Search

Purpose To assess whether high temporal/spatial resolution GRASP MRI acquired during routine clinical imaging can identify several degrees of renal function impairment referenced against renal dynamic scintigraphy. Methods This retrospective study consists of method development and method verification parts. During method development, patients subject to renal imaging using gadoterate meglumine and GRASP post-contrast MRI technique (TR/TE 3.3/1.6 ms; FoV320 × 320 mm; FA12°; Voxel1.1 × 1.1x2.5 mm) were matched into four equally-sized renal function groups (no-mild-moderate-severe impairment) according to their laboratory-determined estimated glomerular filtration rates (eGFR); 60|120 patients|kidneys were included. Regions-of-interest (ROIs) were placed on cortices, medullary pyramids and collecting systems of bilateral kidneys. Cortical perfusion, tubular concentration and collecting system excretion were determined as TimeCortex=Pyramid(sec), SlopeTubuli (sec−1), and TimeCollecting System (sec), respectively, and were measured by a combination of extraction of time intensity curves and respective quantitative parameters. For method verification, patients subject to GRASP MRI and renal dynamic scintigraphy (99mTc-MAG3, 100 MBq/patient) were matched into three renal function groups (no-mild/moderate-severe impairment). Split renal function parameters post 1.5–2.5 min as well as MAG3 TER were correlated with time intensity parameters retrieved using GRASP technique; 15|30 patients|kidneys were included. Results Method development showed differing values for TimeCortex=Pyramid(71|75|93|122 s), SlopeTubuli(2.6|2.1|1.3|0.5 s−1) and TimeCollecting System(90|111|129|139 s) for the four renal function groups with partial significant tendencies (several p-values Conclusion High temporal and spatial resolution GRASP MR imaging allows to identify several degrees of renal function impairment using routine clinical imaging with a high degree of accuracy.

MRI-targeted prostate biopsy improves detection of clinically significant prostate cancer (PCa). However, up to 70% of PCa lesions display intralesional tumor heterogeneity. Current target sampling strategies do not yet adequately account for this finding. This prospective study included 118 patients who underwent transperineal robotic assisted biopsy of the prostate. We identified a total of 58 PCa-positive PI-RADS lesions. We compared diagnostic accuracy of a target-saturation biopsy strategy to accuracy of single, two, or three randomly selected targeted biopsy cores and analysed potential clinical implications. Intralesional detection of clinically significant cancer (ISUP ≥ 2) was 78.3% for target-saturation biopsy and 39.1%, 52.2%, and 67.4% for one, two, and three targeted cores, respectively. Target-saturation biopsies led to a more accurate characterization of PCa in terms of Gleason score and reduced rates of significant cancer missed. Compared to one, two, and three targeted biopsy cores, target-saturation biopsies led to intensified staging procedures in 21.7%, 10.9, and 8.7% of patients, and ultimately to a potential change in therapy in 39.1%, 26.1%, and 10.9% of patients. This work presents the concept of robotic-assisted target saturation biopsy. This technique has the potential to improve diagnostic accuracy and thus individual staging procedures and treatment decisions.

Objectives: The objectives of this study were to assess patient comfort when imaged on a newly introduced 0.55T low-field magnetic resonance (MR) scanner system with a wider bore opening compared to a conventional 1.5T MR scanner system. Materials and Methods: In this prospective study, fifty patients (mean age: 66.2 ± 17.0 years, 22 females, 28 males) underwent subsequent magnetic resonance imaging (MRI) examinations with matched imaging protocols at 0.55T (MAGNETOM FreeMax, Siemens Healthineers; Erlangen, Germany) and 1.5T (MAGNETOM Avanto Fit, Siemens Healthineers; Erlangen, Germany) on the same day. MRI performed between 05/2021 and 07/2021 was included for analysis. The 0.55T MRI system had a bore opening of 80 cm, while the bore diameter of the 1.5T scanner system was 60 cm. Four patient groups were defined by imaged body regions: (1) cranial or cervical spine MRI using a head/neck coil (n = 27), (2) lumbar or thoracic spine MRI using only the in-table spine coils (n = 10), (3) hip MRI using a large flex coil (n = 8) and (4) upper- or lower-extremity MRI using small flex coils (n = 5). Following the MRI examinations, patients evaluated (1) sense of space, (2) noise level, (3) comfort, (4) coil comfort and (5) overall examination impression on a 5-point Likert-scale (range: 1= “much worse” to 5 = “much better”) using a questionnaire. Maximum noise levels of all performed imaging studies were measured in decibels (dB) by a sound level meter placed in the bore center. Results: Sense of space was perceived to be “better” or “much better” by 84% of patients for imaging examinations performed on the 0.55T MRI scanner system (mean score: 4.34 ± 0.75). Additionally, 84% of patients rated noise levels as “better” or “much better” when imaged on the low-field scanner system (mean score: 3.90 ± 0.61). Overall sensation during the imaging examination at 0.55T was rated as “better” or “much better” by 78% of patients (mean score: 3.96 ± 0.70). Quantitative assessment showed significantly reduced maximum noise levels for all 0.55T MRI studies, regardless of body region compared to 1.5T, i.e., brain MRI (83.8 ± 3.6 dB vs. 89.3 ± 5.4 dB; p = 0.04), spine MRI (83.7 ± 3.7 dB vs. 89.4 ± 2.6 dB; p = 0.004) and hip MRI (86.3 ± 5.0 dB vs. 89.1 ± 1.4 dB; p = 0.04). Conclusions: Patients perceived 0.55T new-generation low-field MRI to be more comfortable than conventional 1.5T MRI, given its larger bore opening and reduced noise levels during image acquisition. Therefore, new concepts regarding bore design and noise level reduction of MR scanner systems may help to reduce patient anxiety and improve well-being when undergoing MR imaging.

