A5092960928- Medical Imaging Techniques and Applications
- Atomic and Subatomic Physics Research
- Geological Modeling and Analysis
- Nutrition and Health in Aging
- Advanced MRI Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Cancer Risks and Factors
- Body Composition Measurement Techniques
- Lung Cancer Diagnosis and Treatment
- Cardiovascular Disease and Adiposity
- Endometrial and Cervical Cancer Treatments
Istanbul Medipol University
2024
Sağlık Bilimleri Üniversitesi
2024
Izmir University
2024
Izmir Tepecik Eğitim ve Araştırma Hastanesi
2023
A major challenge in computational research 3D medical imaging is the lack of comprehensive datasets. Addressing this issue, our study introduces CT-RATE, first dataset that pairs images with textual reports. CT-RATE consists 25,692 non-contrast chest CT volumes, expanded to 50,188 through various reconstructions, from 21,304 unique patients, along corresponding radiology text Leveraging we developed CT-CLIP, a CT-focused contrastive language-image pre-training framework. As versatile,...
<title>Abstract</title> While computer vision has achieved tremendous success with multimodal encoding and direct textual interaction images via chat-based large language models, similar advancements in medical imaging AI—particularly 3D imaging—have been limited due to the scarcity of comprehensive datasets. To address this critical gap, we introduce CT-RATE, first dataset that pairs corresponding reports. CT-RATE comprises 25,692 non-contrast chest CT scans from 21,304 unique patients....
Obesity is known as a risk factor for endometrial cancer (EC). Only few studies investigate the relationship between sarcopenia and sarcopenic obesity EC. In this study, our aim was to cross-sectional imaging-based body composition parameters disease prognosis in low-grade (LG) high-grade (HG)
<h3>Introduction/Background</h3> It is known that obesity a risk factor for endometrial cancer. Body composition can be determined from the standard of care imaging methods such as computed tomography (CT) and magnetic resonance (MRI). We aim to investigate relationship between imaging-based body parameters clinicopathologic features in patients with <h3>Methodology</h3> conducted retrospective study women diagnosed high-grade (HG; non-endometrioid FIGO G3 endometrioid) low grade (LG; G1–2...