석준걸 교수

BACKGROUND: Distant metastasis of adenoid cystic carcinoma (ACC) is most commonly identified in the lung, but risk factors are still on debate. METHODS: Risk factors for lung metastasis were evaluated by using Cox proportional hazards model and Kaplan-Meier curves. RESULTS: Of 112 patients, 48% had distant metastasis; 94.4% of whom had lung metastasis. Univariable analysis revealed sublingual or minor salivary gland, tumor size ≥2.5 cm, and perineural invasion as risk factors (hazard ratio [HR]:

Carcinoma ex pleomorphic adenoma (CXPA) arises from the primary or recurrent benign pleomorphic adenoma. The purpose of this study was to evaluate the clinical features that could be referenced in the differentiation. The medical records of 221 patients with pleomorphic adenoma and 15 patients with CXPA were retrospectively reviewed. Clinical characteristics, computed tomography and magnetic resonance imaging findings, and surgical pathology were analyzed. Patients with CXPA were older (55.1 vs

There were significant correlations between BTT scores and self-rated severity scales (r = 0.619, p < 0.001) and between CCSIT scores and self-rated severity scales (r = 0.597, p < 0.001) after adjustment for age, sex, and medical conditions. Using discriminant analysis for both BTT and CCSIT, scores 0-4 could be statistically rated as anosmia, scores 5 and 6 as severe hyposmia, scores 7 and 8 as moderate hyposmia, and scores 9-12 as normosmia (Wilks's lambda = 0.605, p < 0.001 for BTT and Wilks

Objective Despite the growing evidence that metastatic lymph node ratio (MLNR) is a valuable predictor for the prognosis of papillary thyroid carcinoma, it has not yet been fully determined which factors give the ratio predictive value independent of the number of metastatic lymph nodes (MLNs). Study Design Retrospective cohort study. Setting A comprehensive cancer center. Methods Recurrence and clinicopathologic factors were analyzed in 2409 patients with papillary thyroid carcinoma who underwe

The aim of this study was to evaluate the usefulness of a personalized 3D-printed thyroid model that characterizes a patient’s individual thyroid lesion. The randomized controlled prospective clinical trial (KCT0005069) was designed. Fifty-three of these patients undergoing thyroid surgery were randomly assigned to two groups: with or without a 3D-printed model of their thyroid lesion when obtaining informed consent. We used a U-Net-based deep learning architecture and a mesh-type 3D modeling te

Abstract Objectives The purpose of this study was to create a deep learning model for the detection and segmentation of major structures of the tympanic membrane. Methods Total 920 tympanic endoscopic images had been stored were obtained, retrospectively. We constructed a detection and segmentation model using Mask R-CNN with ResNet-50 backbone targeting three clinically meaningful structures: (1) tympanic membrane (TM); (2) malleus with side of tympanic membrane; and (3) suspected perforation a

Although three-dimensional (3D)-printed anatomic models are not new to medicine, the high costs and lengthy production times entailed have limited their application. Our goal was developing a new and less costly 3D modeling method to depict organ-tumor relations at faster printing speeds. We have devised a method of 3D modeling using tomographic images. Coordinates are extracted at a specified interval, connecting them to create mesh-work replicas. Adjacent constructs are depicted by density var

Diagnosis using voice is non-invasive and can be implemented through various voice recording devices; therefore, it can be used as a screening or diagnostic assistant tool for laryngeal voice disease to help clinicians. The development of artificial intelligence algorithms, such as machine learning, led by the latest deep learning technology, began with a binary classification that distinguishes normal and pathological voices; consequently, it has contributed in improving the accuracy of multi-c

Background: Jaundice commonly indicates liver dysfunction and is traditionally diagnosed via invasive blood tests. Objective: This study aimed to develop an AI-based program utilizing images of sclera and urine for non-invasive jaundice screening and compared its accuracy to that of standard blood tests. Methods: This retrospective study involved patients who underwent liver function and bilirubin tests. Scleral and urine images were collected and processed following a standardized protocol to e

Abstract Background After surgery in the thyroid region, patients may present with phonation or singing difficulty, even within their vocal range. We designed a novel voice evaluation method that reflects subjective and objective voice complications of the surgery. Methods This tool recorded patients' voice ranges while singing, which was named the singing voice range profile (singing VRP). Patients were asked to sing “Happy Birthday,” which has a one‐octave scale, at a comfortable tone and inte

Due to the low incidence and histologic diversity of salivary gland cancer, analyzing the incidence of salivary gland cancer is necessary to understand the macroscopic aspects. We intend to investigate the international trend of the reported incidence rate of salivary gland cancer. Using the Korea Central Cancer Registry data, the domestic change in the incidence rate was examined. As a result, a significant increasing trend was confirmed, consistent with the United States and Japan trends. The

OBJECTIVE: Although 3D-printed anatomic models are not new to medicine, the high costs and lengthy production times entailed have limited their application. Our goal was developing a new and less costly 3D modeling method to depict organ-tumor relations at faster printing speeds. METHODS: We have devised a method of 3D modeling using DICOM images. Coordinates are extracted at a specified interval, connecting them to create mesh-work replicas. Adjacent constructs are depicted by density variation