A concurrent, deep learning-based computer-aided detection system for prostate multiparametric MRI: a performance study involving experienced and less-experienced radiologists.

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.

Emergency Presentations for Dizziness-Radiological Findings, Final Diagnoses, and Mortality.

Background: Dizziness is a frequent presentation in patients presenting to emergency departments (EDs), often triggering extensive work-up, including neuroimaging. Therefore, gathering knowledge on final diagnoses and outcomes is important. We aimed to describe the incidence of dizziness as primary or secondary complaint, to list final diagnoses, and to determine the use and yield of neuroimaging and outcomes in these patients. Methods: Secondary analysis of two observational cohort studies, including all patients presenting to the ED of the University Hospital of Basel from 30th January 2017-19th February 2017 and from 18th March 2019-20th May 2019. Baseline demographics, Emergency Severity Index (ESI), hospitalization, admission to Intensive Care Units (ICUs), and mortality were extracted from the electronic health record database. At presentation, patients underwent a structured interview about their symptoms, defining their primary and secondary complaints. Neuroimaging results were obtained from the picture archiving and communication system (PACS). Patients were categorized into three non-overlapping groups: dizziness as primary complaint, dizziness as secondary complaint, and absence of dizziness. Results: Of 10076 presentations, 232 (2.3%) indicated dizziness as their primary and 984 (9.8%) as their secondary complaint. In dizziness as primary complaint, the three (out of 73 main conditions defined) main diagnoses were nonspecific dizziness (47, 20.3%), dysfunction of the peripheral vestibular system (37, 15.9%), as well as somatization, depression, and anxiety (20, 8.6%). 104 of 232 patients (44.8%) underwent neuroimaging, with relevant findings in 5 (4.8%). In dizziness as primary complaint 30-day mortality was 0%. Conclusion: Work-up for dizziness in emergency presentations has to consider a broad differential diagnosis, but due to the low yield, it should include neuroimaging only in few and selected cases, particularly with additional neurological abnormalities. Presentation with primary dizziness carries a generally favorable prognosis lacking short-term mortality. .

Building Large-Scale Quantitative Imaging Databases with Multi-Scale Deep Reinforcement Learning: Initial Experience with Whole-Body Organ Volumetric Analyses.

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.

High spatiotemporal resolution dynamic contrast-enhanced MRI improves the image-based discrimination of histopathology risk groups of peripheral zone prostate cancer: a supervised machine learning approach.

OBJECTIVE: 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. MATERIALS AND METHODS: 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. RESULTS: 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 < 0.001 and p = 0.038), while no statistically significant effect was found for low- vs. intermediate- and high-grade PCa. CONCLUSION: Perfusion information from DCE MRI acquisition schemes with high spatiotemporal resolution to ML classifiers enables a superior risk stratification between benign and malignant and intermediate- and high-risk PCa in the PZ compared with classifiers based on T2w/DWI information alone. KEY POINTS: • In the recent guidelines, the role of DCE MRI has changed from a mandatory to recommended sequence. • DCE MRI acquisition schemes with high spatiotemporal resolution (e.g., GRASP) have been shown to improve the diagnostic performance compared with conventional DCE MRI sequences. • Using perfusion information acquired with GRASP in combination with ML classifiers significantly improved the prediction of benign vs. malignant and intermediate- vs. high-grade peripheral zone prostate cancer compared with non-contrast sequences.

Automated detection of pulmonary embolism in CT pulmonary angiograms using an AI-powered algorithm.

OBJECTIVES: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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. KEY POINTS: • 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.

Gamification of Electronic Learning in Radiology Education to Improve Diagnostic Confidence and Reduce Error Rates.

OBJECTIVE. The purpose of this study is to validate an electronic learning, or e-learning, concept featuring gamification elements, rapid case reading, and instant feedback. SUBJECTS AND METHODS. An e-learning concept was devised that offered game levels for the purpose of providing training in the detection of pneumothorax in 195 cases, with questions read in rapid succession and instant feedback provided for each case. The user's task was to locate the pneumothorax on chest radiographs and indicate its presence by clicking a mouse. The game level design included an entry test consisting of 15 cases, training levels with increasing difficulty that involved 150 cases, and a final test that including 30 cases (the 15 cases from the entry test plus 15 new cases). A total of 126 candidates were invited via e-mail to participate and were asked to complete a survey before and after playing the game, which is known as RapRad. The level of diagnostic confidence and the error rate before and after playing the game were compared using a Wilcoxon signed rank test. RESULTS. Fifty-nine of 126 participants (47%) responded to the first survey and finished the game. Of these 59 participants, 29 (49%) responded to the second survey after completing the game. Diagnostic confidence in pneumothorax detection improved significantly, from a mean (± SD) score of 4.3 ± 2.1 on the entry test to a final score of 7.3 ± 2.1 (p < 0.01) after playing RapRad, with the score measured on a 10-point scale, with 10 denoting the highest possible score. Of the participants, 93% indicated that they would use the game for learning purposes again, and 87% indicated that they had fun using RapRad (7% had a neutral response and 6% had a negative response). The error rate (i.e., the number of failed attempts to answer a question correctly) significantly decreased from 39% for the entry test to 22% for the final test (p < 0.01). CONCLUSION. Our e-learning concept is capable of improving diagnostic confidence, reducing error rates in training pneumothorax detection, and offering fun in interaction with the platform.

Gadoxetate Disodium versus Gadoterate Meglumine: Quantitative Respiratory and Hemodynamic Metrics by Using Compressed-Sensing MRI.

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.

Compressed Sensing Radial Sampling MRI of Prostate Perfusion: Utility for Detection of Prostate Cancer.

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 [Ktrans] and rate constant [Kep]) 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 Ktrans or Kep 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 Ktrans and Kep). 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. © RSNA, 2018.

