• Journal of Multimedia Information System
• /
• v.3 no.3
• /
• pp.97-102
• /
• 2016

Deep learning enables machines to have perception and can potentially outperform humans in the medical field. It can save a lot of time and reduce human error by detecting certain patterns from medical images without being trained. The main goal of this paper is to build the optimal model for breast mass classification by applying various methods that influence the performance of Convolutional Neural Network (CNN). Google's newly developed software library Tensorflow was used to build CNN and the mammogram dataset used in this study was obtained from 340 breast cancer cases. The best classification performance we achieved was an accuracy of 0.887, sensitivity of 0.903, and specificity of 0.869 for normal tissue versus malignant mass classification with augmented data, more convolutional filters, and ADAM optimizer. A limitation of this method, however, was that it only considered malignant masses which are relatively easier to classify than benign masses. Therefore, further studies are required in order to properly classify any given data for medical uses.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2004.11a
• /
• pp.124-130
• /
• 2004

Microarray expression datasets are incessantly cumulated with the aid of recent technological advances. One of the first steps for analyzing these data under various experimental conditions is determining differentially expressed genes (DEGs) in each condition. Reasonable choices of thresholds for determining differentially expressed genes are used for the next -step-analysis with suitable statistical significances. We present a model for identifying DEGs using pathway information based on the global connectivity structure. Pathway information can be regarded as a collection of biological knowledge, thus we are tying to determine the optimal threshold so that the consequential connectivity structure can be the most compatible with the existing pathway information. The significant feature of our model is that it uses established knowledge as a reference to determine the direction of analyzing microarray dataset. In the most of previous work, only intrinsic information in the miroarray is used for the identifying DEGs. We hope that our proposed method could contribute to construct biologically meaningful network structure from microarray datasets.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2004.11a
• /
• pp.29-35
• /
• 2004

유방암 환자의 임상정보(clinical features)와 cDNA microarray 기술을 이용하여 얻은 유전자 발현 프로파일은 유방암 예후 인자를 찾는 데에 매우 중요하다. 본 논문에서는 임상정보와 유전자 발현 정보를 접목해서 분석하는 방법으로써 주성분 분석(Principal Component Analysis)을 이용하였다. 이 방법은 다변량 자료의 차원을 줄이는 방법으로써, 대용량 실험 데이터로 인해 발생하는 문제점을 해결하기 위하여 많이 쓰이고 있다. 본 연구에서는 주성분 분석을 이용하여 먼저 한국인 유방암 환자 73명의 cDNA microarray 데이터 차원을 줄이고, 이를 통해 얻어진 주성분(Principal Components)과 임상정보 데이터와의 상관관계를 보았다. One-way ANOVA를 이용한 상관관계 분석 결과의 P-value는 permutation test를 통해 검증하였다. 동일한 방법을 estrogen receptor(ER)(+) 환자 20명과 ER(-) 환자 31명에 적용해본 결과, ER(-) 환자 중에서 재발과 관련된 유전자를 찾을 수 있었다. 주성분 분석을 molecular phenotypic profiles of clinical features에 이용한 결과 발견된 유전자는 유방암의 재발과 관련된 예후 인자로서 의미가 있다.

• 한국생물공학회:학술대회논문집
• /
• 2005.10a
• /
• pp.961-961
• /
• 2005

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.871-872
• /
• 2006

In this paper, we designed bio-signal acquisition system in Magnetic Resonance Imager(MRI) Environment. In MRI Environment, Strong RF Pulse and Gradient Field Switching Noise exist and can cause distortion of ECG. By this, ECG can lose their important information. So we proposed a bio-signal acquisition system with robust immunity to RF pulse and gradient switching noise. In conclusions, the proposed system showed the prevent saturation of measured biosignal and possibility of using cardiac gating and respiration gating method.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.873-874
• /
• 2006

In this paper, we have developed a ventricular fibrillation detection system based on DSP processor. The developed system was able to detect VF in real time correctly and quickly. We compared the performance of the floating point simulation with that of fixed point simulation. The computational cost of fixed point simulation was remarkably reduced than that of floating point simulation.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.4
• /
• pp.571-579
• /
• 2005