Aims To present and validate a fully automated, deep learning (DL)-based branch-wise coronary artery calcium (CAC) scoring algorithm on a multi-centre dataset. Methods and results We retrospectively included 1171 patients referred for a CAC computed tomography examination. Total CAC scores for each case were manually evaluated by a human reader. Next, each dataset was fully automatically evaluated by the DL-based software solution with output of the total CAC score and sub-scores per coronary artery (CA) branch [right coronary artery (RCA), left main (LM), left anterior descending (LAD), and circumflex (CX)]. Three readers independently manually scored the CAC for all CA branches for 300 cases from a single centre and formed the consensus using a majority vote rule, serving as the reference standard. Established CAC cut-offs for the total Agatston score were used for risk group assignments. The performance of the algorithm was evaluated using metrics for risk class assignment based on total Agatston score, and unweighted Cohen’s Kappa for branch label assignment. The DL-based software solution yielded a class accuracy of 93% (1085/1171) with a sensitivity, specificity, and accuracy of detecting non-zero coronary calcium being 97%, 93%, and 95%. The overall accuracy of the algorithm for branch label classification was 94% (LM: 89%, LAD: 91%, CX: 93%, RCA: 100%) with a Cohen's kappa of k = 0.91. Conclusion Our results demonstrate that fully automated total and vessel-specific CAC scoring is feasible using a DL-based algorithm. There was a high agreement with the manually assessed total CAC from a multi-centre dataset and the vessel-specific scoring demonstrated consistent and reproducible results.

To evaluate the performance of an AI-powered algorithm for the automatic detection of pulmonary embolism (PE) on chest computed tomography pulmonary angiograms (CTPAs) on a large dataset. We retrospectively identified all CTPAs conducted at our institution in 2017 (n = 1499). Exams with clinical questions other than PE were excluded from the analysis (n = 34). The remaining exams were classified into positive (n = 232) and negative (n = 1233) for PE based on the final written reports, which defined the reference standard. The fully anonymized 1-mm series in soft tissue reconstruction served as input for the PE detection prototype algorithm that was based on a deep convolutional neural network comprising a Resnet architecture. It was trained and validated on 28,000 CTPAs acquired at other institutions. The result series were reviewed using a web-based feedback platform. Measures of diagnostic performance were calculated on a per patient and a per finding level. The algorithm correctly identified 215 of 232 exams positive for pulmonary embolism (sensitivity 92.7%; 95% confidence interval [CI] 88.3–95.5%) and 1178 of 1233 exams negative for pulmonary embolism (specificity 95.5%; 95% CI 94.2–96.6%). On a per finding level, 1174 of 1352 findings marked as embolus by the algorithm were true emboli. Most of the false positive findings were due to contrast agent–related flow artifacts, pulmonary veins, and lymph nodes. The AI prototype algorithm we tested has a high degree of diagnostic accuracy for the detection of PE on CTPAs. Sensitivity and specificity are balanced, which is a prerequisite for its clinical usefulness. • An AI-based prototype algorithm showed a high degree of diagnostic accuracy for the detection of pulmonary embolism on CTPAs. • It can therefore help clinicians to automatically prioritize exams with a high suspection of pulmonary embolism and serve as secondary reading tool. • By complementing traditional ways of worklist prioritization in radiology departments, this can speed up the diagnostic and therapeutic workup of patients with pulmonary embolism and help to avoid false negative calls.

To assess if adding perfusion information from dynamic contrast-enhanced (DCE MRI) acquisition schemes with high spatiotemporal resolution to T2w/DWI sequences as input features for a gradient boosting machine (GBM) machine learning (ML) classifier could better classify prostate cancer (PCa) risk groups than T2w/DWI sequences alone. One hundred ninety patients (68 ± 9 years) were retrospectively evaluated at 3T MRI for clinical suspicion of PCa. Included were 201 peripheral zone (PZ) PCa lesions. Histopathological confirmation on fusion biopsy was matched with normal prostate parenchyma contralaterally. Biopsy results were grouped into benign tissue and low-, intermediate-, and high-risk groups (Gleason sum score 6, 7, and > 7, respectively). DCE MRI was performed using golden-angle radial sparse MRI. Perfusion maps (Ktrans, Kep, Ve), apparent diffusion coefficient (ADC), and absolute T2w signal intensity were determined and used as input features for building two ML models: GBM with/without perfusion maps. Areas under the receiver operating characteristic curve (AUC) values for correlated models were compared. For the classification of benign vs. malignant and intermediate- vs. high-grade PCa, perfusion information added relevant information (AUC values 1 vs. 0.953 and 0.909 vs. 0.700, p

