Diagnosis of Early Glottic Cancer Using Laryngeal Image and Voice Based on Ensemble Learning of Convolutional Neural Network Classifiers.

OBJECTIVES: The purpose of study is to improve the classification accuracy by comparing the results obtained by applying decision tree ensemble learning, which is one of the methods to increase the classification accuracy for a relatively small dataset, with the results obtained by the convolutional neural network (CNN) algorithm for the diagnosis of glottal cancer. METHODS: Pusan National University Hospital (PNUH) dataset were used to establish classifiers and Pusan National University Yangsan Hospital (PNUYH) dataset were used to verify the classifier's performance in the generated model. For the diagnosis of glottic cancer, deep learning-based CNN models were established and classified using laryngeal image and voice data. Classification accuracy was obtained by performing decision tree ensemble learning using probability through CNN classification algorithm. In this process, the classification and regression tree (CART) method was used. Then, we compared the classification accuracy of decision tree ensemble learning with CNN individual classifiers by fusing the laryngeal image with the voice decision tree classifier. RESULTS: We obtained classification accuracy of 81.03 % and 99.18 % in the established laryngeal image and voice classification models using PNUH training dataset, respectively. However, the classification accuracy of CNN classifiers decreased to 73.88 % in voice and 68.92 % in laryngeal image when using an external dataset of PNUYH. To solve this problem, decision tree ensemble learning of laryngeal image and voice was used, and the classification accuracy was improved by integrating data of laryngeal image and voice of the same person. The classification accuracy was 87.88 % and 89.06 % for the individualized laryngeal image and voice decision tree model respectively, and the fusion of the laryngeal image and voice decision tree results represented a classification accuracy of 95.31 %. CONCLUSION: The results of our study suggest that decision tree ensemble learning aimed at training multiple classifiers is useful to obtain an increased classification accuracy despite a small dataset. Although a large data amount is essential for AI analysis, when an integrated approach is taken by combining various input data high diagnostic classification accuracy can be expected.

Intravenous Infiltration Risk by Catheter Dwell Time Among Hospitalized Children.

PURPOSE: This study was aimed to examine the cumulative risk for infiltration over IV catheter dwell time by general or catheterization-specific characteristics of pediatric patients with IV therapy. DESIGN AND METHODS: This secondary data analysis was done with the data of 1596 children who received peripheral IV therapy at least once during their hospital stay between August 1st and October 30th, 2011 and in June, 2013 in an academic medical center, Yangsan, Republic of Korea. The survival functions of infiltration were determined by using the Kaplan-Meier analysis. RESULT: The cumulative risk for infiltration had rapidly increased from 1.5% after 24 hours of catheter dwell time to 17.3% after 96 hours. The survival functions were significantly different in the medical than in the surgical department (p=.005), lower extremities than upper ones (p=.001), and use of 10% dextrose (p=.001), ampicillin/sulbactam (p<.001), vancomycin (p=.024), high-concentration electrolytes (p=.001), and phenytoin (p<.001). CONCLUSION: When catheter dwell times are similar, the cumulative risk for infiltration was higher in cases wherein the patient had a risk factor. The cumulative risk for infiltration has rapidly increased after 24 hours in patients who have 10% dextrose, high-concentration electrolytes, and phenytoin. PRACTICE IMPLICATIONS: The results suggest that nurses are required to assess the IV site every hour after 24 hours of catheter dwell time for the infusion of irritants for a safer practice of IV therapy. However, this monitoring time may be modified by the age of child, previous IV complications, and/or hemodynamic issues which may impact IV integrity.

Real-time Simultaneous DKG and 2D DKG Using High-speed Digital Camera.

INTRODUCTION: For the evaluation of voice disorders, direct observation of vocal cord vibration is important. Among the various methods, laryngeal videostroboscopy (LVS) is widely used, but it was not a true image because it collects images from different cycles. In contrast, high-speed videoendoscopy and videokymography have much higher frame rates and can assess functional and mobility disorders. OBJECTIVE: The purpose of the study is to describe real-time, simultaneous digital kymography (DKG), two-dimensional scanning (2D) DKG, and multi-frame (MF) LVS system using a high-speed digital camera, and identify the efficacy of this system in evaluating vibratory patterns of pathologic voice. METHODS: The pattern of vocal fold vibration was evaluated in a vocally healthy subject and in subjects with vocal polyp, vocal nodules, vocal cord scar, and vocal cord paralysis. We used both quantitative (left-right phase symmetry, amplitude symmetry index) and qualitative (anterior-posterior phase symmetry) parameters for assessment of vocal fold vibration. RESULTS: Our system could record videos within seconds and required relatively little memory. The speed of replay in the DKG, 2D DKG, MF LVS, and high-speed videoendoscopy was controllable. The number of frame per cycle with MF LVS was almost the same as the fundamental frequency. CONCLUSION: Our system can provide images of various modalities simultaneously in real time and analyze morphological and functional vibratory patterns. It can be possible to provide a greater level of information for the diagnosis and treatment of vibratory disorders.

Imaging and Analysis of Human Vocal Fold Vibration Using Two-Dimensional (2D) Scanning Videokymography.

OBJECTIVE: Laryngeal videokymography and high-speed digital kymography are the currently available techniques for studying aperiodic vibration of the vocal folds. However, videokymography has a fundamental limitation that only linear portions of the vocal fold mucosa can be visualized, whereas high-speed digital kymography has the disadvantages of lack of immediate feedback during examination and considerable waiting time before kymographic visualization. We developed a new system, two-dimensional (2D) scanning videokymography, that provides a possible alternative for evaluation of the vibratory pattern of the vocal folds. Herein, we report the application of 2D scanning videokymography for visualization of vocal fold vibration in humans and an analysis of its parameters. MATERIALS AND METHODS: Two young healthy volunteers (one man and one woman) took part in this study. The vibratory patterns of their vocal folds were evaluated using 2D scanning videokymography and laryngeal stroboscopy. RESULTS: Two-dimensional scanning videokymography provided a high-definition image of the vibratory movements of the vocal folds. In analysis of the images acquired by the device, various parameters including fundamental frequency; ratio of the vibratory phases; phase, amplitude, and glottal area symmetry; and cycle-to-cycle variability were extracted. CONCLUSIONS: Our results indicate that 2D scanning videokymography is a useful and promising tool for visualization of the vibratory movement of the vocal folds. This new technique might improve our understanding of the mechanism of vocal fold vibration and contribute to voice research as well as clinical practice.

Development of laser ruler in rigid laryngoscope.

OBJECTIVES: The objective of this study was to develop a new device that provides a simple, noninvasive method of measuring accurate lesion size while using an endoscope. METHODS: We developed a rigid laryngoscope with a built-in laser-ruler using a one-light emitting diode and an acrylic plate. The invention incorporates a built-in laser diode that projects an auto-parallel beam into the optical path of the rigid laryngoscope to form two spots in the field of view. RESULTS: While the interspot distance remains consistent despite changes in focal plane, magnification, or viewing angle of the laryngoscope, projection to an uneven surface introduces certain variations in the shape, and size of the spots, and the distance between the two spots. CONCLUSION: The device enables a laryngologist to easily measure the distance between landmarks, as well as the change in real size, and the progressive change of vocal fold lesions in an outpatient setting.