• 한국멀티미디어학회논문지
• /
• 제23권9호
• /
• pp.1129-1138
• /
• 2020

The performance of convolutional deep learning networks is generally determined according to parameters of target dataset, structure of network, convolution kernel, activation function, and optimization algorithm. In this paper, a genetic algorithm is used to select the appropriate deep learning model and parameters for Alzheimer's classification and to compare the learning results with preliminary experiment. We compare and analyze the Alzheimer's disease classification performance of VGG-16, GoogLeNet, and ResNet to select an effective network for detecting AD and MCI. The simulation results show that the network structure is ResNet, the activation function is ReLU, the optimization algorithm is Adam, and the convolution kernel has a 3-dilated convolution filter for the accuracy of dementia medical images.

• 대한불안의학회지
• /
• 제1권1호
• /
• pp.18-24
• /
• 2005

The Diagnostic and Statistical Manual 4th edition (DSM-IV) has been widely accepted and used for international classification of mental disorder. The DSM has been changed to improve diagnostic reliability and validity through descriptive and categorical approaches which was undertaken atheoretically. The authors reviewed current studies about the DSM-IV classification system and the diagnostic issues of representative categories of anxiety disorder. The authors concluded that the anxiety disorder classification system in DSM-IV has limitations such as a lack of empirical consideration for overlapping features of anxiety disorders and a lack of discriminant validity. To improve diagnostic validity and revise the current DSM-IV classification system, the authors suggested 1) more longitudinal studies for collecting empirical evidence, 2) decreasing the dependence upon operational criteria, 3) deceasing diagnostic boundary blurring, 4) developing disease specific biological diagnostic techniques and 5) continued collaboration between the DSM and International Classification of Diseases (ICD) systems.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 B
• /
• pp.555-559
• /
• 1998

The human chromosome analysis is widely used to diagnose genetic disease and various congenital anomalies. Many researches on automated chromosome karyotype analysis have been carried out, some of which produced commercial systems. However, there still remains much room for improving the accuracy of chromosome classification. In this paper, We proposed an optimal pattern classifier by neural network to improve the accuracy of chromosome classification. The proposed pattern classifier was built up of two-step multi-layer neural network(TMANN). We reconstructed chromosome image to improve the chromosome classification accuracy and extracted four morphological features parameters such as centromeric index (C.I.), relative length ratio(R.L.), relative area ratio(R.A.) and chromosome length(C.L.). These Parameters employed as input in neural network by preprocessing twenty human chromosome images. The experiment results shown that the chromosome classification error was reduced much more than that of the other classification methods.

• Journal of Korean Neurosurgical Society
• /
• 제67권3호
• /
• pp.308-314
• /
• 2024

Vein of Galen aneurysmal malformation is one of important pediatric arteriovenous shunt diseases, especially among neonates and infants. Here, early history of the disease identification, basic pathoanatomy with a focus on the embryonic median prosencephalic vein, classification and differential diagnoses, and recent genetic studies are reviewed.

• 한국콘텐츠학회논문지
• /
• 제9권7호
• /
• pp.1-8
• /
• 2009

본 논문에서는 질병에 대한 전문적인 지식이 부족한 일반인들을 대상으로 자신의 건강 상태를 쉽게 파악할 수 있는 퍼지 신경망 기법을 이용한 한방 자가 진단 질병 분류 시스템과, 자택에서 간편하게 전문의의 진료상담을 받을 수 있는 원격 진료 시스템을 통합한 홈메디컬 시스템을 제안한다. 제안한 한방 자가 진단 시스템은 72가지 한방 질병과 각 질병에 대한 증상을 분석하여 데이터베이스로 구축하고 구축된 데이터베이스 정보를 기반으로 퍼지 신경망 기법을 적용하여 사용자의 질병을 도출한다. 본 논문의 자가 진단 방법은 사용자가 자신의 대표 증상을 제시하면 해당 증상을 포함하는 질병들을 도출하고, 도출된 질병들의 세부 증상들을 사용자가 입력 벡터로 제시하면 퍼지 신경망 기법을 적용하여 세부 증상에 대한 질병들을 클러스터링한 후, 세부 증상에 대한 질병의 소속 정도를 제공한다. 제안한 원격 진료 시스템은 사용자와 전문의가 모두 로그인을 통하여 접속하게 되면 서버에 클라이언트의 정보가 송신되고, 사용자는 서버에서 전문의의 접속 현황을 전달받아 원하는 전문의와 동화상으로 원격 연결되어 전문의의 진료 소견을 받는다. 본 논문에서 제안한 시스템을 한의학 전문의가 분석한 결과, 본 논문에서 제안한 시스템이 한방 질병의 보조 진단으로서의 가능성을 확인하였다.

