A5024776075- Advanced X-ray and CT Imaging
- Medical Imaging Techniques and Applications
- Radiation Dose and Imaging
- Cardiac Imaging and Diagnostics
- Radiomics and Machine Learning in Medical Imaging
- Advanced MRI Techniques and Applications
- Advanced Radiotherapy Techniques
- Anatomy and Medical Technology
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Lung Cancer Diagnosis and Treatment
- Delphi Technique in Research
- Ultrasound in Clinical Applications
- AI in cancer detection
- Coronary Interventions and Diagnostics
Canon Medical Systems Corporation (Japan)
2019-2025
Canon (Japan)
2019-2025
Canon (United States)
2020
Duke Medical Center
2020
Swedish Medical Center
2020
Johns Hopkins University
2020
American Association of Physicists in Medicine
2020
Ashland (United States)
2020
Philips (Finland)
2020
John Wiley & Sons (United States)
2020
OBJECTIVE. The objective of this study was to compare image quality and clinically significant lesion detection on deep learning reconstruction (DLR) iterative (IR) images submillisievert chest abdominopelvic CT. MATERIALS AND METHODS. Our prospective multiinstitutional included 59 adult patients (33 women, 26 men; mean age ± SD, 65 12 years old; body mass index [weight in kilograms divided by the square height meters] = 27 5) who underwent routine (n 22; 16 six men) 37; 17 20 CT a 640-MDCT...
To evaluate the effect of a deep learning-based reconstruction (DLR) method on conspicuity hypovascular hepatic metastases abdominal CT images.This retrospective study with institutional review board approval included 58 patients metastases. A radiologist recorded standard deviation attenuation in paraspinal muscle as image noise and contrast-to-noise ratio (CNR). CNR was calculated region interest ([ROI]L - ROIT)/N, where ROIL is mean liver parenchyma attenuation, ROIT, tumor N, noise. Two...
Deep learning reconstruction (DLR) has been introduced by major vendors, tested for CT examinations of a variety organs, and compared with other methods. The purpose this study was to compare the capabilities DLR image quality improvement lung texture evaluation those hybrid-type iterative (IR) standard-, reduced- ultra-low-dose CTs (SDCT, RDCT ULDCT) obtained high-definition (HDCT) reconstructed at 0.25-mm, 0.5-mm 1-mm section thicknesses 512 × or 1024 matrixes patients various pulmonary...
Chronic obstructive pulmonary disease (COPD), encompassing chronic bronchitis and emphysema, requires precise quantification through CT imaging to accurately assess severity progression. However, inconsistencies in protocols often lead unreliable measurements. This study aims optimize acquisition reconstruction for cross-sectional longitudinal measurements of COPD using a virtual (in-silico) framework. We developed human models at various stages emphysema bronchitis, informed by the COPDGene...
Purpose To validate a normal‐resolution (NR) simulation (NRsim) algorithm that uses high‐resolution (HR) or super‐high resolution (SHR) acquisitions on commercial HR computed tomography (CT) scanner by comparing image quality between NRsim‐generated images and actual NR images. NRsim is intended to allow direct comparison CT HR/SHR reconstructions in clinical investigations, without repeating exams. Methods The Aquilion Precision (Canon Medical Systems Corporation) has three modes resulting...
It is common for CT images to be reconstructed differently different clinical examination purposes. difficult conventional filtered backprojection (FBP) methods and standard model-based iterative reconstruction (MBIR) produce a single context-sensitive image without multiple reconstructions. In this article, we address challenge by leveraging the power of deep learning. We propose train convolution neural network reconstruct universal from one FBP image. present new data argumentation method...
Accurate noise model is essential for dose reduction in iterative reconstruction (IR) computed tomography, and has been studied extensively literature. It also important to understand how the can be used at low counts without sacrificing spatial resolution image quality. In this work we present a method reduce data caused by photon count include statistical information into algorithm. Our approach based on computing tables each system. extensive evaluation with experimental shows that...
One of the newest CT application technologies is cardiac synchronized image reconstruction. In this technology, evaluation time-resolution very important. We developed a method measuring in reconstruction, and evaluated various scanning protocols. our experiment, ECG-gated was done by multi-slice (Aquilion16 Super Heart Edition, Toshiba Medical Systems Co., Ltd., Japan). The nominal slice thickness 0.5 mm, rotation time sec. Input heart rate set at 40, 45, 50, 55, 60, 70, 75, 80, 90 bpm,...
The purpose of this study was to compare radiation dose reduction capability for accurate liver tumor measurements a computer-aided volumetry (CADv) software filtered back projection (FBP), hybrid-type iterative reconstruction (IR), mode-based (MBIR), and deep learning (DLR) at phantom study.
In conventional CT, it is difficult to generate consistent organ specific noise and resolution with a single reconstruction kernel. Therefore, necessary in principle reconstruct scan multiple times using different kernels order obtain clinical diagnosis information for anatomies. this paper, we provide deep learning solution which can balance one reconstruction. We propose image convolution neural network (DCNN) trained by feature aware target. It integrates desirable features from...