BACKGROUND: To investigate if supervised machine learning (ML) classifiers would be able to predict clinically significant cancer (sPC) from a set of quantitative image-features and to compare these results with established PI-RADS v2 assessment scores. METHODS: We retrospectively included 201, histopathologically-proven, peripheral zone (PZ) prostate cancer lesions. Gleason scores ≤3+3 were considered as clinically insignificant (inPC) and Gleason scores ≥3+4 as sPC and were encoded in a binary fashion, serving as ground-truth. MRI was performed at 3T with high spatiotemporal resolution DCE using Golden-angle RAdial SParse (GRASP) MRI. Perfusion maps (Ktrans, Kep, Ve), apparent diffusion coefficient (ADC), and absolute T2-signal intensities (SI) were determined in all lesions and served as input parameters for four supervised ML models: Gradient Boosting Machines (GBM), Neural Networks (NNet), Random Forest (RF) and Support Vector Machines (SVM). ML results and PI-RADS scores were compared with the ground-truth. Next ROC-curves and AUC values were calculated. RESULTS: All ML models outperformed PI-RADS v2 assessment scores in the prediction of sPC (RF, GBM, NNet and SVM vs. PI-RADS: AUC 0.899, 0.864, 0.884 and 0.874 vs. 0.595, all P

Hypertensive heart disease (HHD) develops in response to the chronic exposure of the left ventricle and left atrium to elevated systemic blood pressure. Left ventricular structural changes include hypertrophy and interstitial fibrosis that in turn lead to functional changes including diastolic dysfunction and impaired left atrial and LV mechanical function. Ultimately, these changes can lead to heart failure with a preserved (HFpEF) or reduced (HFrEF) ejection fraction. This review will outline the clinical evaluation of a patient with hypertension and/or suspected HHD, with a particular emphasis on the role and recent advances of multimodality imaging in both diagnosis and differential diagnosis.

Item does not contain fulltext OBJECTIVES: To evaluate the effect of a deep learning-based computer-aided diagnosis (DL-CAD) system on experienced and less-experienced radiologists in reading prostate mpMRI. METHODS: In this retrospective, multi-reader multi-case study, a consecutive set of 184 patients examined between 01/2018 and 08/2019 were enrolled. Ground truth was combined targeted and 12-core systematic transrectal ultrasound-guided biopsy. Four radiologists, two experienced and two less-experienced, evaluated each case twice, once without (DL-CAD-) and once assisted by DL-CAD (DL-CAD+). ROC analysis, sensitivities, specificities, PPV and NPV were calculated to compare the diagnostic accuracy for the diagnosis of prostate cancer (PCa) between the two groups (DL-CAD- vs. DL-CAD+). Spearman's correlation coefficients were evaluated to assess the relationship between PI-RADS category and Gleason score (GS). Also, the median reading times were compared for the two reading groups. RESULTS: In total, 172 patients were included in the final analysis. With DL-CAD assistance, the overall AUC of the less-experienced radiologists increased significantly from 0.66 to 0.80 (p = 0.001; cutoff ISUP GG >/= 1) and from 0.68 to 0.80 (p = 0.002; cutoff ISUP GG >/= 2). Experienced radiologists showed an AUC increase from 0.81 to 0.86 (p = 0.146; cutoff ISUP GG >/= 1) and from 0.81 to 0.84 (p = 0.433; cutoff ISUP GG >/= 2). Furthermore, the correlation between PI-RADS category and GS improved significantly in the DL-CAD + group (0.45 vs. 0.57; p = 0.03), while the median reading time was reduced from 157 to 150 s (p = 0.023). CONCLUSIONS: DL-CAD assistance increased the mean detection performance, with the most significant benefit for the less-experienced radiologist; with the help of DL-CAD less-experienced radiologists reached performances comparable to that of experienced radiologists. KEY POINTS: * DL-CAD used as a concurrent reading aid helps radiologists to distinguish between benign and cancerous lesions in prostate MRI. * With the help of DL-CAD, less-experienced radiologists may achieve detection performances comparable to that of experienced radiologists. * DL-CAD assistance increases the correlation between PI-RADS category and cancer grade.

Background Gadoxetate disodium has been associated with various respiratory irregularities at arterial imaging MRI. Purpose To measure the relationship between gadolinium-based contrast agent administration and irregularities by comparing gadoxetate disodium and gadoterate meglumine at free breathing. Materials and Methods This prospective observational cohort study (January 2015 to May 2017) included consecutive abdominal MRI performed with either gadoxetate disodium or gadoterate meglumine enhancement. Participants underwent dynamic imaging by using the golden-angle radial sparse parallel sequence at free breathing. The quantitative assessment evaluated the aortic contrast enhancement, the respiratory hepatic translation, and the k-space-derived respiratory pattern. Analyses of variance compared hemodynamic metrics, respiratory-induced hepatic motion, and respiratory parameters before and after respiratory gating. Results A total of 497 abdominal MRI examinations were included. Of these, 338 participants were administered gadoxetate disodium (mean age, 59 years ± 15; 153 women) and 159 participants were administered gadoterate meglumine (mean age, 59 years ± 17; 85 women). The arterial bolus of gadoxetate disodium arrived later than gadoterate meglumine (19.7 vs 16.3 seconds, respectively; P < .001). Evaluation of the hepatic respiratory translation showed respiratory motion occurring in 70.7% (239 of 338) of participants who underwent gadoxetate-enhanced examinations and in 28.9% (46 of 159) of participants who underwent gadoterate-enhanced examinations (P < .001). The duration of motion irregularities was longer for gadoxetate than for gadoterate (19.2 seconds vs 17.2 seconds, respectively) and the motion irregularities were more severe (P < .001). Both the respiratory frequency and amplitude were shorter for participants administered gadoxetate from the prebolus phase to the late arterial phase compared with gadoterate (P < .001). Conclusion The administration of two different gadolinium-based contrast agents, gadoxetate and gadoterate, at free-breathing conditions potentially leads to respiratory irregularities with differing intensity and onset. © RSNA, 2019 Online supplemental material is available for this article.

