Contrast-enhanced mammography showed high diagnostic performance in breast cancer detection, particularly when lesion morphologic characteristics and enhancement from both low-energy and recombined... Background Contrast-enhanced mammography (CEM) is a promising technique for breast cancer detection, but conflicting results have been reported in previous meta-analyses. Purpose To perform a syste...

In the mid-1990s, the identification of BRCA1/2 genes for breast cancer susceptibility led to testing breast MRI accuracy in screening women at increased risk. From 2000 onwards, ten intraindividual comparative studies showed the marked superiority of MRI: the sensitivity ranged 25−58% for mammography, 33−52% for ultrasound, 48−67% for mammography plus ultrasound, and 71−100% for MRI; specificity 93–100%, 91–98%, 89–98%, and 81–98%, respectively. Based on the available evidence, in 2006–2007, the UK National Institute for Clinical Excellence and the American Cancer Society recommended MRI screening of high-risk women, followed by other international guidelines. Despite evidence-based medicine ideally requiring randomised controlled trials (RCTs) for policy changes regarding screening procedures, breast MRI for high-risk screening was adopted in many countries worldwide. In 2019, the results of the “DENSE” RCT were published in favour of breast MRI screening of women with extremely dense breasts compared to mammography alone, showing a reduction of more than 80% of the interval cancer rate in women who attended MRI screening. Even though international recommendations in favour of this practice were issued, substantial obstacles still prevent health systems from adopting breast MRI for screening women with extremely dense breasts. A paradox is evident: we adopted a screening procedure without evidence from RCTs, and now that we have this level-1 evidence for the same procedure, we fail to do so. This critical review tries to explain the differences between the two cases, as examples of the complex pathways of translating radiological research into everyday practice.Critical relevance statement The high-level evidence in favour of breast MRI screening of women with extremely dense breasts is failing to persuade policy makers to translate this into clinical practice.Key points• Breast MRI screening of high-risk women was adopted on basis of the evidence provided by test accuracy comparative studies showing an MRI performance greatly superior to that of mammography.• Breast MRI screening of women with extremely dense breasts has not been adopted although the evidence of a large reduction in interval cancer rate from a RCT.• We illustrate the differences between the two cases, as an example of the complex ways of translation of radiological research in clinical practice according to the EBM theory. Graphical Abstract

“Just Accepted” papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review ...

Pulmonary parenchymal and vascular damage are frequently reported in COVID-19 patients and can be assessed with unenhanced chest computed tomography (CT), widely used as a triaging exam. Integrating clinical data, chest CT features, and CT-derived vascular metrics, we aimed to build a predictive model of in-hospital mortality using univariate analysis (Mann–Whitney U test) and machine learning models (support vectors machines (SVM) and multilayer perceptrons (MLP)). Patients with RT-PCR-confirmed SARS-CoV-2 infection and unenhanced chest CT performed on emergency department admission were included after retrieving their outcome (discharge or death), with an 85/15% training/test dataset split. Out of 897 patients, the 229 (26%) patients who died during hospitalization had higher median pulmonary artery diameter (29.0 mm) than patients who survived (27.0 mm, p < 0.001) and higher median ascending aortic diameter (36.6 mm versus 34.0 mm, p < 0.001). SVM and MLP best models considered the same ten input features, yielding a 0.747 (precision 0.522, recall 0.800) and 0.844 (precision 0.680, recall 0.567) area under the curve, respectively. In this model integrating clinical and radiological data, pulmonary artery diameter was the third most important predictor after age and parenchymal involvement extent, contributing to reliable in-hospital mortality prediction, highlighting the value of vascular metrics in improving patient stratification.