Search

Purpose Identify chronic shoulder MRI findings in patients with known shoulder injury related to vaccine administration (SIRVA). Materials and methods Two fellowship-trained musculoskeletal radiologists retrospectively reviewed the MRI of nine patients with clinically established SIRVA. MRI was performed at least 4 weeks after vaccination and included intravenous contrast-enhanced sequences. MRI was reviewed for the presence of erosions, tendonitis, capsulitis, synovitis, bone marrow oedema, joint effusion, bursitis, cartilage defects, rotator cuff lesions, and lymphadenopathy. The number and location of focal lesions were recorded. Results Erosions of the greater tuberosity were present in 8/9 (89%), tendonitis of the infraspinatus muscle tendon in 7/9 (78%), capsulitis, synovitis, and bone marrow oedema in 5/9 (56%) cases, respectively. Effusion was found in three, and subdeltoid bursitis, rotator cuff lesions as well as cartilage defects in one patient, respectively. None of our included subjects showed axillary lymphadenopathy. Conclusion In this case series, greater humeral tuberosity erosions, infraspinatus muscle tendonitis, capsulitis, synovitis, and bone marrow oedema were common MRI findings in chronic SIRVA.

Zusammenfassung Hintergrund Die Niederfeld-Magnetresonanztomographie (MRT) erlebt aufgrund technischer Neuerungen eine Renaissance. Die Geräte der neuen Generation bieten neue Anwendungsspektren in der Bildgebung und eine mögliche Antwort auf den steigenden Kostendruck im Gesundheitssystem. Fragestellung Einfluss der Feldstärke auf die Technik, Physik, Bildakquisition und die diagnostische Qualität der Untersuchungen. Material und Methode Rekapitulation der wichtigen grundlegenden physikalischen Parameter für Bildgewinnung und Qualität. Erste klinische Erfahrungen mit einem neuen 0,55-T-Niederfeldscanner. Ergebnisse Niedrigere Feldstärken als die klinisch aktuell verbreiteten 1,5 T und 3 T sind in der Bildgewinnung durch ein zu erwartendes geringeres Signal-zu-Rausch Verhältnis gekennzeichnet. Ob dies eine diagnostische Limitation ist, muss in Studien evaluiert werden, da es verschiedene Optionen gibt, dieses vermeintliche Defizit zu kompensieren. Dies kann durch eine Verlängerung der Akquisitionszeit oder durch Einsatz von Nachverarbeitungsverfahren mit Hilfe der künstlichen Intelligenz (KI) geschehen. Zudem ist zu validieren, in welchen Körperregionen und bei welchen Krankheitsbildern die Bildqualität diagnostisch ausreichend ist. Erste Untersuchungen in unserer Klinik sind vielversprechend und zeigen beispielsweise diagnostische Qualität ohne relevanten Zeitverlust für Untersuchungen der Lendenwirbelsäule. Potenzielle Stärken aufgrund geringerer Suszeptibilitätsartefakte ergeben sich in der Lungenbildgebung oder bei Implantaten. Schlussfolgerung Niederfeldscanner bieten eine Vielzahl von neuen Anwendungsfeldern mit feldstärkebedingten Vorteilen. Bei den meisten anderen klinischen Untersuchungsfeldern kann mindestens eine diagnostische Qualität erwartet werden.

Background To investigate hip implant-related metal artifacts on a 0.55-T system compared with 1.5-T and 3-T systems. Methods Total hip arthroplasty made of three different alloys were evaluated in a water phantom at 0.55, 1.5, and 3 T using routine protocols. Visually assessment (VA) was performed by three readers using a Likert scale from 0 (no artifacts) to 6 (extremely severe artifacts). Quantitative assessment (QA) was performed using the coefficient of variation (CoV) and the fraction of voxels within a threshold of the mean signal intensity compared to an automatically defined region of interest (FVwT). Agreement was evaluated using intra/inter-class correlation coefficient (ICC). Results Interreader agreement of VA was strong-to-moderate (ICC 0.74−0.82). At all field strengths (0.55-T/1.5-T/3-T), artifacts were assigned a lower score for titanium (Ti) alloys (2.44/2.9/2.7) than for stainless steel (Fe-Cr) (4.1/3.9/5.1) and cobalt-chromium (Co-Cr) alloys (4.1/4.1/5.2) (p < 0.001 for both). Artifacts were lower for 0.55-T and 1.5-T than for 3-T systems, for all implants (p ≤ 0.049). A strong VA-to-QA correlation was found (r = 0.81; p < 0.001); CoV was lower for Ti alloys than for Fe-Cr and Co-Cr alloys at all field strengths. The FVwT showed a negative correlation with VA (-0.68 < r < -0.84; p < 0.001). Conclusions Artifact intensity was lowest for Ti alloys at 0.55 T. For other alloys, it was similar at 0.55 T and 1.5 T, higher at 3 T. Despite an inferior gradient system and a larger bore width, the 0.55-T system showed the same artifact intensity of the 1.5-T system.