The aim of this study was to investigate whether structured reports (SRs) of prostate MRI results are more suitable than non-structured reports (NSRs) for promoting the more accurate assessment of the location of a single prostate cancer lesion by novices in MRI-targeted biopsy. 50 NSRs and 50 SRs describing a single prostatic lesion were presented to 5 novices in MRI-targeted biopsy. The participants were asked to plot the tumor location in a two-dimensional prostate diagram and to answer a questionnaire on the quality of the reports. The accuracy of the plotted tumor position was evaluated with a validated 30-point scoring system that distinguished between “major” and “minor” mistakes. The overall mean score for the accuracy of the tumor plotting was significantly higher for SRs than for NSRs (26.4 vs. 20.7, p

INTRODUCTION AND OBJECTIVE:MRI-targeted prostate biopsy improves the detection of clinically significant prostate cancer (PCa) and reduces overdetection of clinically insignificant cancer. However,...

Development of supervised AI algorithms requires a large amount of labeled images. Image labelling is both time-consuming and expensive. Therefore, we explored the value of e-learning derived annotations for AI algorithm development in medical imaging. Methods We have developed an e-learning platform that involves image-based single click labelling as part of the educational learning process. Ten radiology residents, as part of their residency training, trained the recognition of pneumothorax on 1161 chest X-rays in posterior-anterior projection. Using this data, multiple AI algorithms for detecting pneumothorax were developed. Classification and localization performance of the models was tested on an independent internal testing dataset and on the public NIH ChestX-ray14 dataset. Results The AI models F1 scores on the internal and the NIH dataset were 0.87 and 0.44, respectively. Sensitivity was 0.85 and 0.80 for classification and specificity 0.96 and 0.48 for classification. F1 scores were 0.72 and 0.66, sensitivity 0.72 and 0.72. False positive rate was 0.36 and 0.32 for localisation. Conclusion Our results demonstrated that e-learning derived annotations are a valuable data source for algorithm development. Further work is needed to include additional parameters such as user performance, consensus of diagnosis, and quality control in the development pipeline.

PURPOSE: The aim of this study was to investigate the diagnostic value of descriptive prostate perfusion parameters derived from signal enhancement curves acquired using golden-angle radial sparse parallel dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) with high spatiotemporal resolution in advanced, quantitative evaluation of prostate cancer compared with the usage of apparent diffusion coefficient (ADC) values. METHODS: A retrospective study (from January 2016 to July 2019) including 75 subjects (mean, 65 years; 46–80 years) with 2.5-second temporal resolution DCE-MRI and PIRADS 4 or 5 lesions was performed. Fifty-four subjects had biopsy-proven prostate cancer (Gleason 6, 15; Gleason 7, 20; Gleason 8, 13; Gleason 9, 6), whereas 21 subjects had negative MRI/ultrasound fusion-guided biopsies. Voxel-wise analysis of contrast signal enhancement was performed for all time points using custom-developed software, including automatic arterial input function detection. Seven descriptive parameter maps were calculated: normalized maximum signal intensity, time to start, time to maximum, time-to-maximum slope, and maximum slope with normalization on maximum signal and the arterial input function (SMN1, SMN2). The parameters were compared with ADC using multiparametric machine-learning models to determine classification accuracy. A Wilcoxon test was used for the hypothesis test and the Spearman coefficient for correlation. RESULTS: There were significant differences (P < 0.05) for all 7 DCE-derived parameters between the normal peripheral zone versus PIRADS 4 or 5 lesions and the biopsy-positive versus biopsy-negative lesions. Multiparametric analysis showed better performance when combining ADC + DCE as input (accuracy/sensitivity/specificity, 97%/93%/100%) relative to ADC alone (accuracy/sensitivity/specificity, 94%/95%/95%) and to DCE alone (accuracy/sensitivity/specificity, 78%/79%/77%) in differentiating the normal peripheral zone from PIRADS lesions, biopsy-positive versus biopsy-negative lesions (accuracy/sensitivity/specificity, 68%/33%/81%), and Gleason 6 versus ≥7 prostate cancer (accuracy/sensitivity/specificity, 69%/60%/72%). CONCLUSIONS: Descriptive perfusion characteristics derived from high-resolution DCE-MRI using model-free computations show significant differences between normal and cancerous tissue but do not reach the accuracy achieved with solely ADC-based classification. Combining ADC with DCE-based input features improved classification accuracy for PIRADS lesions, discrimination of biopsy-positive versus biopsy-negative lesions, and differentiation between Gleason 6 versus Gleason ≥7 lesions.

