A5029030083- Advanced MRI Techniques and Applications
- Catalysis and Hydrodesulfurization Studies
- Advanced Neuroimaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Liver Disease and Transplantation
- Artificial Intelligence in Healthcare and Education
- Petroleum Processing and Analysis
- MRI in cancer diagnosis
- Liver Disease Diagnosis and Treatment
- Pituitary Gland Disorders and Treatments
- Hepatocellular Carcinoma Treatment and Prognosis
- Cancer and Skin Lesions
- Multiple Sclerosis Research Studies
- Organ Transplantation Techniques and Outcomes
- Cutaneous Melanoma Detection and Management
- COVID-19 diagnosis using AI
- Cerebrovascular and Carotid Artery Diseases
- Autoimmune Bullous Skin Diseases
- Fetal and Pediatric Neurological Disorders
- Sepsis Diagnosis and Treatment
- Nonmelanoma Skin Cancer Studies
- Medical Imaging Techniques and Applications
- Glioma Diagnosis and Treatment
- Moyamoya disease diagnosis and treatment
- Radiology practices and education
Osaka Metropolitan University
2022-2025
Tokyo Metropolitan University
2023-2024
San Francisco VA Medical Center
2024
University of California, San Francisco
2024
Osaka City University Hospital
2009-2023
Kobe Children's Hospital
2023
Osaka City University
2013-2022
Metropolitan University
2022
Universidad Metropolitana
2022
Fordham University
2017-2021
Purpose To develop and evaluate a supportive algorithm using deep learning for detecting cerebral aneurysms at time-of-flight MR angiography to provide second assessment of images already interpreted by radiologists. Materials Methods reported radiologists contain were extracted from four institutions the period November 2006 through October 2017. The divided into three data sets: training set, internal test external set. was constructed with its sensitivity detect in sets evaluated. find...
We developed and validated a deep learning (DL)-based model using the segmentation method assessed its ability to detect lung cancer on chest radiographs. Chest radiographs for use as training dataset test were collected separately from January 2006 June 2018 at our hospital. The was used train validate DL-based with five-fold cross-validation. sensitivity mean false positive indications per image (mFPI) independent dataset. included 629 652 nodules/masses 151 159 nodules/masses. had of 0.73...
Chest radiography is a common and widely available examination. Although cardiovascular structures-such as cardiac shadows vessels-are visible on chest radiographs, the ability of these radiographs to estimate function valvular disease poorly understood. Using datasets from multiple institutions, we aimed develop validate deep-learning model simultaneously detect functions radiographs.
Abstract Background GPT-4-based ChatGPT demonstrates significant potential in various industries; however, its clinical applications remain largely unexplored. Methods We employed the New England Journal of Medicine (NEJM) quiz “Image Challenge” from October 2021 to March 2023 assess ChatGPT's capabilities. The quiz, designed for healthcare professionals, tests ability analyze scenarios and make appropriate decisions. evaluated performance on NEJM analyzing accuracy rate by questioning type...
Multiple sclerosis (MS) is a disease of the white matter. Magnetic resonance imaging (MRI) proven to be sensitive method monitoring progression this and its changes due treatment protocols. Quantification severity through estimation MS lesion volume via MR vital for understanding treatment. This paper presents novel methodology system that can routinely used segmenting estimating lesions dual-echo fast spin-echo imagery. A recently developed concept fuzzy objects forms basis methodology. An...
IgG-secretion was induced in a human B blastoid cell line, CESS, by the addition of partially purified T cell-derived helper factor(s) (TRF), which had been obtained from PHA-stimulated cells. The number IgG-producing cells CESS reached its maximal level (10% total cells) within 48 hr after TRF. TRF did not affect proliferation and block with hydroxyurea inhibit increase cells, showing that IgG-production without any requirement division. activity completely removed but TCGF-activity same...
Abstract Introduction Abnormal body temperatures (T b ) are frequently seen in patients with severe sepsis. However, the relationship between T abnormalities and severity of disease is not clear. This study investigated impact on outcomes Methods We enrolled 624 sepsis grouped them into 6 categories according to their at time enrollment. The temperature (≤35.5°C, 35.6–36.5°C, 36.6–37.5°C, 37.6–38.5°C, 38.6–39.5°C, ≥39.6°C) were based data Acute Physiology Chronic Health Evaluation II (APACHE...
Abstract Introduction To validate the Japanese Association for Acute Medicine (JAAM) disseminated intravascular coagulation (DIC) scoring system in patients with severe sepsis, we conducted a multicenter, prospective study at 15 critical care centers tertiary hospitals. Methods This included 624 sepsis patients. JAAM DIC was scored on day of diagnosis (day 1) and 4. Scores disease severity organ dysfunction were also evaluated. Results The prevalence 46.8% (292/624), 21% according to...
Clinical diagnosis of internal hernias is challenging because their nonspecific signs and symptoms. Many types have been defined: paraduodenal, small bowel mesentery-related, greater omentum-related, lesser sac, transverse mesocolon-related, pericecal, sigmoid falciform ligament, pelvic internal, Roux-en-Y anastomosis-related. An hernia a surgical emergency that can develop into intestinal strangulation ischemia. Accurate preoperative crucial for appropriate management. Multidetector...
To compare the diagnostic accuracy of Generative Pre-trained Transformer (GPT)-4-based ChatGPT, GPT-4 with vision (GPT-4V) based and radiologists in musculoskeletal radiology.
Abstract Purpose The performance of vision-language models (VLMs) with image interpretation capabilities, such as GPT-4 omni (GPT-4o), vision (GPT-4V), and Claude-3, has not been compared remains unexplored in specialized radiological fields, including nuclear medicine interventional radiology. This study aimed to evaluate compare the diagnostic accuracy various VLMs, + GPT-4V, GPT-4o, Claude-3 Sonnet, Opus, using Japanese radiology, medicine, radiology (JDR, JNM, JIR, respectively) board...
Large language models like GPT-4 have demonstrated potential for diagnosis in radiology. Previous studies investigating this primarily utilized quizzes from academic journals. This study aimed to assess the diagnostic capabilities of GPT-4-based Chat Generative Pre-trained Transformer (ChatGPT) using actual clinical radiology reports brain tumors and compare its performance with that neuroradiologists general radiologists.
We examined the relations between quantitative volumetric estimates of cerebral lesion load based on magnetization transfer imaging (MTI), clinical data, and measures neuropsychological function in 44 patients with clinically diagnosed MS. In this population we assessed correlation several MTI measures, neurologic (Kurtzke Expanded Disability Status Scale Ambulation Index), disease duration using Spearman9s coefficient. Patients were classified basis test performance as severely impaired,...
In order to clarify the regulatory mechanisms of periodontal regeneration by basic fibroblast growth factor (bFGF), effects bFGF on proliferation, alkaline phosphatase activity, calcified nodule formation and extracellula: matrix synthesis human ligament (PDL) cells were examined in this study. enhanced proliferative responses PDL a dose‐ dependent manner. The maximum mitogenic effect was observed at concentration 10ng/ml. contrast, inhibited induction activity mineralized cells. Moreover,...