In this paper, we proposed an algorithm for arrhythmia classification, which is associated with the reduction of feature dimensions by linear discriminant analysis (LDA) and a support vector machine (SVM) based classifier. Seventeen original input features were extracted from preprocessed signals by wavelet transform, and attempts were then made to reduce these to 4 features, the linear combination of original features, by LDA. The performance of the SVM classifier with reduced features by LDA showed higher than with that by principal component analysis (PCA) and even with original features. For a cross-validation procedure, this SVM classifier was compared with Multilayer Perceptrons (MLP) and Fuzzy Inference System (FIS) classifiers. When all classifiers used the same reduced features, the overall performance of the SVM classifier was comprehensively superior to all others. Especially, the accuracy of discrimination of normal sinus rhythm (NSR), arterial premature contraction (APC), supraventricular tachycardia (SVT), premature ventricular contraction (PVC), ventricular tachycardia (VT) and ventricular fibrillation (VF) were $99.307\%,\;99.274\%,\;99.854\%,\;98.344\%,\;99.441\%\;and\;99.883\%$, respectively. And, even with smaller learning data, the SVM classifier offered better performance than the MLP classifier.

• Journal of Biomedical Engineering Research
• /
• v.31 no.1
• /
• pp.40-49
• /
• 2010

A rule weight -based fuzzy classification model is proposed to analyze the patterns of admission-discharge of patients as a previous research for differential diagnosis of dyspnea. The proposed model is automatically generated from a labeled data set, supervised learning strategy, using three procedure methodology: i) select fuzzy partition regions from spatial distribution of data; ii) generate fuzzy membership functions from the selected partition regions; and iii) extract a set of candidate rules and resolve a conflict problem among the candidate rules. The effectiveness of the proposed fuzzy classification model was demonstrated by comparing the experimental results for the dyspnea patients' data set with 11 features selected from 55 features by clinicians with those obtained using the conventional classification methods, such as standard fuzzy classifier without rule weights, C4.5, QDA, kNN, and SVMs.

• Genomics & Informatics
• /
• v.3 no.1
• /
• pp.30-34
• /
• 2005

Microarray technology makes it possible to measure the expressions of tens of thousands of genes simultaneously under various experimental conditions. Identifying differentially expressed genes in each single experimental condition is one of the most common first steps in microarray gene expression data analysis. Reasonable choices of thresholds for determining differentially expressed genes are used for the next-stap-analysis with suitable statistical significances. We present a supervised model for identifying DEGs using pathway information based on the global connectivity structure. Pathway information can be regarded as a collection of biological knowledge, thus we are trying to determine the optimal threshold so that the consequential connectivity structure can be the most compatible with the existing pathway information. The significant feature of our model is that it uses established knowledge as a reference to determine the direction of analyzing microarray dataset. In the most of previous work, only intrinsic information in the miroarray is used for the identifying DEGs. We hope that our proposed method could contribute to construct biologically meaningful structure from microarray datasets.

• Genomics & Informatics
• /
• v.12 no.4
• /
• pp.236-239
• /
• 2014

The genetic regulation of glucose and insulin levels might be modified by adiposity. With regard to the genetic factors that are altered by adiposity, a large meta-analysis on the interactions between genetic variants and body mass index with regard to fasting glucose and insulin levels was reported by the Meta-Analyses of Glucose- and Insulin-related trait Consortium (MAGIC), based on European ancestry. Because no replication study has been performed in other ethnic groups, we first examined the link between reported single-nucleotide polymorphisms (SNPs) and fasting glucose and insulin levels in a large Korean cohort (Korean Genome and Epidemiology Study cohort [KoGES], n = 5,814). The MAGIC study reported 7 novel SNPs for fasting glucose levels and 6 novel SNPs for fasting insulin levels. In this study, we attempted to replicate the association of 5 SNPs with fasting glucose levels and 5 SNPs with fasting insulin levels. One SNP (rs2293941) in PDX1 was identified as a significant obesity-modifiable factor in Koreans. Our results indicate that the novel loci that were identified by MAGIC are poorly replicated in other ethnic groups, although we do not know why.