Purpose To compare the performance of lesion detection and Prostate Imaging-Reporting and Data System (PI-RADS) classification between a deep learning-based algorithm (DLA), clinical reports and radiologists with different levels of experience in prostate MRI. Methods This retrospective study included 121 patients who underwent prebiopsy MRI and prostate biopsy. More than five radiologists (Reader groups 1, 2: residents; Readers 3, 4: less-experienced radiologists; Reader 5: expert) independently reviewed biparametric MRI (bpMRI). The DLA results were obtained using bpMRI. The reference standard was based on pathologic reports. The diagnostic performance of the PI-RADS classification of DLA, clinical reports, and radiologists was analyzed using AUROC. Dichotomous analysis (PI-RADS cutoff value ≥ 3 or 4) was performed, and the sensitivities and specificities were compared using McNemar’s test. Results Clinically significant cancer [CSC, Gleason score ≥ 7] was confirmed in 43 patients (35.5%). The AUROC of the DLA (0.828) for diagnosing CSC was significantly higher than that of Reader 1 (AUROC, 0.706; p = 0.011), significantly lower than that of Reader 5 (AUROC, 0.914; p = 0.013), and similar to clinical reports and other readers (p = 0.060–0.661). The sensitivity of DLA (76.7%) was comparable to those of all readers and the clinical reports at a PI-RADS cutoff value ≥ 4. The specificity of the DLA (85.9%) was significantly higher than those of clinical reports and Readers 2–3 and comparable to all others at a PI-RADS cutoff value ≥ 4. Conclusions The DLA showed moderate diagnostic performance at a level between those of residents and an expert in detecting and classifying according to PI-RADS. The performance of DLA was similar to that of clinical reports from various radiologists in clinical practice.

OBJECTIVE The aim of this study was to evaluate the effect of a deep learning based computer-aided diagnosis (DL-CAD) system on radiologists' interpretation accuracy and efficiency in reading biparametric prostate magnetic resonance imaging scans. MATERIALS AND METHODS We selected 100 consecutive prostate magnetic resonance imaging cases from a publicly available data set (PROSTATEx Challenge) with and without histopathologically confirmed prostate cancer. Seven board-certified radiologists were tasked to read each case twice in 2 reading blocks (with and without the assistance of a DL-CAD), with a separation between the 2 reading sessions of at least 2 weeks. Reading tasks were to localize and classify lesions according to Prostate Imaging Reporting and Data System (PI-RADS) v2.0 and to assign a radiologist's level of suspicion score (scale from 1-5 in 0.5 increments; 1, benign; 5, malignant). Ground truth was established by consensus readings of 3 experienced radiologists. The detection performance (receiver operating characteristic curves), variability (Fleiss κ), and average reading time without DL-CAD assistance were evaluated. RESULTS The average accuracy of radiologists in terms of area under the curve in detecting clinically significant cases (PI-RADS ≥4) was 0.84 (95% confidence interval [CI], 0.79-0.89), whereas the same using DL-CAD was 0.88 (95% CI, 0.83-0.94) with an improvement of 4.4% (95% CI, 1.1%-7.7%; P = 0.010). Interreader concordance (in terms of Fleiss κ) increased from 0.22 to 0.36 (P = 0.003). Accuracy of radiologists in detecting cases with PI-RADS ≥3 was improved by 2.9% (P = 0.10). The median reading time in the unaided/aided scenario was reduced by 21% from 103 to 81 seconds (P < 0.001). CONCLUSIONS Using a DL-CAD system increased the diagnostic accuracy in detecting highly suspicious prostate lesions and reduced both the interreader variability and the reading time.

PURPOSE: To investigate the diagnostic performance of a dual-parameter approach by combining either volumetric interpolated breath-hold examination (VIBE)- or golden-angle radial sparse parallel (GRASP)–derived dynamic contrast agent–enhanced (DCE) MRI with established diffusion-weighted imaging (DWI) compared with traditional single-parameter evaluations on the basis of DWI alone. MATERIALS AND METHODS: Ninety-four male participants (66 years ± 7 [standard deviation]) were prospectively evaluated at 3.0-T MRI for clinical suspicion of prostate cancer. Included were 101 peripheral zone prostate cancer lesions. Histopathologic confirmation at MRI transrectal US fusion biopsy was matched with normal contralateral prostate parenchyma. MRI was performed with diffusion weighting and DCE by using GRASP (temporal resolution, 2.5 seconds) or VIBE (temporal resolution, 10 seconds). Perfusion (influx forward volume transfer constant [K(trans)] and rate constant [K(ep)]) and apparent diffusion coefficient (ADC) parameters were determined by tumor volume analysis. Areas under the receiver operating characteristic curve were compared for both sequences. RESULTS: Evaluated were 101 prostate cancer lesions (GRASP, 61 lesions; VIBE, 40 lesions). In a combined analysis, diffusion and perfusion parameters ADC with K(trans) or K(ep) acquired with GRASP had higher diagnostic performance compared with diffusion characteristics alone (area under the curve, 0.97 ± 0.02 [standard error] vs 0.93 ± 0.03; P < .006 and .021, respectively), whereas ADC with perfusion parameters acquired with VIBE had no additional benefit (area under the curve, 0.94 ± 0.03 vs 0.93 ± 0.04; P = .18and .50, respectively, for combination of ADC with K(trans) and K(ep)). CONCLUSION: If used in a dual-parameter model, incorporating diffusion and perfusion characteristics, the golden-angle radial sparse parallel acquisition technique improves the diagnostic performance of multiparametric MRI examinations of the prostate. This effect could not be observed combining diffusing with perfusion parameters acquired with volumetric interpolated breath-hold examination.

