• 시스템엔지니어링학술지
• /
• 제15권2호
• /
• pp.72-78
• /
• 2019

Pathology is the motor that drives healthcare to understand diseases. The way pathologists diagnose diseases, which involves manual observation of images under a microscope has been used for the last 150 years, it's time to change. This paper is specifically based on tumor detection using deep learning techniques. Pathologist examine the specimen slides from the specific portion of body (e-g liver, breast, prostate region) and then examine it under the microscope to identify the effected cells among all the normal cells. This process is time consuming and not sufficiently accurate. So, there is a need of a system that can detect tumor automatically in less time. Solution to this problem is computational pathology: an approach to examine tissue data obtained through whole slide imaging using modern image analysis algorithms and to analyze clinically relevant information from these data. Artificial Intelligence models like machine learning and deep learning are used at the molecular levels to generate diagnostic inferences and predictions; and presents this clinically actionable knowledge to pathologist through dynamic and integrated reports. Which enables physicians, laboratory personnel, and other health care system to make the best possible medical decisions. I will discuss the techniques for the automated tumor detection system within the new discipline of computational pathology, which will be useful for the future practice of pathology and, more broadly, medical practice in general.

• 대한수의학회지
• /
• 제43권3호
• /
• pp.477-483
• /
• 2003

Molecular diagnostic techniques have been used to identify porcine epidemic diarrhea virus (PEDV), a causative agent of acute enteritis in swine, but they were difficult to be petformed and time-consuming. To detect PEDV in a rapid and easy way, we developed biotinylated cDNA probe for N gene encoding the nucleoproteins of PEDV. Formalin-fixed and paraffin-embedded tissues from 24 naturally infected pigs were used for the experiment. The ISH produced a positive reaction in all cases. When intestinal tissues were hybridized with PEDV probe, strong signals were seen in the villus enterocytes of the jejunum and ileum. Hybridization signals were also found in the duodenum from one pig and in colon from dnother. In conclusion, ISH with a biotinylated cDNA probe was provided to be a useful diagnostic method for detecting PEDV effectively in routinely processed tissue sections.

• 한국수의병리학회지
• /
• 제5권2호
• /
• pp.57-62
• /
• 2001

Recently various molecular diagnostic techniques have been used to identify rabbit hemorrhagic disease virus (RHDV), a causative agent responsible for acute hepatitis and disseminated intravascular coagulation in rabbit. But they were hard to perform and time consuming. To detect RHDV in a rapid and easy way, we developed biotinylated oligonucleotide probe within ORF 1 region encoding the polyprotein of RHDV in formalin-fixed and paraffin-embedded tissues from various tissues of 20 rabbits naturally infected with RHDV, Our in situ hybridization (ISH) was quickly carried out within two hours by MicroProbe capillary action system. The ISH produced a positive reaction in liver, kidney and lung. In conclusion, ISH with a biotintlated oligonucleotide probe provided a useful diagnostic method for detecting RHDV.

• 대한방사성의약품학회지
• /
• 제5권2호
• /
• pp.145-151
• /
• 2019

Fluorine-18 is considered to be the radionuclide of choice for positron emission tomography (PET). Thus, the development of small molecule-based radiopharmaceuticals for use in diagnostic imaging relies heavily on efficient radiofluorination techniques. Until the early 2000s, diaryliodonium salts and aryliodonium ylides were widely employed as labeling precursors to yield aromatic PET radiotracers with cyclotron-produced [¹⁸F]fluoride ion. Rapid recent progress in the development of efficient borylation methods has led to a paradigm shift in ¹⁸F-labeling methods. In addition, deoxyfluorination has attracted a great deal of interest as an alternative approach to aryl ring activation with ¹⁸F^-. In this review, methods for radiolabel development are discussed with a specific focus on the progress made in the last 5 years. Other interesting ¹⁸F-based protocols are also briefly introduced. New methods for exploiting ¹⁸F^- are expected to increase the number of ¹⁸F-labeling methods, to allow applications in a range of chemical environments.

• 한국응용약물학회:학술대회논문집
• /
• 한국응용약물학회 2007년도 Proceedings of The Convention
• /
• pp.19-27
• /
• 2007

An important potential of metabolomics-based approach is the possibility to develop fingerprints of diseases or cellular responses to classes of compounds with known common biological effect. Such fingerprints have the potential to allow classification of disease states or compounds, to provide mechanistic information on cellular perturbations and pathways and to identify biomarkers specific for disease severity and drug efficacy. Metabolic profiles of biological fluids contain a vast array of endogenous metabolites. Changes in those profiles resulting from perturbations of the system can be observed using analytical techniques, such as NMR and MS. $^1H$ NMR was used to generate a molecular fingerprint of serum or urinary sample, and then pattern recognition technique was applied to identity molecular signatures associated with the specific diseases or drug efficiency. Several metabolites that differentiate disease samples from the control were thoroughly characterized by NMR spectroscopy. We investigated the metabolic changes in human normal and clinical samples using $^1H$ NMR. Spectral data were applied to targeted profiling and spectral binning method, and then multivariate statistical data analysis (MVDA) was used to examine in detail the modulation of small molecule candidate biomarkers. We show that targeted profiling produces robust models, generates accurate metabolite concentration data, and provides data that can be used to help understand metabolic differences between healthy and disease population. Such metabolic signatures could provide diagnostic markers for a disease state or biomarkers for drug response phenotypes.

