[Artificial intelligence in cardiovascular radiology : Image acquisition, image reconstruction and workflow optimization]. / Künstliche Intelligenz in der kardiovaskulären Radiologie : Bildakquisition, Bildrekonstruktion und Workflowoptimierung.

BACKGROUND: Artificial intelligence (AI) has the potential to fundamentally change radiology workflow. OBJECTIVES: This review article provides an overview of AI applications in cardiovascular radiology with a focus on image acquisition, image reconstruction, and workflow optimization. MATERIALS AND METHODS: First, established applications of AI are presented for cardiovascular computed tomography (CT) and magnetic resonance imaging (MRI). Building on this, we describe the range of applications that are currently being developed and evaluated. The practical benefits, opportunities, and potential risks of artificial intelligence in cardiovascular imaging are critically discussed. The presentation is based on the relevant specialist literature and our own clinical and scientific experience. RESULTS: AI-based techniques for image reconstruction are already commercially available and enable dose reduction in cardiovascular CT and accelerated image acquisition in cardiac MRI. Postprocessing of cardiovascular CT and MRI examinations can already be considerably simplified using established AI-based segmentation algorithms. In contrast, the practical benefits of many AI applications aimed at the diagnosis of cardiovascular diseases are less evident. Potential risks such as automation bias and considerations regarding cost efficiency should also be taken into account. CONCLUSIONS: In a market characterized by great expectations and rapid technical development, it is important to realistically assess the practical benefits of AI applications for your own hospital or practice.

Influence of Deep Learning Based Image Reconstruction on Quantitative Results of Coronary Artery Calcium Scoring.

RATIONALE AND OBJECTIVES: To assess the impact of deep learning-based imaging reconstruction (DLIR) on quantitative results of coronary artery calcium scoring (CACS) and to evaluate the potential of DLIR for radiation dose reduction in CACS. METHODS: For a retrospective cohort of 100 consecutive patients (mean age 62 ±10 years, 40% female), CACS scans were reconstructed with filtered back projection (FBP), adaptive statistical iterative reconstruction (ASiR-V in 30%, 60% and 90% strength) and DLIR in low, medium and high strength. CACS was quantified semi-automatically and compared between image reconstructions. In a phantom study, a cardiac calcification insert was scanned inside an anthropomorphic thorax phantom at standard dose, 50% dose and 25% dose. FBP reconstructions at standard dose served as the reference standard. RESULTS: In the patient study, DLIR led to a mean underestimation of Agatston score by 3.5, 6.4 and 11.6 points at low, medium and high strength, respectively. This underestimation of Agatston score was less pronounced for DLIR than for ASiR-V. In the phantom study, quantitative CACS results increased with reduced radiation dose and decreased with increasing strength of DLIR. Medium strength DLIR reconstruction at 50% dose reduction and high strength DLIR reconstruction at 75% dose reduction resulted in quantitative CACS results that were comparable to FBP reconstructions at standard dose. CONCLUSION: Compared to FBP as the historical reference standard, DLIR leads to an underestimation of CACS but this underestimation is more moderate than with ASiR-V. DLIR can offset the increase in image noise and calcium score at reduced dose and may thus allow for substantial radiation dose reductions in CACS studies.

Effects of Contagious Respiratory Pathogens on Breath Biomarkers.