ObjectivesTo predict ultimate treatment intensity of COVID-19 patients using pulmonary and cardiovascular metrics fully automatically extracted from initial chest CTs.Methods All patients tested positive for SARS-CoV-2 by RT-PCR at our emergency department between March 25 and April 14, 2020 were identified (n=391). For those patients, all initial chest CTs were analyzed (n=85). Multiple pulmonary and cardiovascular metrics were extracted using deep convolutional neural networks. Three clinical treatment intensity groups were defined according to the most intensive treatment of a patient, determined six weeks later: Group 1 (outpatient), group 2 (general ward), and group 3 (intensive care unit; ICU). Univariate analyses were performed to analyze differences between groups. Subsequently, multiple metrics were combined in two binary logistic regression analyses and resulting prediction probabilities used to classify whether a patient needed hospitalization or ICU care. For analysis of discriminatory power, ROC curves were plotted and areas-under-the-curves (AUCs) calculated.ResultsThe mean interval between presentation at the emergency department and the chest CT was 1.4 days. Among others, mean percentage of lung volume affected by opacities (PO) and mean total pericardial volume (TPV) increased statistically significantly with higher treatment intensity [from group 1 to 3, standard deviation in brackets: PO: 0.8%(1.5)–11.6%(13.1)–31.6%(20.1); TPV: 733.4ml(231.7)–866.2ml(211.2)–925.7ml(125.5); both: pConclusions Metrics fully automatically extracted from initial chest CTs increase with treatment intensity of COVID-19 patients. This information can be exploited to prospectively manage allocation of healthcare resources.

The aim of this study was to test the diagnostic performance of a deep learning-based triage system for the detection of acute findings in abdominal computed tomography (CT) examinations.Using a RIS/PACS (Radiology Information System/Picture Archiving and Communication System) search engine, we obtained 100 consecutive abdominal CTs with at least one of the following findings: free-gas, free-fluid, or fat-stranding and 100 control cases with absence of these findings. The CT data were analyzed using a convolutional neural network algorithm previously trained for detection of these findings on an independent sample. The validation of the results was performed on a Web-based feedback system by a radiologist with 1 year of experience in abdominal imaging without prior knowledge of image findings through both visual confirmation and comparison with the clinically approved, written report as the standard of reference. All cases were included in the final analysis, except those in which the whole dataset could not be processed by the detection software. Measures of diagnostic accuracy were then calculated.A total of 194 cases were included in the analysis, 6 excluded because of technical problems during the extraction of the DICOM datasets from the local PACS. Overall, the algorithm achieved a 93% sensitivity (91/98, 7 false-negative) and 97% specificity (93/96, 3 false-positive) in the detection of acute abdominal findings. Intra-abdominal free gas was detected with a 92% sensitivity (54/59) and 93% specificity (39/42), free fluid with a 85% sensitivity (68/80) and 95% specificity (20/21), and fat stranding with a 81% sensitivity (42/50) and 98% specificity (48/49). False-positive results were due to streak artifacts, partial volume effects, and a misidentification of a diverticulum (each n = 1).The algorithm's autonomous detection of acute pathological abdominal findings demonstrated a high diagnostic performance, enabling guidance of the radiology workflow toward prioritization of abdominal CT examinations with acute conditions.

To explore the feasibility of a fully automated workflow for whole-body volumetric analyses based on deep reinforcement learning (DRL) and to investigate the influence of contrast-phase (CP) and slice thickness (ST) on the calculated organ volume. This retrospective study included 431 multiphasic CT datasets—including three CP and two ST reconstructions for abdominal organs—totaling 10,508 organ volumes (10,344 abdominal organ volumes: liver, spleen, and kidneys, 164 lung volumes). Whole-body organ volumes were determined using multi-scale DRL for 3D anatomical landmark detection and 3D organ segmentation. Total processing time for all volumes and mean calculation time per case were recorded. Repeated measures analyses of variance (ANOVA) were conducted to test for robustness considering CP and ST. The algorithm calculated organ volumes for the liver, spleen, and right and left kidney (mean volumes in milliliter (interquartile range), portal venous CP, 5 mm ST: 1868.6 (1426.9, 2157.8), 350.19 (45.46, 395.26), 186.30 (147.05, 214.99) and 181.91 (143.22, 210.35), respectively), and for the right and left lung (2363.1 (1746.3, 2851.3) and 1950.9 (1335.2, 2414.2)). We found no statistically significant effects of the variable contrast phase or the variable slice thickness on the organ volumes. Mean computational time per case was 10 seconds. The evaluated approach, using state-of-the art DRL, enables a fast processing of substantial amounts irrespective of CP and ST, allowing building up organ-specific volumetric databases. The thus derived volumes may serve as reference for quantitative imaging follow-up.

