During the last 20 years, cardiac imaging has drastically evolved. Positron emission tomography (PET), fast three-dimensional (3D) imaging with the latest generations of echocardiography & multi-detector computed tomography (CT), stress perfusion assessed by magnetic resonance imaging (MRI), blood flow analysis using four-dimensional (4D) flow MRI, all these techniques offer new trends for optimal noninvasive functional cardiac imaging. Dynamic functional imaging is obtained by acquiring images of the heart at different phases of the cardiac cycle, allowing assessment of cardiac motion, function, and perfusion. Between CT and Cardiac MRI (CMR), CMR has the best temporal resolution, which is suitable for functional imaging while cardiac CT provides higher spatial resolution with isotropic data that have an identical resolution in the three dimensions of the space. The latest generations of CT scanners enable whole heart assessment in one beat, offering also an acceptable temporal resolution with the possibility to display the images in a dynamic mode. Another rapidly growing technique using functional and molecular imaging for the assessment of biological and metabolic pathways is the PET using radio-labeled tracers. Meanwhile, the oldest cardiac imaging tool with doppler ultrasound technology has never stopped evolving. Echocardiography today performs 3D imaging, stress perfusion, and myocardial strain assessment, with high temporal resolution. It still is the first line and more accessible exam for the patient. These different modalities are complementary and may be even combined into PET-CT or PET-MRI. The ability to combine the functional/molecular data with anatomical images may implement a new dimension to our diagnostic tools.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.lpm.2022.104119 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Integrating Retinal Segmentation Metrics with Machine Learning for Predictions from Mouse SD-OCT Scans.
Curr Eye Res
January 2025
Department of Ophthalmology, Edward S. Harkness Eye Institute, Columbia University, Vagelos College of Physicians and Surgeons, New York, NY, USA.
Purpose: This study aimed to initially test whether machine learning approaches could categorically predict two simple biological features, mouse age and mouse species, using the retinal segmentation metrics.
Methods: The retinal layer thickness data obtained from C57BL/6 and DBA/2J mice were processed for machine learning after segmenting mouse retinal SD-OCT scans. Twenty-two models were trained to predict the mouse groups.
Multiplexed single-cell imaging reveals diverging subpopulations with distinct senescence phenotypes during long-term senescence induction.
Geroscience
January 2025
Lineberger Comprehensive Cancer Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA.
Cellular senescence is a phenotypic state that contributes to the progression of age-related disease through secretion of pro-inflammatory factors known as the senescence-associated secretory phenotype (SASP). Understanding the process by which healthy cells become senescent and develop SASP factors is critical for improving the identification of senescent cells and, ultimately, understanding tissue dysfunction. Here, we reveal how the duration of cellular stress modulates the SASP in distinct subpopulations of senescent cells.
View Article and Find Full Text PDFPerformance of Radiomics-based machine learning and deep learning-based methods in the prediction of tumor grade in meningioma: a systematic review and meta-analysis.
Neurosurg Rev
January 2025
Department of Neurosurgery, Mount Sinai Hospital, Icahn School of Medicine, New York City, NY, USA.
Currently, the World Health Organization (WHO) grade of meningiomas is determined based on the biopsy results. Therefore, accurate non-invasive preoperative grading could significantly improve treatment planning and patient outcomes. Considering recent advances in machine learning (ML) and deep learning (DL), this meta-analysis aimed to evaluate the performance of these models in predicting the WHO meningioma grade using imaging data.
View Article and Find Full Text PDFCT angiography of acute aortic syndrome in patients with chronic kidney disease.
Int J Cardiovasc Imaging
January 2025
Department of Clinical Radiology, AHEPA University Hospital of Thessaloniki, Aristotle University of Thessaloniki, Thessaloniki, Greece.
The term acute aortic syndrome (AAS) refers to a range of different entities, including dissection, intramural haematoma and penetrating atherosclerotic ulcer. Patients with chronic renal disease and particularly those with dominant polycystic kidney disease are susceptible to this pathology, given the underlying renal arteriopathy and hypertension. Imaging plays a crucial role in diagnosing, grading and guiding management of these patients, with computed tomography angiography (CTA) being on the frontline.
View Article and Find Full Text PDFDeep Convolutional Neural Networks on Multiclass Classification of Three-Dimensional Brain Images for Parkinson's Disease Stage Prediction.
J Imaging Inform Med
January 2025
Department of Anesthesiology, E-Da Cancer Hospital, I-Shou University, Kaohsiung, Taiwan.
Parkinson's disease (PD), a degenerative disorder of the central nervous system, is commonly diagnosed using functional medical imaging techniques such as single-photon emission computed tomography (SPECT). In this study, we utilized two SPECT data sets (n = 634 and n = 202) from different hospitals to develop a model capable of accurately predicting PD stages, a multiclass classification task. We used the entire three-dimensional (3D) brain images as input and experimented with various model architectures.
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!