• Childhood Kidney Diseases
• /
• 제16권1호
• /
• pp.21-31
• /
• 2012

초점성 분절성 사구체 경화증(focal segmental glomerulosclerosis; FSGS)은 경화증을 주 병변으로 하는 질환으로서 일차성 사구체 질환의 하나이면서 진행된 사구체 질환의 형태적 변화를 기술하는 단어로도 사용되고 있다. 사구체에는 경화증, 유리질 형성, 거품세포의 출현, 발세포의 공포화, 광륜형성 등이 보이고, 간질의 섬유화와 염증세포의 침윤, 세뇨관의 위축, 혈관의 비후 및 내막 섬유화 등을 특징으로 한다. 면역형광검사에서 부분적으로 IgM과 C3 등의 침착을 보이지만 면역관련 질환은 아니다. 전자현미경 검사에서는 발세포의 손상 현상으로 세포질 내의 공포화와 족돌기가 상실되는 것이 중요 소견이다. 2004년 표준화 된 FSGS의 분류는 과거의 형태학적 변형들을 모아서 임상과의 상관관계를 지웠다. 그 결과 tip형이 가장 예후가 좋으며, collapsing형이 가장 나쁜 것으로 알려졌다. 그러나 이 분류가 증례에 따라서는 적용하기가 애매한 경우가 많고, collapsing형을 FSGS에 분류하는 것에 대한 반론 등이 제기되고 있다. 한편, 임상적으로는 FSGS를 원인에 따라 분류하여 거꾸로 형태학적 공통점을 찾으려는 노력을 하고 있다. 사구체의 수가 적어서 일어나는 과여과로 인한 FSGS는 perihilar형이 많고 유전적 질환에 의한 것은 diffuse mesangial sclerosis가 특징인 것으로 주장되고 있다. FSGS는 이와 같이 아직도 밝혀져야 할 것이 많은 질환이며, 계속적인 연구가 이루어져야 할 필요가 있다.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• 제17권4호
• /
• pp.223-231
• /
• 2014

Purpose: With previous methods based on only age and location, there are many difficulties in identifying the etiology of acute abdominal pain in children. We sought to develop a new systematic classification of acute abdominal pain and to give some helps to physicians encountering difficulties in diagnoses. Methods: From March 2005 to May 2010, clinical data were collected retrospectively from 442 children hospitalized due to acute abdominal pain with no apparent underlying disease. According to the final diagnoses, diseases that caused acute abdominal pain were classified into nine groups. Results: The nine groups were group I "catastrophic surgical abdomen" (7 patients, 1.6%), group II "acute appendicitis and mesenteric lymphadenitis" (56 patients, 12.7%), group III "intestinal obstruction" (57 patients, 12.9%), group IV "viral and bacterial acute gastroenteritis" (90 patients, 20.4%), group V "peptic ulcer and gastroduodenitis" (66 patients, 14.9%), group VI "hepatobiliary and pancreatic disease" (14 patients, 3.2%), group VII "febrile viral illness and extraintestinal infection" (69 patients, 15.6%), group VIII "functional gastrointestinal disorder (acute manifestation)" (20 patients, 4.5%), and group IX "unclassified acute abdominal pain" (63 patients, 14.3%). Four patients were enrolled in two disease groups each. Conclusion: Patients were distributed unevenly across the nine groups of acute abdominal pain. In particular, the "unclassified abdominal pain" only group was not uncommon. Considering a systemic classification for acute abdominal pain may be helpful in the diagnostic approach in children.