• Parasites, Hosts and Diseases
• /
• 제54권5호
• /
• pp.673-678
• /
• 2016

Epidemiological study on strongyloidiasis in humans is currently lacking in Malaysia. Thus, a cross-sectional study was carried out to determine the prevalence of Strongyloides stercoralis infection among the inhabitants of longhouse indigenous communities in Sarawak. A single stool and blood sample were collected from each participant and subjected to microscopy, serological and molecular techniques. Five species of intestinal parasites were identified by stool microscopy. None of the stool samples were positive for S. stercoralis. However, 11% of 236 serum samples were seropositive for strongyloidiasis. Further confirmation using molecular technique on stool samples of the seropositive individuals successfully amplified 5 samples, suggesting current active infections. The prevalence was significantly higher in adult males and tended to increase with age. S. stercoralis should no longer be neglected in any intestinal parasitic survey. Combination of more than 1 diagnostic technique is necessary to increase the likelihood of estimating the 'true' prevalence of S. stercoralis.

• 한국동물위생학회지
• /
• 제44권2호
• /
• pp.119-124
• /
• 2021

The report describes an avian mycobacteriosis in a captive wild bird. A 7-year-old female Indian peafowl (Pavo cristatus) maintained in a zoo of Korea presented a gradual cachexia and eventually was found dead. At necropsy, severely atrophied pectoral muscles exposing the keel bone were noticed. Yellowish thick nodules in varying sizes were scattered in all lobes of lungs, liver and spleen, suggesting mycobacteriosis. Histopathologically, multifocal to coalescing granulomas surrounded by multinucleated giant cells were observed. Numbers of acid-fast bacilli were revealed in granulomas. Then, a series of molecular diagnostic techniques were followed: a nested PCR, DNA sequencing and bioinformatics analysis. It resulted as Mycobacterium genavense. The identification of M. genavense as an etiological agent suggested that it might serve as a risk factor for other captive wild animals, and for a potential zoonotic risk since M. genavense have been a definite cause of disseminated mycobacterial infection in immunocompromised people. To the authors' knowledge, this is the first report of avian mycobacteriosis with M. genavense in a captive Indian peafowl.

• Journal of Korea Artificial Intelligence Association
• /
• 제2권1호
• /
• pp.7-14
• /
• 2024

In this paper, we explore the application of RNA-sequencing data and ensemble machine learning to predict lung cancer and treatment strategies for lung cancer, a leading cause of cancer mortality worldwide. The research utilizes Random Forest, XGBoost, and LightGBM models to analyze gene expression profiles from extensive datasets, aiming to enhance predictive accuracy for lung cancer prognosis. The methodology focuses on preprocessing RNA-seq data to standardize expression levels across samples and applying ensemble algorithms to maximize prediction stability and reduce model overfitting. Key findings indicate that ensemble models, especially XGBoost, substantially outperform traditional predictive models. Significant genetic markers such as ADGRF5 is identified as crucial for predicting lung cancer outcomes. In conclusion, ensemble learning using RNA-seq data proves highly effective in predicting lung cancer, suggesting a potential shift towards more precise and personalized treatment approaches. The results advocate for further integration of molecular and clinical data to refine diagnostic models and improve clinical outcomes, underscoring the critical role of advanced molecular diagnostics in enhancing patient survival rates and quality of life. This study lays the groundwork for future research in the application of RNA-sequencing data and ensemble machine learning techniques in clinical settings.

• Molecular & Cellular Toxicology
• /
• 제1권1호
• /
• pp.7-12
• /
• 2005

Proteomics has recently received intense scientific interest after the completion of the Human Genome Project, because this genome-based high technology allows to search new drug targets or diagnostic markers. Many proteome projects including Human plasma proteome projects (HPPP), Human liver proteome projects (HLPP), Human brain proteome projects (HBPP), and Mouse and Rat Proteome Project (MRPP) have been carried out and proteomic analytical techniques have been developed in second dimensional electrophoresis (2-DE) and LC/MS system. This powerful method has been applied in toxicology producing a new term "Toxicoproteomics". In this review, recent proteome projects, proteomic technologies, and toxicoproteomics will be discussed.

• Nuclear Medicine and Molecular Imaging
• /
• 제43권3호
• /
• pp.222-228
• /
• 2009

Risk stratification and assessment of prognosis in patients with known or suspected CAD is of crucial important for the practice of contemporary medicine. Noninvasive testing such as myocardial perfusion scintigraphy, coronary artery calcium scoring or CT coronary angiography is increasingly being used to determine the need for aggressive medical therapy and to select patients for catheterization. The integrated anatomic and functional information may provide more additional information for the cardiologist or other clinician by the improved risk stratification and diagnostic accuracy of integrated techniques. The development of SPECT/CT or PET/CT hybrid systems is therefore of important value for the nuclear cardiology.