Due to their immediate exhalation after generation at the cellular/microbiome levels, exhaled volatile organic compounds (VOCs) may provide real-time information on pathophysiological mechanisms and the host response to infection. In recent years, the metabolic profiling of the most frequent respiratory infections has gained interest as it holds potential for the early, non-invasive detection of pathogens and the monitoring of disease progression and the response to therapy. Using previously unpublished data, randomly selected individuals from a COVID-19 test center were included in the study. Based on multiplex PCR results (non-SARS-CoV-2 respiratory pathogens), the breath profiles of 479 subjects with the presence or absence of flu-like symptoms were obtained using proton-transfer-reaction time-of-flight mass spectrometry. Among 223 individuals, one respiratory pathogen was detected in 171 cases, and more than one pathogen in 52 cases. A total of 256 subjects had negative PCR test results and had no symptoms. The exhaled VOC profiles were affected by the presence of Haemophilus influenzae, Streptococcus pneumoniae, and Rhinovirus. The endogenous ketone, short-chain fatty acid, organosulfur, aldehyde, and terpene concentrations changed, but only a few compounds exhibited concentration changes above inter-individual physiological variations. Based on the VOC origins, the observed concentration changes may be attributed to oxidative stress and antioxidative defense, energy metabolism, systemic microbial immune homeostasis, and inflammation. In contrast to previous studies with pre-selected patient groups, the results of this study demonstrate the broad inter-individual variations in VOC profiles in real-life screening conditions. As no unique infection markers exist, only concentration changes clearly above the mentioned variations can be regarded as indicative of infection or colonization.

Improved image quality in CT pulmonary angiography using deep learning-based image reconstruction.

We investigated the effect of deep learning-based image reconstruction (DLIR) compared to iterative reconstruction on image quality in CT pulmonary angiography (CTPA) for suspected pulmonary embolism (PE). For 220 patients with suspected PE, CTPA studies were reconstructed using filtered back projection (FBP), adaptive statistical iterative reconstruction (ASiR-V 30%, 60% and 90%) and DLIR (low, medium and high strength). Contrast-to-noise ratio (CNR) served as the primary parameter of objective image quality. Subgroup analyses were performed for normal weight, overweight and obese individuals. For patients with confirmed PE (n = 40), we further measured PE-specific CNR. Subjective image quality was assessed independently by two experienced radiologists. CNR was lowest for FBP and enhanced with increasing levels of ASiR-V and, even more with increasing strength of DLIR. High strength DLIR resulted in an additional improvement in CNR by 29-67% compared to ASiR-V 90% (p < 0.05). PE-specific CNR increased by 75% compared to ASiR-V 90% (p < 0.05). Subjective image quality was significantly higher for medium and high strength DLIR compared to all other image reconstructions (p < 0.05). In CT pulmonary angiography, DLIR significantly outperforms iterative reconstruction for increasing objective and subjective image quality. This may allow for further reductions in radiation exposure in suspected PE.

Protocol for visualizing complex volatile metabolomics data in clinical setups using EDaViS software.

Here, we present a protocol for using Early Data Visualization Script, a user-friendly software tool to visualize complex volatile metabolomics data in clinical setups. We describe steps for tabulating data and adjusting visual output to visualize complex time-resolved volatile omics data using simple charts and graphs. We then demonstrate possible modifications by detailing procedures for the adaptation of four basic functions. For complete details on the use and execution of this protocol, please refer to Sukul et al. (2022)1 and Remy et al. (2022).2.

Native myocardial T1 mapping: influence of spatial resolution on quantitative results and reproducibility.

Background: Myocardial mapping techniques can be used to quantitatively assess alterations in myocardial tissue properties. This study aims to evaluate the influence of spatial resolution on quantitative results and reproducibility of native myocardial T1 mapping in cardiac magnetic resonance imaging (MRI). Methods: In this cross-sectional study with prospective data collection between October 2019 and February 2020, 50 healthy adults underwent two identical cardiac MRI examinations in the radiology department on the same day. T1 mapping was performed using a MOLLI 5(3)3 sequence with higher (1.4 mm × 1.4 mm) and lower (1.9 mm × 1.9 mm) in-plane spatial resolution. Global quantitative results of T1 mapping were compared between high-resolution and low-resolution acquisitions using paired t-test. Intra-class correlation coefficient (ICC) and Bland-Altman statistics (absolute and percentage differences as means ± SD) were used for assessing test-retest reproducibility. Results: There was no significant difference between global quantitative results acquired with high vs. low-resolution T1 mapping. The reproducibility of global T1 values was good for high-resolution (ICC: 0.88) and excellent for low-resolution T1 mapping (ICC: 0.95, P=0.003). In subgroup analyses, inferior test-retest reproducibility was observed for high spatial resolution in women compared to low spatial resolution (ICC: 0.71 vs. 0.91, P=0.001) and heart rates >77 bpm (ICC: 0.53 vs. 0.88, P=0.004). Apical segments had higher T1 values and variability compared to other segments. Regional T1 values for basal (ICC: 0.81 vs. 0.89, P=0.023) and apical slices (ICC: 0.86 vs. 0.92, P=0.024) showed significantly higher reproducibility in low-resolution compared to high-resolution acquisitions but without differences for midventricular slice (ICC: 0.91 vs. 0.92, P=0.402). Conclusions: Based on our data, we recommend a spatial resolution on the order of 1.9 mm × 1.9 mm for native myocardial T1 mapping using a MOLLI 5(3)3 sequence at 1.5 T particularly in individuals with higher heart rates and women.