Purpose The aim was to investigate the variation of the arterial input function (AIF) within and between various DCE MRI sequences. Material and methods A dynamic flow-phantom and steady signal reference were scanned on a 3T MRI using fast low angle shot (FLASH) 2d, FLASH3d (parallel imaging factor (P) = P0, P2, P4), volumetric interpolated breath-hold examination (VIBE) (P = P0, P3, P2 × 2, P2 × 3, P3 × 2), golden-angle radial sparse parallel imaging (GRASP), and time-resolved imaging with stochastic trajectories (TWIST). Signal over time curves were normalized and quantitatively analyzed by full width half maximum (FWHM) measurements to assess variation within and between sequences. Results The coefficient of variation (CV) for the steady signal reference ranged from 0.07-0.8%. The non-accelerated gradient echo FLASH2d, FLASH3d, and VIBE sequences showed low within sequence variation with 2.1%, 1.0%, and 1.6%. The maximum FWHM CV was 3.2% for parallel imaging acceleration (VIBE P2 × 3), 2.7% for GRASP and 9.1% for TWIST. The FWHM CV between sequences ranged from 8.5–14.4% for most non-accelerated/accelerated gradient echo sequences except 6.2% for FLASH3d P0 and 0.3% for FLASH3d P2; GRASP FWHM CV was 9.9% versus 28% for TWIST. Conclusion MRI acceleration techniques vary in reproducibility and quantification of the AIF. Incomplete coverage of the k-space with TWIST as a representative of view-sharing techniques showed the highest variation within sequences and might be less suited for reproducible quantification of the AIF

Purpose To evaluate the performance of an artificial intelligence (AI) based software solution tested on liver volumetric analyses and to compare the results to the manual contour segmentation. Materials and methods We retrospectively obtained 462 multiphasic CT datasets with six series for each patient: three different contrast phases and two slice thickness reconstructions (1.5/5 mm), totaling 2772 series. AI-based liver volumes were determined using multi-scale deep-reinforcement learning for 3D body markers detection and 3D structure segmentation. The algorithm was trained for liver volumetry on approximately 5000 datasets. We computed the absolute error of each automatically- and manually-derived volume relative to the mean manual volume. The mean processing time/dataset and method was recorded. Variations of liver volumes were compared using univariate generalized linear model analyses. A subgroup of 60 datasets was manually segmented by three radiologists, with a further subgroup of 20 segmented three times by each, to compare the automatically-derived results with the ground-truth. Results The mean absolute error of the automatically-derived measurement was 44.3 mL (representing 2.37 % of the averaged liver volumes). The liver volume was neither dependent on the contrast phase (p = 0.697), nor on the slice thickness (p = 0.446). The mean processing time/dataset with the algorithm was 9.94 s (sec) compared to manual segmentation with 219.34 s. We found an excellent agreement between both approaches with an ICC value of 0.996. Conclusion The results of our study demonstrate that AI-powered fully automated liver volumetric analyses can be done with excellent accuracy, reproducibility, robustness, speed and agreement with the manual segmentation.

To evaluate potential confounding factors in the quantitative assessment of liver fibrosis and cirrhosis using T1 relaxation times.The study population is based on a radiology-information-system database search for abdominal MRI performed from July 2018 to April 2019 at our institution. After applying exclusion criteria 200 (59 ± 16 yrs) remaining patients were retrospectively included. 93 patients were defined as liver-healthy, 40 patients without known fibrosis or cirrhosis, and 67 subjects had a clinically or biopsy-proven liver fibrosis or cirrhosis. T1 mapping was performed using a slice based look-locker approach. A ROI based analysis of the left and the right liver was performed. Fat fraction, R2*, liver volume, laboratory parameters, sex, and age were evaluated as potential confounding factors.T1 values were significantly lower in healthy subjects without known fibrotic changes (1.5 T MRI: 575 ± 56 ms; 3 T MRI: 857 ± 128 ms) compared to patients with acute liver disease (1.5 T MRI: 657 ± 73 ms, p 0.0001; 3 T MRI: 952 ± 37 ms, p = 0.028) or known fibrosis or cirrhosis (1.5 T MRI: 644 ± 83 ms, p 0.0001; 3 T MRI: 995 ± 150 ms, p = 0.018). T1 values correlated moderately with the Child-Pugh stage at 1.5 T (p = 0.01, ρ = 0.35).T1 mapping is a capable predictor for detection of liver fibrosis and cirrhosis. Especially age is not a confounding factor and, hence, age-independent thresholds can be defined. Acute liver diseases are confounding factors and should be ruled out before employing T1-relaxometry based thresholds to screen for patients with liver fibrosis or cirrhosis.

