit), OpenDOAR, and GreyNet International.Review Methods: Systematic review and meta‐analysis from inception to October 31, 2022 for all English language studies pertaining to “carcinoma ex pleomorphic adenoma.” Predicted incidence of each biomarker was calculated with meta‐analysis. Comparison against pleomorphic adenoma (PA) and salivary duct carcinoma (SDC) when reported within the same study are performed. Risk of bias performed with JBI tool for prevalence studies.Results: Of 19151 unique studies undergoing abstract screening, 55 studies (n = 1322 patients) underwent data analysis. Biomarkers with >3 studies were p53, HER2, AR, EGFR, PLAG1, ERBB, ER, PR, HMGA2, p16, p63, a‐SMA, RAS, PTEN, PDL1, BRAF, PIK3CA, and c‐kit. Highest incidence was seen in AR, EGFR, p16, and p53. Significant differences were demonstrated compared with PA and SDC. There was high heterogeneity and overall high risk of bias within studies.Conclusion: Molecular factors are an area of interest in the diagnosis of CXPA. Our study results support examining CXPA as a discrete cohort in future targeted therapy trials. Laryngoscope, 134:1042–1053, 2024

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.

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. Cite this article as: Hasan Z, Lee M, Chen F, et al. A computer vision algorithm to classify pneumatization of the mastoid process on temporal bone computed tomography scans. J Int Adv Otol. 2023;19(3):217-222.

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.