• Journal of Electrical Engineering and Technology
• /
• 제11권4호
• /
• pp.993-1002
• /
• 2016

Hepatitis is a major public health problem all around the world. This paper proposes an automatic disease diagnosis system for hepatitis based on Genetic Algorithm (GA) Wavelet Kernel (WK) Extreme Learning Machines (ELM). The classifier used in this paper is single layer neural network (SLNN) and it is trained by ELM learning method. The hepatitis disease datasets are obtained from UCI machine learning database. In Wavelet Kernel Extreme Learning Machine (WK-ELM) structure, there are three adjustable parameters of wavelet kernel. These parameters and the numbers of hidden neurons play a major role in the performance of ELM. Therefore, values of these parameters and numbers of hidden neurons should be tuned carefully based on the solved problem. In this study, the optimum values of these parameters and the numbers of hidden neurons of ELM were obtained by using Genetic Algorithm (GA). The performance of proposed GA-WK-ELM method is evaluated using statical methods such as classification accuracy, sensitivity and specivity analysis and ROC curves. The results of the proposed GA-WK-ELM method are compared with the results of the previous hepatitis disease studies using same database as well as different database. When previous studies are investigated, it is clearly seen that the high classification accuracies have been obtained in case of reducing the feature vector to low dimension. However, proposed GA-WK-ELM method gives satisfactory results without reducing the feature vector. The calculated highest classification accuracy of proposed GA-WK-ELM method is found as 96.642 %.

• International Journal of Computer Science & Network Security
• /
• 제23권5호
• /
• pp.148-162
• /
• 2023

Classification systems can significantly assist the medical sector by allowing for the precise and quick diagnosis of diseases. As a result, both doctors and patients will save time. A possible way for identifying risk variables is to use machine learning algorithms. Non-surgical technologies, such as machine learning, are trustworthy and effective in categorizing healthy and heart-disease patients, and they save time and effort. The goal of this study is to create a medical intelligent decision support system based on machine learning for the diagnosis of heart disease. We have used a mixed feature creation (MFC) technique to generate new features from the UCI Cleveland Cardiology dataset. We select the most suitable features by using Least Absolute Shrinkage and Selection Operator (LASSO), Recursive Feature Elimination with Random Forest feature selection (RFE-RF) and the best features of both LASSO RFE-RF (BLR) techniques. Cross-validated and grid-search methods are used to optimize the parameters of the estimator used in applying these algorithms. and classifier performance assessment metrics including classification accuracy, specificity, sensitivity, precision, and F1-Score, of each classification model, along with execution time and RMSE the results are presented independently for comparison. Our proposed work finds the best potential outcome across all available prediction models and improves the system's performance, allowing physicians to diagnose heart patients more accurately.

• Journal of Acupuncture Research
• /
• 제25권5호
• /
• pp.43-57
• /
• 2008

Objectives : The purpose of this study is to find the principal of the assignment of Sidong disease and Sosaeng disease(是動病 所生病) into 12 meridians and suggest the author's opinion. Methods : 1. The authors investigated the conception of Sidong disease and Sosaeng disease through several literatures. 2. The authors investigated the line course of 12 meridians(經脈流注) and their Sidong disease and Sosaeng disease. 3. The authors classified Sidong disease and Sosaeng disease following the study by Kim et al. 4. The authors suggested the opinions about the diseases that are difficult to be understood direct relation with the course of meridian. Results : 1. The result of classification of Sidong disease and Sosaeng disease into 5 shows that the percentages were 32.96% for meridian's own disease(本經病), 13.97% for organic own disease(本臟腑病), 12.85% for other organic own disease(他臟腑病), 20.67% for related organic disease(有關器官病), 19.55% for etc.(其他病). 2. Therefore, 19.55% of the whole Sidong disease and Sosaeng disease is that which occurred on the site that is not related directly with the meridian. Conclusions : 1. The exterior and interior relation(表裏關係) and mutual communication between organ and bowel(臟腑相通) are associated with the basic principal of the assignment of Sidong disease and Sosaeng disease that is not related with the course of meridian. 2. The cause of assignment of Sidong disease and Sosaeng disease can be explained according to the profound medical theories.