Computer-Aided Diagnosis Algorithm for Classification of Malignant Melanoma Using Deep Neural Networks.

Malignant melanoma accounts for about 1-3% of all malignancies in the West, especially in the United States. More than 9000 people die each year. In general, it is difficult to characterize a skin lesion from a photograph. In this paper, we propose a deep learning-based computer-aided diagnostic algorithm for the classification of malignant melanoma and benign skin tumors from RGB channel skin images. The proposed deep learning model constitutes a tumor lesion segmentation model and a classification model of malignant melanoma. First, U-Net was used to classify skin lesions in dermoscopy images. We implement an algorithm to classify malignant melanoma and benign tumors using skin lesion images and expert labeling results from convolutional neural networks. The U-Net model achieved a dice similarity coefficient of 81.1% compared to the expert labeling results. The classification accuracy of malignant melanoma reached 80.06%. As a result, the proposed AI algorithm is expected to be utilized as a computer-aided diagnostic algorithm to help early detection of malignant melanoma.

Novel smart clothing with dry electrode biosensor for real-time automatic diagnosis of cardiovascular diseases.

The incidence of heart disease increases with age. The typical method of monitoring arrhythmia is to use a body patch type sensor with a wet electrode. Even though this sensor is easy to use, it has several disadvantages such as problems caused by wet electrodes in tissues when they are monitored for long periods. Thus, a monitoring sensor integrated into clothes with a dry electrode is proposed. In this study, we developed a smart outdoor shirt equipped with a dry electrode electrocardiogram (ECG) sensor for a cardiac arrhythmia computer-aided diagnosis system. The sensor can be inserted in a console close to the chest, charged, used to communicate wirelessly, and can be connected to a smartphone application. According to experiments, the ECG signals measured by the smart shirt indicated that 97.5 ± 1% of the signals could be measured in an immobile state and at least 85.2 ± 2% of the signals could be measured during movement. In addition, we propose a computer-aided diagnosis system for detecting cardiac arrhythmia. It was determined through experiments that the system can detect arrhythmia with an accuracy of 98.2 ± 2%.

Factors Prognostic of Season-Associated Sudden Sensorineural Hearing Loss: A Retrospective Observational Study.

BACKGROUND AND OBJECTIVES: This study examined whether the prognosis of sudden deafness was dependent on the time of onset and evaluated the factors affecting prognosis during each period. SUBJECTS AND METHODS: Patients who developed sudden hearing loss from January 2005 to December 2015 were evaluated retrospectively. Meteorological data were obtained from the official website of the Korea Meteorological Administration. Factors prognostic of hearing recovery rate were analyzed. RESULTS: The hearing recovery rate of the 318 patients who developed sudden deafness did not differ significantly by month. Mean temperature and daily temperature range at onset of sudden deafness were not associated with recovery rate. CONCLUSIONS: The recovery rate in patients with sudden deafness did not differ markedly by season.

Characteristics of Patients with Hearing Aids according to the Degree and Pattern of Hearing Loss.

BACKGROUND AND OBJECTIVES: This study was designed to assess the characteristics of patients according to the degree and audiogram shape of hearing loss and the association of these characteristics with hearing aids (HA) choice, return rate, and cause of return. SUBJECTS AND METHODS: This study included 460 individuals who received HAs from 2011 to 2015. The relationships between type of HA and age, primary and accompanying symptoms, HA choice and return and cause of return were evaluated according to the degree and pattern of hearing loss. RESULTS: HA type did not differ significantly according to the degree and pattern of hearing loss. Intensity of hearing loss was greater in male than in female (p<0.05). Open and completely-in-canal types of HA decreased with age (p<0.05). As degree of hearing loss intensified, behind-the-ear and in-the-ear types increased and Open type decreased (p<0.05). The HA return rate was 9.7%, but was not associated with degree or pattern of hearing loss. The main causes of HA return were costs, psychological fears and adaptive failure. CONCLUSIONS: Choice of HA is affected by age, sex, and degree and pattern of hearing loss. HA for hearing rehabilitation in patients with hearing loss can be personalized according to each patient's characteristics and tendencies.