Search

Objective: Develop an artificial intelligence assisted computer vision model to screen for laryngeal cancer during flexible laryngoscopy., Methods: Using laryngeal images and flexible laryngoscopy video recordings, we developed computer vision models to classify video frames for usability and cancer screening. A separate model segments any identified lesions on the frames. We used these computer vision models to construct a video stream annotation system. This system classifies findings from flexible laryngoscopy as "potentially malignant" or "probably benign" and segments any detected lesions. Additionally, the model provides a confidence level for each classification., Results: The overall accuracy of the flexible laryngoscopy cancer screening model was 92%. For cancer screening, it achieved a sensitivity of 97.7% and a specificity of 76.9%. The segmentation model attained an average precision at a 0.50 intersection-over-union of 0.595. The confidence level for positive screening results can assist clinicians in counseling patients regarding the findings., Conclusion: Our model is highly sensitive and adequately specific for laryngeal cancer screening. Segmentation helps endoscopists identify and describe potential lesions. Further optimization is required to enable the model's deployment in clinical settings for real-time annotation during flexible laryngoscopy., Competing Interests: Declaration of Conflicting InterestsThe author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Objective: Build a microlaryngoscopy surgical simulator for endoscopic laryngeal surgery using standard microsurgical instruments and a CO 2 laser., Study Design: Anatomical modeling, CAD design and 3D printed manufacturing., Subjects and Methods: We created a modular design for a microlaryngoscopy simulator in CAD software. Components include plastic and stainless-steel models of a standard operating laryngoscope and a cassette system for mounting porcine or synthetic models of the vocal folds. All simulator parts, including the metallic laryngoscope model, were manufactured using 3D printing technology. Tumors were simulated in porcine tissue models by injecting a soy protein-based tumor phantom. Residents and faculty in the Louisiana State University otolaryngology department evaluated the system. Each participant performed microlaryngoscopy with laser resection on a porcine larynx and cold instrument procedures on synthetic vocal folds. Participants scored the simulator using a 5-point Likert scale., Results: The microlaryngeal surgical simulator demonstrated in this project is realistic, economical, and easily assembled. We have included 3D printed parts files and detailed assembly instructions that will enable educators interested in surgical simulation to build the device.Participants in the simulator evaluation session felt that the simulator faithfully represented the procedure to resect vocal fold lesions using a CO 2 laser. The synthetic model allows the trainee to develop hand-eye coordination while using standard laryngeal instruments., Conclusions: The simulator described herein will enable surgeons to acquire the surgical skills necessary to perform operative microlaryngoscopy prior to operating on live patients., Competing Interests: The author declares there is no potential conflicts of interest., (© 2022 The Authors. Laryngoscope Investigative Otolaryngology published by Wiley Periodicals LLC on behalf of The Triological Society.)

Objectives/hypothesis: Create an autonomous computational system to classify endoscopy findings., Study Design: Computational analysis of vocal fold images at an academic, tertiary-care laryngology practice., Methods: A series of normal and abnormal vocal fold images were obtained from the image database of an academic tertiary care laryngology practice. The benign images included normals, nodules, papilloma, polyps, and webs. A separate set of carcinoma and leukoplakia images comprised a single malignant-premalignant class. All images were classified with their existing labels. Images were randomly withheld from each class for testing. The remaining images were used to train and validate a neural network for classifying vocal fold lesions. Two classifiers were developed. A multiclass system classified the five categories of benign lesions. A separate analysis was performed using a binary classifier trained to distinguish malignant-premalignant from benign lesions., Results: Precision ranged from 71.7% (polyps) to 89.7% (papilloma), and recall ranged from 70.0% (papilloma) to 88.0% (nodules) for the benign classifier. Overall accuracy for the benign classifier was 80.8%. The binary classifier correctly identified 92.0% of the malignant-premalignant lesions with an overall accuracy of 93.0%., Conclusions: Autonomous classification of endoscopic images with artificial intelligence technology is possible. Better network implementations and larger datasets will continue to improve classifier accuracy. A clinically useful optical cancer screening system may require a multimodality approach that incorporates nonvisual spectra., Level of Evidence: NA Laryngoscope, 132:S1-S8, 2022., (© 2020 The American Laryngological, Rhinological and Otological Society, Inc.)

There is growing support from the Accreditation Council for Graduate Medical Education and the Joint Commission of Accreditation of Health Care Organizations for a competency-based evaluation of medical and surgical performance. This is part of the quality movement in health care whereby the Centers for Medicare and Medicaid Services and third-party insurance companies have begun to link reimbursement incentives to positive surgical outcomes. Laryngeal and airway surgery require precise technique and significant mastered skill that can be difficult to obtain during otolaryngology residency training. Simulators are useful for developing laryngeal and airway surgery skills ultimately evaluated in a competency-based manner., (Copyright © 2017 Elsevier Inc. All rights reserved.)

Objective: To determine whether there is an association between the presence of asthma and a clinically aggressive disease course in patients with recurrent respiratory papillomatosis (RRP)., Design: Retrospective multi-institutional cohort study (level III evidence)., Setting: Two academic medical centers in the southeastern United States., Patients: Adult patients with RRP treated at the Georgia Health Sciences University or at the Emory University School of Medicine between January 1998 and December 2009. Excluded from the study were adult patients who had been diagnosed as having RRP when they were a child (<18 years)., Main Outcome Measures: The primary outcome measure was the presence of a clinically aggressive RRP disease course (defined as distal spread of disease, >4 procedures performed in 12 months, or progression to laryngeal squamous cell carcinoma). The secondary outcome measure was the frequency of required surgical interventions., Results: Identified were 90 patients with RRP (age range at first diagnosis, 19.1-86.4 years). Seventeen patients had aggressive disease, and 73 patients had nonaggressive disease. Seven patients had a history of asthma, 5 of whom were using daily inhaled corticosteroids. An association was noted between the presence of asthma and aggressive RRP, which was found in 57% (4 of 7) of patients with asthma vs 16% (13 of 83) of patients without asthma (P = .02). Patients with asthma using daily inhaled corticosteroids were especially likely to have aggressive RRP, which was found in 80% (4 of 5) of corticosteroid users vs 15% (13 of 85) of nonusers (P = .004)., Conclusions: Patients with asthma, particularly those using daily inhaled corticosteroids, may have a more clinically aggressive RRP course. The cause of this association is unclear, and clinical recommendations should not yet be made based on these data.