ECG-gated MR angiography at 3T for follow-up after surgery involving the ascending aorta.

We aimed to evaluate electrocardiogram (ECG)-gated MR angiography (MRA) in the follow-up after surgery involving the ascending aorta regarding technical feasibility, image quality, spectrum of findings, and their implications for clinical management. We retrospectively analyzed a cohort of 19 patients (median age 59 years, range 38-79 years), who underwent MRA for follow-up imaging after surgery involving the ascending aorta. Our magnetic resonance imaging protocol consisted of a time-resolved, non-ECG-gated MRA and an ECG-gated MRA performed at 3T. Median examination duration was 25 minutes (range 11-41 minutes). All examinations were assessed by 2 readers in consensus for image quality on a 5-point scale ranging from 1 (non-diagnostic) to 5 (excellent). MRA examinations and patient charts were analyzed for diagnostic findings and their consequences for further management. Subjective image quality was rated as "sufficient" (score 3.1 ±â€…1.1) for the aortic root and as "good" to "excellent" for the ascending aorta (score 4.5 ±â€…0.7), aortic arch (4.5 ±â€…0.7), supra-aortic branches (4.5 ±â€…0.6) and descending aorta (4.6 ±â€…0.7). Abnormal findings were seen in 6 patients (32%) including progressive diameter of remaining aneurysm or dissection (3 patients, 16%) and suture aneurysms (3 patients, 16%). In all 6 of these patients, abnormal findings at MRA had consequences for clinical management. ECG-gated MR angiography at 3T yields good image quality for post-operative surveillance after aortic surgery involving the ascending aorta. This technique may serve as an alternative to computed tomography particularly in younger patients with repeated follow-up.

Improved image quality in transcatheter aortic valve implantation planning CT using deep learning-based image reconstruction.

Background: This study aims to evaluate the impact of a novel deep learning-based image reconstruction (DLIR) algorithm on the image quality in computed tomographic angiography (CTA) for pre-interventional planning of transcatheter aortic valve implantation (TAVI). Methods: We analyzed 50 consecutive patients (median age 80 years, 25 men) who underwent TAVI planning CT on a 256-dectector-row CT. Images were reconstructed with adaptive statistical iterative reconstruction V (ASIR-V) and DLIR. Intravascular image noise, edge sharpness, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were quantified for ascending aorta, descending aorta, abdominal aorta and iliac arteries. Two readers (one radiologist and one interventional cardiologist) scored task-specific subjective image quality on a five-point scale. Results: DLIR significantly reduced median image noise by 29-57% at all anatomical locations (all P<0.001). Accordingly, median SNR improved by 44-133% (all P<0.001) and median CNR improved by 44-125% (all P<0.001). DLIR significantly improved subjective image quality for all four pre-specified TAVI-specific tasks (measuring the annulus, assessing valve morphology and calcifications, the coronary ostia, and the suitability of the aorto-iliac access route) for both the radiologist and the interventional cardiologist (P≤0.001). Measurements of the aortic annulus circumference, area and diameter did not differ between ASIR-V and DLIR reconstructions (all P>0.05). Conclusions: DLIR significantly improves objective and subjective image quality in TAVI planning CT compared to a state-of-the-art iterative reconstruction without affecting measurements of the aortic annulus. This may provide an opportunity for further reductions in contrast medium volume in this population.

