Enhanced artificial intelligence-based diagnosis using CBCT with internal denoising: Clinical validation for discrimination of fungal ball, sinusitis, and normal cases in the maxillary sinus.

BACKGROUND AND OBJECTIVE: The cone-beam computed tomography (CBCT) provides three-dimensional volumetric imaging of a target with low radiation dose and cost compared with conventional computed tomography, and it is widely used in the detection of paranasal sinus disease. However, it lacks the sensitivity to detect soft tissue lesions owing to reconstruction constraints. Consequently, only physicians with expertise in CBCT reading can distinguish between inherent artifacts or noise and diseases, restricting the use of this imaging modality. The development of artificial intelligence (AI)-based computer-aided diagnosis methods for CBCT to overcome the shortage of experienced physicians has attracted substantial attention. However, advanced AI-based diagnosis addressing intrinsic noise in CBCT has not been devised, discouraging the practical use of AI solutions for CBCT. We introduce the development of AI-based computer-aided diagnosis for CBCT considering the intrinsic imaging noise and evaluate its efficacy and implications. METHODS: We propose an AI-based computer-aided diagnosis method using CBCT with a denoising module. This module is implemented before diagnosis to reconstruct the internal ground-truth full-dose scan corresponding to an input CBCT image and thereby improve the diagnostic performance. The proposed method is model agnostic and compatible with various existing and future AI-based denoising or diagnosis models. RESULTS: The external validation results for the unified diagnosis of sinus fungal ball, chronic rhinosinusitis, and normal cases show that the proposed method improves the micro-, macro-average area under the curve, and accuracy by 7.4, 5.6, and 9.6% (from 86.2, 87.0, and 73.4 to 93.6, 92.6, and 83.0%), respectively, compared with a baseline while improving human diagnosis accuracy by 11% (from 71.7 to 83.0%), demonstrating technical differentiation and clinical effectiveness. In addition, the physician's ability to evaluate the AI-derived diagnosis results may be enhanced compared with existing solutions. CONCLUSION: This pioneering study on AI-based diagnosis using CBCT indicates that denoising can improve diagnostic performance and reader interpretability in images from the sinonasal area, thereby providing a new approach and direction to radiographic image reconstruction regarding the development of AI-based diagnostic solutions. Furthermore, we believe that the performance enhancement will expedite the adoption of automated diagnostic solutions using CBCT, especially in locations with a shortage of skilled clinicians and limited access to high-dose scanning.

Internal Nasal Valve Modification via Correction of High Dorsal Deviation Using a Modified Mattress Suture Technique.

High dorsal deviation of the septum can cause nasal obstruction due to internal nasal valve (INV) stenosis. We have developed a new technique using a modified mattress suture on the bony-cartilaginous junction to correct high dorsal septal deviation. This study focused on the effect of this suturing technique on the modification of the INV. We enrolled 40 patients who underwent septoplasty using a modified mattress suture technique. We retrospectively analyzed the data of the preoperative and postoperative INV angles and cross-sectional areas (CSAs), which were measured using computed tomography. In addition, we compared the patients' subjective nasal symptoms, which were measured with the preoperative and postoperative Nasal Obstruction Symptom Evaluation (NOSE) instrument. Postoperative increases in the narrow side INV angle and CSA were achieved. Additionally, the wide side INV angle and CSA were significantly decreased postoperatively. The INV and CSA ratio (wide/narrow) were also decreased postoperatively and were brought closer to 1. The subjective nasal symptoms also exhibited significantly reduced NOSE values. In this study, we confirmed the effects of septoplasty using a modified mattress suture technique for INV modification through the comparison of the preoperative and postoperative INV angles and CSAs.

Intractable middle ear effusion in EGPA patients might cause permanent hearing loss: a case-control study.