Comparison of image quality and radiation dose between split-filter dual-energy images and single-energy images in single-source abdominal CT.

OBJECTIVES: 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). METHODS: 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. RESULTS: Image noise of SF-CI was 18% lower compared to SEI and 48% lower compared to SF-MI (p < 0.001). Composed images yielded higher CNRliv over single-energy images (23.4 vs. 20.9; p < 0.001), whereas CNRpv was significantly lower (3.5 vs. 5.2; p < 0.001). Monoenergetic images overcame this inferiority in CNRpv and achieved similar results compared to single-energy images (5.1 vs. 5.2; 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). CONCLUSIONS: 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. KEY POINTS: • 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.

Cardiac Cine MRI Using a Commercially Available 0.55-T Scanner.

Purpose To compare parameters of left ventricular (LV) and right ventricular (RV) volume and function between a commercially available 0.55-T low-field-strength cardiac cine MRI scanner and a 1.5-T scanner. Materials and Methods In this prospective study, healthy volunteers (May 2022 to July 2022) underwent same-day cine imaging using both scanners (0.55 T, 1.5 T). Volumetric and functional parameters were assessed by two experts. After analyzing the results of a blinded crossover reader study of the healthy volunteers, 20 participants with clinically indicated cardiac MRI were prospectively included (November 2022 to February 2023). In a second blinded expert reading, parameters from clinical 1.5-T scans in these participants were compared with those same-day 0.55-T scans. Results are displayed as Bland-Altman plots. Results Eleven healthy volunteers (mean age: 33 years [95% CI: 27, 40]; four of 11 [36%] female, seven of 11 [64%] male) were included. Very strong mean correlation was observed (r = 0.98 [95% CI: 0.97, 0.98]). Average deviation between MRI systems was 1.6% (95% CI: 0.3, 2.9) for both readers. Twenty participants with clinically indicated cardiac MRI were included (mean age: 55 years [95% CI: 48, 62], six of 20 [30%] female, 14 of 20 [70%] male). Mean correlation was very strong (r = 0.98 [95% CI: 0.97, 0.98]). LV and RV parameters demonstrated an average deviation of 1.1% (95% CI: 0.1, 2.1) between MRI systems. Conclusion Cardiac cine MRI at 0.55 T yielded comparable results for quantitative biventricular volumetric and functional parameters compared with routine imaging at 1.5 T, if acquisition time is doubled. Keywords: Cardiac, Comparative Studies, Heart, Cardiovascular MRI, Cine, Myocardium Supplemental material is available for this article. ©RSNA, 2024.

Multimodality imaging and 3D-printing of a thoraco-abdominal aortic aneurysm eroding into the spine.

A rare case of a previously treated thoraco-abdominal aortic aneurysm eroding into the thoracic spine is described. Initially, several follow-up CT angiography scans showed an increasing aneurysm sack, but no endoleak could be depicted. Then, a new rapidly developing erosion into the thoracic spine was noted. MRI imaging excluded any other underlying infectious or malignant process. Additional contrast-enhanced ultrasound excluded an endoleak. A 3D-printed model of the aneurysm and spine and cinematic renderings were created to improve visualization. She underwent relining of the thoracic stent graft. Follow-up imaging showed a stable aneurysm size and no progression of the vertebral erosions.

Estimation of differential renal function on routine abdominal imaging employing compressed-sensed contrast-enhanced MR: a feasibility study referenced against dynamic renal scintigraphy in patients with deteriorating renal retention parameters.

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 < 0.001). In method verification, 29/30 kidneys (96.7%) were assigned to the correct renal function group. 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.

Hypertensive Heart Disease-The Imaging Perspective.

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.

More Space, Less Noise-New-generation Low-Field Magnetic Resonance Imaging Systems Can Improve Patient Comfort: A Prospective 0.55T-1.5T-Scanner Comparison.

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.

Deep learning for vessel-specific coronary artery calcium scoring: validation on a multi-centre dataset.

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.

Evaluation of liver fibrosis and cirrhosis on the basis of quantitative T1 mapping: Are acute inflammation, age and liver volume confounding factors?

PURPOSE: To evaluate potential confounding factors in the quantitative assessment of liver fibrosis and cirrhosis using T1 relaxation times. METHODS: 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 ±â€¯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. RESULTS: T1 values were significantly lower in healthy subjects without known fibrotic changes (1.5 T MRI: 575 ±â€¯56 ms; 3 T MRI: 857 ±â€¯128 ms) compared to patients with acute liver disease (1.5 T MRI: 657 ±â€¯73 ms, p < 0.0001; 3 T MRI: 952 ±â€¯37 ms, p = 0.028) or known fibrosis or cirrhosis (1.5 T MRI: 644 ±â€¯83 ms, p < 0.0001; 3 T MRI: 995 ±â€¯150 ms, p = 0.018). T1 values correlated moderately with the Child-Pugh stage at 1.5 T (p = 0.01, ρ = 0.35). CONCLUSION: 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.

Prediction of Patient Management in COVID-19 Using Deep Learning-Based Fully Automated Extraction of Cardiothoracic CT Metrics and Laboratory Findings.

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.

Revisiting DCE-MRI: Classification of Prostate Tissue Using Descriptive Signal Enhancement Features Derived From DCE-MRI Acquisition With High Spatiotemporal Resolution.

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.

A Novel Deep Learning Based Computer-Aided Diagnosis System Improves the Accuracy and Efficiency of Radiologists in Reading Biparametric Magnetic Resonance Images of the Prostate: Results of a Multireader, Multicase Study.

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.

Validation of a fully automated liver segmentation algorithm using multi-scale deep reinforcement learning and comparison versus manual segmentation.

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.