Profiling of exhaled volatile organics in the screening scenario of a COVID-19 test center.

Breath volatile organics (VOCs) may provide immediate information on infection mechanisms and host response. We conducted real-time mass spectrometry-based breath profiling in 708 non-preselected consecutive subjects in the screening scenario of a COVID-19 test center. Recruited subjects were grouped based on PCR-confirmed infection status and presence or absence of flu-like symptoms. Exhaled VOC profiles of SARS-CoV-2-positive cases (n = 36) differed from healthy (n = 256) and those with other respiratory infections (n = 416). Concentrations of most VOCs were suppressed in COVID-19. VOC concentrations also differed between symptomatic and asymptomatic cases. Breath markers mirror effects of infections onto host's cellular metabolism and microbiome. Downregulation of specific VOCs was attributed to suppressive effects of SARS-CoV-2 onto gut or pulmonary microbial metabolism. Breath analysis holds potential for monitoring SARS-CoV-2 infections rather than for primary diagnosis. Breath profiling offers unconventional insight into host-virus cross-talk and infection microbiology and enables non-invasive assessment of disease manifestation.

Volatile scents of influenza A and S. pyogenes (co-)infected cells.

Influenza A is a serious pathogen itself, but often leads to dangerous co-infections in combination with bacterial species such as Streptococcus pyogenes. In comparison to classical biochemical methods, analysis of volatile organic compounds (VOCs) in headspace above cultures can enable destruction free monitoring of metabolic processes in vitro. Thus, volatile biomarkers emitted from biological cell cultures and pathogens could serve for monitoring of infection processes in vitro. In this study we analysed VOCs from headspace above (co)-infected human cells by using a customized sampling system. For investigating the influenza A mono-infection and the viral-bacterial co-infection in vitro, we analysed VOCs from Detroit cells inoculated with influenza A virus and S. pyogenes by means of needle-trap micro-extraction (NTME) and gas chromatography mass spectrometry (GC-MS). Besides the determination of microbiological data such as cell count, cytokines, virus load and bacterial load, emissions from cell medium, uninfected cells and bacteria mono-infected cells were analysed. Significant differences in emitted VOC concentrations were identified between non-infected and infected cells. After inoculation with S. pyogenes, bacterial infection was mirrored by increased emissions of acetaldehyde and propanal. N-propyl acetate was linked to viral infection. Non-destructive monitoring of infections by means of VOC analysis may open a new window for infection research and clinical applications. VOC analysis could enable early recognition of pathogen presence and in-depth understanding of their etiopathology.

Differences in the Emission of Volatile Organic Compounds (VOCs) between Non-Differentiating and Adipogenically Differentiating Mesenchymal Stromal/Stem Cells from Human Adipose Tissue.

Metabolic characterization of human adipose tissue-derived mesenchymal stromal/stem cells (ASCs) is of importance in stem cell research. The monitoring of the cell status often requires cell destruction. An analysis of volatile organic compounds (VOCs) in the headspace above cell cultures might be a noninvasive and nondestructive alternative to in vitro analysis. Furthermore, VOC analyses permit new insight into cellular metabolism due to their view on volatile compounds. Therefore, the aim of our study was to compare VOC profiles in the headspace above nondifferentiating and adipogenically differentiating ASCs. To this end, ASCs were cultivated under nondifferentiating and adipogenically differentiating conditions for up to 21 days. At different time points the headspace samples were preconcentrated by needle trap micro extraction and analyzed by gas chromatography/mass spectrometry. Adipogenic differentiation was assessed at equivalent time points. Altogether the emissions of 11 VOCs showed relevant changes and were analyzed in more detail. A few of these VOCs, among them acetaldehyde, were significantly different in the headspace of adipogenically differentiating ASCs and appeared to be linked to metabolic processes. Furthermore, our data indicate that VOC headspace analysis might be a suitable, noninvasive tool for the metabolic monitoring of (mesenchymal stem) cells in vitro.