The purpose of this study was to develop strategies for optimal image reconstruction in multidetector-row cardiac CT and to discuss the results in the context of individual heart rate, cardiac physiology, and technical prerequisite. Sixty-four patients underwent multidetector-row cardiac CT. Depending on the heart rate either a single-segmental reconstruction (SSR) or an adaptive two-segmental reconstruction (ASR) was applied. Image reconstruction was done either antegrade (a) or retrograde (r) in relation to the R-peak. Reconstruction of all data sets was performed at multiple time points within the t-wave/p-wave interval, differing from each other by 50 ms. In addition, each reconstruction was assigned to one of six reconstruction intervals (A-F), each corresponding to a specific event in the cardiac cycle. While no significant time points were found for absolute values, the following interval/reconstruction technique combinations provided significant better image quality: F/r at HR <60 bpm for all coronary segments ( p65 bpm for all segments ( p
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s00330-002-1553-5 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Systematic Review of Hybrid Vision Transformer Architectures for Radiological Image Analysis.
J Imaging Inform Med
January 2025
School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, AZ, USA.
Vision transformer (ViT)and convolutional neural networks (CNNs) each possess distinct strengths in medical imaging: ViT excels in capturing long-range dependencies through self-attention, while CNNs are adept at extracting local features via spatial convolution filters. While ViT may struggle with capturing detailed local spatial information, critical for tasks like anomaly detection in medical imaging, shallow CNNs often fail to effectively abstract global context. This study aims to explore and evaluate hybrid architectures that integrate ViT and CNN to leverage their complementary strengths for enhanced performance in medical vision tasks, such as segmentation, classification, reconstruction, and prediction.
View Article and Find Full Text PDFMultistage deep learning methods for automating radiographic sharp score prediction in rheumatoid arthritis.
Sci Rep
January 2025
Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, MD, USA.
The Sharp-van der Heijde score (SvH) is crucial for assessing joint damage in rheumatoid arthritis (RA) through radiographic images. However, manual scoring is time-consuming and subject to variability. This study proposes a multistage deep learning model to predict the Overall Sharp Score (OSS) from hand X-ray images.
View Article and Find Full Text PDFSquared diffusion-weighted imaging for improving the detection of clinically significant prostate cancer.
Sci Rep
January 2025
Department of Diagnostic and Interventional Radiology, Medical Faculty, University Dusseldorf, Moorenstr. 5, 40225, Dusseldorf, Germany.
Aim of this study was to proof the concept of optimizing the contrast between prostate cancer (PC) and healthy tissue by DWI post-processing using a quadrature method. DWI post-processing was performed on 30 patients (median age 67 years, prostate specific antigen 8.0 ng/ml) with PC and clear MRI findings (PI-RADS 4 and 5).
View Article and Find Full Text PDFMulti scale multi attention network for blood vessel segmentation in fundus images.
Sci Rep
January 2025
Department of Data Science and Artificial Intelligence, Sunway University, 47500, Petaling Jaya, Selangor Darul Ehsan, Malaysia.
Precise segmentation of retinal vasculature is crucial for the early detection, diagnosis, and treatment of vision-threatening ailments. However, this task is challenging due to limited contextual information, variations in vessel thicknesses, the complexity of vessel structures, and the potential for confusion with lesions. In this paper, we introduce a novel approach, the MSMA Net model, which overcomes these challenges by replacing traditional convolution blocks and skip connections with an improved multi-scale squeeze and excitation block (MSSE Block) and Bottleneck residual paths (B-Res paths) with spatial attention blocks (SAB).
View Article and Find Full Text PDFSTAIG: Spatial transcriptomics analysis via image-aided graph contrastive learning for domain exploration and alignment-free integration.
Nat Commun
January 2025
Department of Computational Biology and Medical Science, Graduate School of Frontier Sciences, the University of Tokyo, Tokyo, Japan.
Spatial transcriptomics is an essential application for investigating cellular structures and interactions and requires multimodal information to precisely study spatial domains. Here, we propose STAIG, a deep-learning model that integrates gene expression, spatial coordinates, and histological images using graph-contrastive learning coupled with high-performance feature extraction. STAIG can integrate tissue slices without prealignment and remove batch effects.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!