Objective: To investigate the diagnostic performance of deep learning (DL)-based vascular extraction and stenosis detection technology in assessing coronary artery disease (CAD). Methods: The diagnostic performance of DL technology was evaluated by retrospective analysis of coronary computed tomography angiography in 124 suspected CAD patients, using invasive coronary angiography as reference standard. Lumen diameter stenosis ≥50% was considered obstructive, and the diagnostic performances were evaluated at per-patient, per-vessel and per-segment levels. The diagnostic performances between DL model and reader model were compared by the areas under the receiver operating characteristics curves (AUCs). Results: In patient-based analysis, AUC of 0.78 was obtained by DL model to detect obstructive CAD [sensitivity of 94%, specificity of 63%, positive predictive value of 94%, and negative predictive value of 59%], While AUC by reader model was 0.74 (sensitivity of 97%, specificity of 50%, positive predictive value of 93%, negative predictive value of 73%). In vessel-based analysis, the AUCs of DL model and reader model were 0.87 and 0.89 respectively. In segment-based analysis, the AUCs of 0.84 and 0.89 were obtained by DL model and reader model respectively. It took 0.47 min to analyze all segments per patient by DL model, which is significantly less than reader model (29.65 min) (p < 0.001). Conclusion: The DL technology can accurately and effectively identify obstructive CAD, with less time-consuming, and it could be a reliable diagnostic tool to detect CAD. Advances in knowledge: The DL technology has valuable prospect with the diagnostic ability to detect CAD.

Bimodal imaging has captured increasing interests due to its complementary characteristics of two kinds of imaging modalities. Among the various dual-modal imaging techniques, MR/fluorescence imaging has been widely studied owing to its high 3D resolution and sensitivity. There is, however, still a strong demand to construct biocompatible MR/fluorescence contrast agents with near-infrared (NIR) fluorescent emissions and high relaxivities. In this study, BSA-DTPA(Gd) derived from bovine serum albumin (BSA) as a novel kind of biotemplate is employed for biomineralization of paramagnetic NIR Ag2S quantum dots (denoted as Ag2S@BSA-DTPA(Gd) pQDs). This synthetic strategy is found to be bioinspired, environmentally benign, and straightforward. The obtained Ag2S@BSA-DTPA(Gd) pQDs have fine sizes (ca. 6 nm) and good colloidal stability. They exhibit unabated NIR fluorescent emission (ca. 790 nm) as well as high longitudinal relaxivity (r1 = 12.6 mM(-1) s(-1)) compared to that of commercial Magnevist (r1 = 3.13 mM(-1) s(-1)). In vivo tumor-bearing MR and fluorescence imaging both demonstrate that Ag2S@BSA-DTPA(Gd) pQDs have pronounced tiny tumor targeting capability. In vitro and in vivo toxicity study show Ag2S@BSA-DTPA(Gd) pQDs are biocompatible. Also, biodistribution analysis indicates they can be cleared from body mainly via liver metabolism. This protein-mediated biomineralized Ag2S@BSA-DTPA(Gd) pQDs presents great potential as a novel bimodal imaging contrast agent for tiny tumor diagnosis.

In this study, we report novel multifunctional nanoagents for in vivo enzyme-responsive anticancer drug delivery and magnetic resonance imaging (MRI), based on mesoporous silica coated iron oxide nanoparticles (Fe3O4@MSNs). The anticancer drug, DOX, was encapsulated in the porous cavities with a MMP-2 enzyme responsive peptide being covalently linked to the nanoparticles surface. The in vitro experiment results indicated that the enzyme responsive nanoagents own high specificity for controlled drug release in the cell line with high MMP-2 expression. Furthermore, the targeted delivery of the nanoagents to the tumor site purpose has been successfully achieved through magnet-guided nanocarrier accumulation by utilizing the magnetic properties of the Fe3O4 nanocores, which resulted in efficient inhibition of the tumor growth. Additionally, these novel nanoagents can also be used as MRI agent for the real-time diagnosis the tumor treatment process of living animals. Taking the advantages of high specificity, controllable drug release and real-time MRI imaging, we believe these multifunctional nanoagents could also be used as a general platform for the design of stimulus-responsive multifunctional nanomaterials for the aim of accurate diagnosis and efficient treatment of other diseases.

The iodinated contrast agent itself can lead to an increase in the level of DSBs as assessed with γH2AX foci formation, and the application of ICA can amplify DNA damage induced by diagnostic x-ray procedures such as whole abdominal CT.