BACKGROUND: Ear, nose, and throat involvement are common in eosinophilic granulomatosis with polyangiitis (EGPA). Among otologic manifestation, middle ear effusion (MEE) is less recognized but a problematic condition as it may progress to hearing impairment when left untreated. This study aimed to evaluate the characteristics, risk factors and clinical outcomes of MEE in EGPA patients. METHODS: This is a case-control study of patients who were diagnosed and treated for EGPA from January 1995 to November 2018. Patients with ear symptoms (ear fullness, ear discharge, tinnitus or hearing loss) were assessed by otologists and were included in the case group (n = 23) if clinically relevant. The other patients without MEE were included in the control group (n = 52). Risk of MEE was calculated using the Cox proportional-hazard model. RESULTS: During median follow-up of 9.9 years, 23 (30.7%) out of 75 patients had MEE. In MEE group, 12 (52.2%) patients had hearing loss; conductive type in 10 (10/12, 83.3%) and mixed type in two (2/12, 16.7%). In multivariable regression analysis, major organ involvement at diagnosis (adjusted hazard ratio [aHR] 65.4; 95% confidence interval [CI], 1.50-2838.39; P = 0.030] , early onset of ear symptom after systemic therapy (< 6 months) (aHR 40.0; 95% CI, 1.35-1183.43; P = 0.033) and continuing the maintenance steroid without cessation (aHR 8.59; 95% CI, 1.13-65.42; P = 0.038) were independently associated with a risk of MEE. To control MEE, 16 (69.6%) patients had to increase maintenance steroid dose and 9 (39.1%) patients experienced recurrent MEE whenever maintenance dose was tapered. CONCLUSIONS: MEE is a common but frequently neglected condition in EGPA which is often intractable. The maintenance steroid dose should be adequately adjusted to control MEE and to prevent from progressive hearing loss. Novel biologic agents possibly have a role in controlling MEE in EGPA.

Tumor dimension-dependent microscopic extensions of hypopharyngeal cancer: Therapeutic implications for larynx-preserving hypopharyngectomy.

INTRODUCTION: Hypopharyngeal cancer (HPC) is well characterized by the early submucosal spread of cancer cells into adjacent subsites of the hypopharynx and deep tissues, advocating a wide extent of treatment. However, the microscopic extensions (ME) from gross tumors, according to the primary tumor dimensions, has not been reported in detail. METHODS: We included patients who underwent upfront curative surgery, and retrospectively reviewed pathology specimens from 45 HPC cases. The distance of the MEs, defined as tumor infiltration beyond the gross tumor border on the submucosal and deep sides, was measured. We analyzed potential correlations between MEs and various physical tumor factors. RESULTS: A rough linear correlation between the submucosal ME and the maximal diameter of tumors was found (p < .001, r2 = 0.225). Deep MEs did not correlate with tumor physical factors. However, the MEs differed significantly by the T status (p = .033 and .015 in submucosal and deep sides). In T1-2 tumors, the submucosal MEs were less than 0.5 cm, whereas those of T3-4 tumors were 1.5-2.0 cm. CONCLUSION: In HPC, local MEs beyond the gross tumor border correlated with primary tumor T status. Our findings support that the surgical safety margin for HPC can be adjusted according to tumor dimension.

Safe surgical tracheostomy during the COVID-19 pandemic: A protocol based on experiences with Middle East Respiratory Syndrome and COVID-19 outbreaks in South Korea.

BACKGROUND: A subset of patients with COVID-19 require intensive respiratory care and tracheostomy. Several guidelines on tracheostomy procedures and care of tracheostomized patients have been introduced. In addition to these guidelines, further details of the procedure and perioperative care would be helpful. The purpose of this study is to describe our experience and tracheostomy protocol for patients with MERS or COVID-19. MATERIALS AND METHODS: Thirteen patients with MERS were admitted to the ICU, 9 (69.2%) of whom underwent surgical tracheostomy. During the COVID-19 outbreak, surgical tracheostomy was performed in one of seven patients with COVID-19. We reviewed related documents and collected information through interviews with healthcare workers who had participated in designing a tracheostomy protocol. RESULTS: Compared with previous guidelines, our protocol consisted of enhanced PPE, simplified procedures (no limitation in the use of electrocautery and wound suction, no stay suture, and delayed cannula change) and a validated screening strategy for healthcare workers. Our protocol allowed for all associated healthcare workers to continue their routine clinical work and daily life. It guaranteed safe return to general patient care without any related complications or nosocomial transmission during the MERS and COVID-19 outbreaks. CONCLUSION: Our protocol and experience with tracheostomies for MERS and COVID-19 may be helpful to other healthcare workers in building an institutional protocol optimized for their own COVID-19 situation.