OBJECTIVE: To extract pulmonary and cardiovascular metrics from chest CTs of patients with coronavirus disease 2019 (COVID-19) using a fully automated deep learning-based approach and assess their potential to predict patient management. MATERIALS AND METHODS: All initial chest CTs of patients who tested positive for severe acute respiratory syndrome coronavirus 2 at our emergency department between March 25 and April 25, 2020, were identified (n = 120). Three patient management groups were defined: group 1 (outpatient), group 2 (general ward), and group 3 (intensive care unit [ICU]). Multiple pulmonary and cardiovascular metrics were extracted from the chest CT images using deep learning. Additionally, six laboratory findings indicating inflammation and cellular damage were considered. Differences in CT metrics, laboratory findings, and demographics between the patient management groups were assessed. The potential of these parameters to predict patients' needs for intensive care (yes/no) was analyzed using logistic regression and receiver operating characteristic curves. Internal and external validity were assessed using 109 independent chest CT scans. RESULTS: While demographic parameters alone (sex and age) were not sufficient to predict ICU management status, both CT metrics alone (including both pulmonary and cardiovascular metrics; area under the curve [AUC] = 0.88; 95% confidence interval [CI] = 0.79-0.97) and laboratory findings alone (C-reactive protein, lactate dehydrogenase, white blood cell count, and albumin; AUC = 0.86; 95% CI = 0.77-0.94) were good classifiers. Excellent performance was achieved by a combination of demographic parameters, CT metrics, and laboratory findings (AUC = 0.91; 95% CI = 0.85-0.98). Application of a model that combined both pulmonary CT metrics and demographic parameters on a dataset from another hospital indicated its external validity (AUC = 0.77; 95% CI = 0.66-0.88). CONCLUSION: Chest CT of patients with COVID-19 contains valuable information that can be accessed using automated image analysis. These metrics are useful for the prediction of patient management.

BackgroundEffective interdisciplinary communication of imaging findings is vital for patient care, as referring physicians depend on the contained information for the decision-making and subsequent treatment. Traditional radiology reports contain non-structured free text and potentially tangled information in narrative language, which can hamper the information transfer and diminish the clarity of the report. Therefore, this study investigates whether newly developed structured reports (SRs) of prostate magnetic resonance imaging (MRI) can improve interdisciplinary communication, as compared to non-structured reports (NSRs).Methods50 NSRs and 50 SRs describing a single prostatic lesion were presented to four urologists with expert level experience in prostate cancer surgery or targeted MRI TRUS fusion biopsy. They were subsequently asked to plot the tumor location in a 2-dimensional prostate diagram and to answer a questionnaire focusing on information on clinically relevant key features as well as the perceived structure of the report. A validated scoring system that distinguishes between "major" and "minor" mistakes was used to evaluate the accuracy of the plotting of the tumor position in the prostate diagram.ResultsThe mean total score for accuracy for SRs was significantly higher than for NSRs (28.46 [range 13.33-30.0] vs. 21.75 [range 0.0-30.0], p < 0.01). The overall rates of major mistakes (54% vs. 10%) and minor mistakes (74% vs. 22%) were significantly higher (p < 0.01) for NSRs than for SRs. The rate of radiologist re-consultations was significantly lower (p < 0.01) for SRs than for NSRs (19% vs. 85%). Furthermore, SRs were rated as significantly superior to NSRs in regard to determining the clinical tumor stage (p < 0.01), the quality of the summary (4.4 vs. 2.5; p < 0.01), and overall satisfaction with the report (4.5 vs. 2.3; p < 0.01), and as more valuable for further clinical decision-making and surgical planning (p < 0.01).ConclusionsStructured reporting of prostate MRI has the potential to improve interdisciplinary communication. Through SRs, expert urologists were able to more accurately assess the exact location of single prostate cancer lesions, which can facilitate surgical planning. Furthermore, structured reporting of prostate MRI leads to a higher satisfaction level of the referring physician.

To compare image quality and radiation dose of abdominal split-filter dual-energy CT (SF-DECT) combined with monoenergetic imaging to single-energy CT (SECT) with automatic tube voltage selection (ATVS). Two-hundred single-source abdominal CT scans were performed as SECT with ATVS (n = 100) and SF-DECT (n = 100). SF-DECT scans were reconstructed and subdivided into composed images (SF-CI) and monoenergetic images at 55 keV (SF-MI). Objective and subjective image quality were compared among single-energy images (SEI), SF-CI and SF-MI. CNR and FOM were separately calculated for the liver (e.g. CNRliv) and the portal vein (CNRpv). Radiation dose was compared using size-specific dose estimate (SSDE). Results of the three groups were compared using non-parametric tests. Image noise of SF-CI was 18% lower compared to SEI and 48% lower compared to SF-MI (p 0.628). Subjective sharpness was equal between single-energy and monoenergetic images and diagnostic confidence was equal between single-energy and composed images. FOMliv was highest for SF-CI. FOMpv was equal for SEI and SF-MI (p = 0.78). SSDE was significant lower for SF-DECT compared to SECT (p < 0.022). The combined use of split-filter dual-energy CT images provides comparable objective and subjective image quality at lower radiation dose compared to single-energy CT with ATVS. • Split-filter dual-energy results in 18% lower noise compared to single-energy with ATVS. • Split-filter dual-energy results in 11% lower SSDE compared to single-energy with ATVS. • Spectral shaping of split-filter dual-energy leads to an increased dose-efficiency.