A5055581106- Artificial Intelligence in Healthcare and Education
- Radiomics and Machine Learning in Medical Imaging
- Clinical Reasoning and Diagnostic Skills
- Cardiac, Anesthesia and Surgical Outcomes
- Advanced X-ray and CT Imaging
- Radiology practices and education
- Adrenal and Paraganglionic Tumors
- Transplantation: Methods and Outcomes
- Renal and related cancers
- Cardiac Structural Anomalies and Repair
- Radiopharmaceutical Chemistry and Applications
- Aortic aneurysm repair treatments
- Williams Syndrome Research
- Vascular Anomalies and Treatments
- Pericarditis and Cardiac Tamponade
- IgG4-Related and Inflammatory Diseases
- Otitis Media and Relapsing Polychondritis
- Hormonal Regulation and Hypertension
- Pancreatic and Hepatic Oncology Research
- Literature and Cultural Memory
- Lung Cancer Treatments and Mutations
- Renal cell carcinoma treatment
- Chemotherapy-induced cardiotoxicity and mitigation
- Hepatocellular Carcinoma Treatment and Prognosis
- Glioma Diagnosis and Treatment
Tohoku University Hospital
2020-2024
Universitätsklinikum Würzburg
2021
Tohoku University
2021
Abstract Purpose Herein, we assessed the accuracy of large language models (LLMs) in generating responses to questions clinical radiology practice. We compared performance ChatGPT, GPT-4, and Google Bard using from Japan Radiology Board Examination (JRBE). Materials methods In total, 103 JRBE 2022 were used with permission Radiological Society. These categorized by pattern, required level thinking, topic. McNemar’s test was compare proportion correct between LLMs. Fisher’s exact assess GPT-4...
Patients with pancreatic cancer have a poor prognosis, therefore identifying particular tumor characteristics associated prognosis is important. This study aims to investigate the utility of radiomics machine learning using 18F-fluorodeoxyglucose (FDG)-PET in patients cancer. We enrolled 161 underwent pretreatment FDG-PET/CT. The area primary was semi-automatically contoured threshold 40% maximum standardized uptake value, and 42 PET features were extracted. To identify relevant parameters...
To evaluate the diagnostic performance of self-attention-based model, termed variable Vision Transformer (vViT), in task predicting grade diffuse glioma based on 2021 World Health Organization (WHO) central nervous system (CNS) tumor classification. This cross-sectional study analyzed adult patients with histopathologically confirmed glioma, following WHO CNS We used age, sex, radiomic features, and four MRI sequences to predict gliomas. As binary classifications, we constructed three...
We present a case of 38-year-old woman who complained with cough, fever, and back pain weight loss. F-FDG PET/CT to search fever origin revealed uptake in the tracheobronchial left auricular cartilage wall thoracic aorta. She underwent biopsy auricle was diagnosed relapsing polychondritis (RP) complicating vasculitis. After steroid therapy, FDG demonstrated regression inflammation, showing decreases uptakes. Vasculitis should be considered RP systemic manifestations. Our utility evaluation...
An 80-year-old patient with hepatocellular carcinoma (HCC) underwent an 18 F-FDG PET/CT scan owing to suspected lumbar metastasis identified via a CT performed during transarterial chemoembolization (TACE) 2 weeks earlier. The PET revealed segmental high uptake in the HCC and surrounding liver parenchyma, where lipiodol deposited TACE had mostly washed out. was attributed TACE-induced inflammatory changes parenchyma around HCC, confirmed by reduced follow-up 4 months later. This highlights...
Abstract Purpose This study aims to investigate the effects of language selection and translation quality on Generative Pre-trained Transformer-4 (GPT-4)'s response accuracy expert-level diagnostic radiology questions. Materials methods We analyzed 146 questions from Japan Radiology Board Examination (2020–2022), with consensus answers provided by two board-certified radiologists. The questions, originally in Japanese, were translated into English GPT-4 DeepL German Chinese GPT-4. Responses...
A 37-year-old man with previous heart transplantation for dilated cardiomyopathy underwent screening malignancy under posttransplantation immunosuppression. 18 F-FDG PET/CT revealed uptake in 2 peritoneal sites of the pericardium that corresponded to insertion a left ventricular assist device was used before transplantation. Additional abnormal right axillary artery, aortic arch, and femoral artery arterial inflow during cardiopulmonary bypass. Knowledge FDG accumulation may occur at an...
Purpose: To present a novel clinical application of silicon-photomultiplier-based positron emission tomography (SiPM-based PET)/computed (CT), detecting type II endoleak 5 years after endovascular aneurysm repair (EVAR). Technique: SiPM-based PET/CT scans with standard whole-body protocol were performed for 73-year-old man past medical history abdominal aortic aneurysms treated EVAR and currently under investigation his duodenal papillary carcinoma. The demonstrated 18F-fluorodeoxyglucose...