Objectives The goal of this study was to investigate the precise timeline of respiratory events occurring after the administration of two gadolinium-based contrast agents, gadoxetate disodium and gadoterate meglumine. Materials and methods This retrospective study examined 497 patients subject to hepatobiliary imaging using the GRASP MRI technique (TR/TE = 4/2 ms; ST = 2.5 mm; 384 × 384 mm). Imaging was performed after administration of gadoxetate (N = 338) and gadoterate (N = 159). All GRASP datasets were reconstructed using a temporal resolution of 1 s. Four regions-of-interest (ROIs) were placed in the liver dome, the right and left cardiac ventricle, and abdominal aorta detecting liver displacement and increasing vascular signal intensities over time. Changes in hepatic intensity reflected respiratory dynamics in temporal correlation to the vascular contrast bolus. Results In total, 216 (67%) and 41 (28%) patients presented with transient respiratory motion after administration of gadoxetate and gadoterate, respectively. The mean duration from start to acme of the respiratory episode was similar (p = 0.4) between gadoxetate (6.0 s) and gadoterate (5.6 s). Its mean onset in reference to contrast arrival in the right ventricle differed significantly (p < 0.001) between gadoxetate (15.3s) and gadoterate (1.8 s), analogously to peak inspiration timepoint in reference to the aortic enhancement arrival (gadoxetate: 0.9s after, gadoterate: 11.2 s before aortic enhancement, p < 0.001). Conclusions The timepoint of occurrence of transient respiratory anomalies associated with gadoxetate disodium and gadoterate meglumine differs significantly between both contrast agents while the duration of the event remains similar. Key Points • Transient respiratory anomalies following the administration of gadoterate meglumine occurred during a time period usually not acquired in MR imaging. • Transient respiratory anomalies following the administration of gadoxetate disodium occurred around the initiation of arterial phase imaging. • The estimated duration of respiratory events was similar between both contrast agents.

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

Background Response Assessment in Neuro-Oncology Criteria (RANO), are used to asses response to first-line treatment of glioblastoma (GBM). Differentiation between response and pseudoresponse under treatment with Bevacizumab (BVZ) remains challenging. This study evaluates ADC changes in patients with radiographic pseudoresponse under treatment with (BVZ). Methods Patients (n = 40) with recurrent GBM under-treatment with BVZ underwent MRI before, two and four months after treatment with BVZ. In patients with radiological pseudoresponse (n = 11), ADC analyses were performed. Areas with decreasing T1 contrast enhancement (CE) and FLAIR signal decrease were manually selected and compared to size and position matched healthy contralateral brain parenchyma. Results Histogram based ADC (10–6 × mm2/s) of these patients decreased significantly (P 0.05) (ADC values: baseline: 786.2 ± 110.7, 2 months: 781.1 ± 76.2, 4 months: 804.1 ± 86.2). Conclusion Treatment of GBM with BVZ leads to a decrease of ADC values in areas of pre-treatment T1-CE/FLAIR signal hyperintensity to levels of comparable with normal brain tissue. ADC values remained stable, even when progressive tumor growth was reported.

Purpose: To compare the segmentation and detection performance of a deep learning model trained on a database of human-labelled clinical diffusion-weighted (DW) stroke lesions to a model trained on the same database enhanced with synthetic DW stroke lesions. Methods: In this institutional review board approved study, a stroke database of 962 cases (mean age 65+/-17 years, 255 males, 449 scans with DW positive stroke lesions) and a normal database of 2,027 patients (mean age 38+/-24 years,1088 females) were obtained. Brain volumes with synthetic DW stroke lesions were produced by warping the relative signal increase of real strokes to normal brain volumes. A generic 3D U-Net was trained on four different databases to generate four different models: (a) 375 neuroradiologist-labeled clinical DW positive stroke cases(CDB);(b) 2,000 synthetic cases(S2DB);(c) CDB+2,000 synthetic cases(CS2DB); or (d) CDB+40,000 synthetic cases(CS40DB). The models were tested on 20%(n=192) of the cases of the stroke database, which were excluded from the training set. Segmentation accuracy was characterized using Dice score and lesion volume of the stroke segmentation, and statistical significance was tested using a paired, two-tailed, Student's t-test. Detection sensitivity and specificity was compared to three neuroradiologists. Results: The performance of the 3D U-Net model trained on the CS40DB(mean Dice 0.72) was better than models trained on the CS2DB (0.70,P, This manuscript has been accepted for publication in Radiology: Artificial Intelligence

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 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.