A5036540955- Radiomics and Machine Learning in Medical Imaging
- Medical Image Segmentation Techniques
- Brain Tumor Detection and Classification
- AI in cancer detection
- Medical Imaging Techniques and Applications
- Cerebrovascular and Carotid Artery Diseases
- Retinal Imaging and Analysis
- Advanced MRI Techniques and Applications
- Medical Imaging and Analysis
- Radiation Dose and Imaging
- T-cell and Retrovirus Studies
- Advanced X-ray and CT Imaging
- COVID-19 diagnosis using AI
- Digital Radiography and Breast Imaging
- Intracranial Aneurysms: Treatment and Complications
- MRI in cancer diagnosis
- Animal Disease Management and Epidemiology
- CRISPR and Genetic Engineering
- Glaucoma and retinal disorders
- HIV Research and Treatment
- Acute Ischemic Stroke Management
- Lung Cancer Diagnosis and Treatment
- Digital Imaging for Blood Diseases
- Vector-Borne Animal Diseases
- Chromosomal and Genetic Variations
University of Miyazaki
2000-2025
Kumamoto University
2014-2023
National Institute of Technology, Oita College
2011-2012
Gifu University
2005-2010
Mie University
2004-2006
University of Chicago
2002-2003
An automated computerized scheme has been developed for the detection and characterization of diffuse lung diseases on high‐resolution computed tomography (HRCT) images. Our database consisted 315 HRCT images selected from 105 patients, which included normal abnormal slices related to six different patterns, i.e., ground‐glass opacities, reticular linear nodular honeycombing, emphysematous change, consolidation. The areas that specific patterns in were marked by three radiologists...
Mammography is considered the most effective method for early detection of breast cancers. However, it difficult radiologists to detect microcalcification clusters. Therefore, we have developed a computerized scheme detecting early-stage clusters in mammograms. We first novel filter bank based on concept Hessian matrix classifying nodular structures and linear structures. The mammogram images were decomposed into several subimages second difference at scales from 1 4 by this bank. component...
The retrovirus human T-cell leukemia virus type 1 (HTLV-1) integrates into the host DNA, achieves persistent infection, and induces diseases. Here, we demonstrate that viral DNA-capture sequencing (DNA-capture-seq) is useful to characterize HTLV-1 proviruses in naturally virus-infected individuals, providing comprehensive information about proviral structure integration site. We analyzed peripheral blood from 98 HTLV-1-infected individuals found defective were present not only patients with...
Human T cell leukemia virus type 1 (HTLV-1) mainly infects CD4+ cells and induces chronic, persistent infection in infected individuals, with some developing adult leukemia/lymphoma (ATL). HTLV-1 alters cellular differentiation, activation, survival; however, it is unknown whether how these changes contribute to the malignant transformation of cells. In this study, we used single-cell RNA-sequencing receptor-sequencing investigate differentiation HTLV-1-mediated We analyzed 87,742 PBMCs from...
Abstract The recent development and advancement of next-generation sequencing (NGS) technologies have enabled the characterization human genome at extremely high resolution. In retrovirology field, NGS been applied to integration-site analysis deep viral genomes in combination with PCR amplification using virus-specific primers. However, primers are not available for some epigenetic analyses, like chromatin immunoprecipitation (ChIP-seq) assays. Viral sequences poorly detected without...
Abstract Combination anti-retroviral therapy (cART) has drastically improved the clinical outcome of HIV-1 infection. Nonetheless, despite effective cART, persists indefinitely in infected individuals. Clonal expansion HIV-1-infected cells peripheral blood been reported recently. cART is stopping retroviral replication cycle, but not inhibiting clonal host cells. Thus, proliferation may play a role viral persistence, little known about kinetics generation, tissue distribution or underlying...
The histological classification of clustered microcalcifications on mammograms can be difficult, and thus often require biopsy or follow-up. Our purpose in this study was to develop a computer-aided diagnosis scheme for identifying the magnification order assist radiologists' interpretation as "second opinion." database consisted 58 mammograms, which included 35 malignant (9 invasive carcinomas, 12 noninvasive carcinomas comedo type, 14 noncomedo type) 23 benign (17 mastopathies 6...
Human endogenous retroviruses (HERVs) occupy approximately 8% of the human genome. HERVs, transcribed in early embryos, are epigenetically silenced somatic cells, except under pathological conditions. HERV-K is thought to protect embryos from exogenous viral infection. However, uncontrolled expression cells has been implicated several diseases. Here, we show that SOX2, which plays a key role maintaining pluripotency stem critical for LTR5Hs. undergoes retrotransposition within producer...
The detection of unruptured intracranial aneurysms is a major subject in magnetic resonance angiography (MRA) images. However,it difficult for radiologists to detect small on the maximum intensity projection (MIP) images, because adjacent vessels overlap with aneurysm. purpose this study was develop an automated computerized order assist radiologists' interpretation as "second opinion." were first segmented from background by use gray-level thresholding and region growing technique. gradient...
The detection of asymptomatic lacunar infarcts on magnetic resonance (MR) images is important because their presence indicates an increased risk severe cerebral infarction. However, accurate identification MR often hard for radiologists the difficulty in distinguishing and enlarged Virchow-Robin spaces. Therefore, we developed a computer-aided diagnosis (CAD) scheme classification Our database consisted T1- T2- weighted obtained from 109 patients. locations spaces were determined by...
Computer-aided diagnostic systems have been developed for the detection and differential diagnosis of coronavirus disease 2019 (COVID-19) pneumonia using imaging studies to characterise a patient's current condition. In this radiomic study, we propose system predicting COVID-19 patients in danger death portable chest X-ray images.In retrospective selected 100 patients, including ten that died 90 recovered from COVID-19-AR database Cancer Imaging Archive. Since it can be difficult analyse...
To develop the following three attenuation correction (AC) methods for brain
The purpose of our study is to develop an algorithm that would enable the automated detection lacunar infarct on T1-and T2-weighted magnetic resonance (MR) images. Automated identification regions not only useful in assisting radiologists detect infarcts as a computer-aided (CAD) system but also beneficial preventing occurrence cerebral apoplexy high-risk patients. are classified into following two types for detection: “isolated regions” and “lacunar adjacent hyperintensive structures.”...
Detection of unruptured aneurysms is a major task in magnetic resonance angiography (MRA). However, it difficult for radiologists to detect small on the maximum intensity projection (MIP) images because adjacent vessels may overlap with aneurysms. Therefore, we proposed method making new MIP image, SelMIP interested only, as opposed all vessels, by manually selecting cerebral artery from list arteries recognized automatically. By using our viewing technique, selected vessel regions can also...