Activity

To assess the feasibility of a proposed pancreatic protocol CT generated from portal-venous phase (PVP) dual-energy CT (DECT) acquisition and its impact on image quality, lesion conspicuity, and arterial visualization/involvement.

We included 111 patients (mean age, 66.8 years) who underwent pancreatic protocol DECT (pancreatic phase, PP, and PVP). The original DECT acquisition was used to create two data sets-standard protocol (50 keV PP/65 keV PVP) and proposed protocol (40 keV/65 keV PVP). Three reviewers evaluated the two data sets for image quality, lesion conspicuity, and arterial visualization/involvement using a 5-point scale. The signal-to-noise ratio (SNR) of pancreas and lesion-to-pancreas contrast-to-noise ratio (CNR) was calculated. Qualitative scores, quantitative parameters, and dose-length product (DLP) were compared between standard and proposed protocols.

The image quality, SNR of pancreas, and lesion-to-pancreas CNR of the standard and proposed protocol were comparable (p = 0.11-1.00)nventional protocol.

• The lesion conspicuity for focal pancreatic lesions was comparable between the proposed protocol and standard dual-phase pancreatic protocol CT. • Qualitative and quantitative image assessments were almost comparable between two protocols. • The radiation dose of a proposed protocol showed a projected 42% reduction from the conventional protocol.

Radiologists’ perception is likely to influence the adoption of artificial intelligence (AI) into clinical practice. RMC-7977 We investigated knowledge and attitude towards AI by radiologists and residents in Europe and beyond.

Between April and July 2019, a survey on fear of replacement, knowledge, and attitude towards AI was accessible to radiologists and residents. The survey was distributed through several radiological societies, author networks, and social media. Independent predictors of fear of replacement and a positive attitude towards AI were assessed using multivariable logistic regression.

The survey was completed by 1,041 respondents from 54 mostly European countries. Most respondents were male (n = 670, 65%), median age was 38 (24-74) years, n = 142 (35%) residents, and n = 471 (45%) worked in an academic center. Basic AI-specific knowledge was associated with fear (adjusted OR 1.56, 95% CI 1.10-2.21, p = 0.01), while intermediate AI-specific knowledge (adjusted OR 0.40, 95% CI 0.20-0.80, p = 0.01)n radiology training curricula to help facilitate its clinical adoption.

• Forty-eight percent of radiologists and residents have an open and proactive attitude towards artificial intelligence (AI), while 38% fear of replacement by AI. • Intermediate and advanced AI-specific knowledge levels may enhance adoption of AI in clinical practice, while rudimentary knowledge levels appear to be inhibitive. • AI should be incorporated in radiology training curricula to help facilitate its clinical adoption.

Due to its high sensitivity, DCE MRI of the breast (bMRI) is increasingly used for both screening and assessment purposes. The high number of detected lesions poses a significant logistic challenge in clinical practice. The aim was to evaluate a temporally and spatially resolved (4D) radiomics approach to distinguish benign from malignant enhancing breast lesions and thereby avoid unnecessary biopsies.

This retrospective study included consecutive patients with MRI-suspicious findings (BI-RADS 4/5). Two blinded readers analyzed DCE images using a commercially available software, automatically extracting BI-RADS curve types and pharmacokinetic enhancement features. After principal component analysis (PCA), a neural network-derived A.I. classifier to discriminate benign from malignant lesions was constructed and tested using a random split simple approach. The rate of avoidable biopsies was evaluated at exploratory cutoffs (C

, 100%, and C

, ≥ 95% sensitivity).

Four hundred seventy (295 malignant) lesioellent diagnostic performance as measured by the area under the ROC curve with 80.6% (training dataset) and 83.5% (testing dataset). • Testing the resulting A.I. classifier showed the potential to lower the number of unnecessary biopsies of benign breast lesions by up to 36.2%, p < .001 at the cost of up to 4.5% (n = 4) false negative low-risk cancers.

• Principal component analysis of the extracted volumetric and temporally resolved (4D) DCE markers favored pharmacokinetic modeling derived features. • An A.I. classifier based on 86 extracted DCE features achieved a good to excellent diagnostic performance as measured by the area under the ROC curve with 80.6% (training dataset) and 83.5% (testing dataset). • Testing the resulting A.I. classifier showed the potential to lower the number of unnecessary biopsies of benign breast lesions by up to 36.2%, p less then .001 at the cost of up to 4.5% (n = 4) false negative low-risk cancers.

Impaired brain cortices contribute significantly to the pathophysiological mechanisms of post-traumatic olfactory dysfunction (PTOD). This study aimed to use

F-fluorodeoxyglucose positron emission tomography/computed tomography (

F-FDG PET/CT) to measure cerebral cortices’ metabolism activity and then to explore their associations with olfaction in patients with PTOD.

Ethics committee-approved prospective studies included 15 patients with post-traumatic anosmia and 11 healthy volunteers. Olfactory function was assessed using the Sniffin’ Sticks. Participants underwent

F-FDG PET/CT scan and the image data were collected for the voxel-based whole brain analysis. Furthermore, the standardized uptake value ratio (SUVR) of the whole brain regions was measured and correlated with olfactory function.

Patients with post-traumatic anosmia showed significantly reduced glucose metabolism in bilateral rectus, bilateral superior and medial orbitofrontal cortex (OFC), bilateral thalamus, left hippocampus and parhe retained olfactory function were identified. The preliminary results further support the potential use of PET imaging for precisely assessing brain metabolism in patients with PTOD.

In recent studies, a 5-stage cardiac damage classification in severe aortic stenosis (AS) based on echocardiographic parameters has shown to provide predictive value regarding clinical outcome. The objective of this study was to investigate the prognostic impact of a cardiac damage classification based on invasive hemodynamics in patients with AS undergoing transcatheter aortic valve replacement (TAVR).

A total of 1400 patients with symptomatic AS and full invasive hemodynamic assessment before TAVR were included. Patients were categorized according to their cardiac damage stage into five groups that are defined as stage 0, no cardiac damage; stage 1, left ventricular damage; stage 2, left atrial and/or mitral valve damage; stage 3, pulmonary vasculature and/or tricuspid valve damage; stage 4, right ventricular damage.

9.9% patients were classified as stage 0, 23.6% as stage 1, the majority of patients as stage 2 (33.5%), 23.1% as stage 3 and 10% as stage 4. One- and 4-year mortality were 10.1%/29.5% in stage 0, 16.