Screening high-risk patients with computed tomography angiography

Multimodal deep learning of fundus abnormalities and traditional risk factors for cardiovascular risk prediction

Cardiovascular disease (CVD), the leading cause of death globally, is associated with complicated underlying risk factors. We develop an artificial intelligence model to identify CVD using multimodal data, including clinical risk factors and fundus photographs from the Samsung Medical Center (SMC) for development and internal validation and from the UK Biobank for external validation. The multimodal model achieves an area under the receiver operating characteristic curve (AUROC) of 0.781 (95% confidence interval [CI] 0.766-0.798) in the SMC and 0.872 (95% CI 0.857-0.886) in the UK Biobank. We further observe a significant association between the incidence of CVD and the predicted risk from at-risk patients in the UK Biobank (hazard ratio [HR] 6.28, 95% CI 4.72-8.34). We visualize the importance of individual features in photography and traditional risk factors. The results highlight that non-invasive fundus photography can be a possible predictive marker for CVD.

Nanoparticle contrast agents for computed tomography: a focus on micelles

Computed tomography (CT) is an X-ray-based whole-body imaging technique that is widely used in medicine. Clinically approved contrast agents for CT are iodinated small molecules or barium suspensions. Over the past seven years there has been a great increase in the development of nanoparticles as CT contrast agents. Nanoparticles have several advantages over small molecule CT contrast agents, such as long blood-pool residence times and the potential for cell tracking and targeted imaging applications. Furthermore, there is a need for novel CT contrast agents, owing to the growing population of renally impaired patients and patients hypersensitive to iodinated contrast. Micelles and lipoproteins, a micelle-related class of nanoparticle, have notably been adapted as CT contrast agents. In this review we discuss the principles of CT image formation and the generation of CT contrast. We discuss the progress in developing nontargeted, targeted and cell tracking nanoparticle CT contrast agents. We feature agents based on micelles and used in conjunction with spectral CT. The large contrast agent doses needed will necessitate careful toxicology studies prior to clinical translation. However, the field has seen tremendous advances in the past decade and we expect many more advances to come in the next decade.

Submillisievert coronary computed tomography angiography using adaptive statistical iterative reconstruction - a new reality

Coronary computed tomography angiography (CCTA) is becoming an increasingly robust tool in the assessment and exclusion of coronary artery disease. Multiple recent studies have raised concerns regarding the radiation dose exposure of CCTA. A novel approach to dose reduction in CCTA using adaptive statistical iterative reconstruction, resulting in a submillisievert CCTA examination, is described. To the authors' knowledge, the present report describes the first submillisievert study performed in Canada. The ability to perform a diagnostic CCTA with such a low dose challenges the role of coronary calcium scoring and will likely have implications for the future use of this test.