Journal: European Radiology

Abbreviation

Eur Radiol

Publisher

Springer

Journal Volumes

ISSN

0938-7994
1432-1084

Description

Filters

Reset filters

Search Results

Publications 1 - 10 of 46
  • Age dependence of spleen- and muscle-corrected hepatic signal enhancement on hepatobiliary phase gadoxetate MRI
    Item type: Journal Article
    Matoori, Simon; Froehlich, Johannes M.; Breitenstein, Stefan; et al. (2016)
    European Radiology
  • Imaging of alert patients after non-self-inflicted strangulation: MRI is superior to CT
    Item type: Journal Article
    Ruder, Thomas D.; Gonzenbach, Alexandra; Heimer, Jakob; et al. (2024)
    European Radiology
    Objective: To assess the accuracy of CT and MRI reports of alert patients presenting after non-self-inflicted strangulation (NSIS) and evaluate the appropriateness of these imaging modalities in NSIS. Material and methods: The study was a retrospective analysis of patient characteristics and strangulation details, with a comparison of original radiology reports (ORR) to expert read-outs (EXR) of CT and MRI studies of all NSIS cases seen from 2008 to 2020 at a single centre. Results: The study included 116 patients (71% women, p < .001, χ²), with an average age of 33.8 years, mostly presenting after manual strangulation (97%). Most had experienced intimate partner violence (74% of women, p < .001, χ²) or assault by unknown offender (88% of men, p < 0.002 χ²). Overall, 132 imaging studies (67 CT, 51% and 65 MRI, 49%) were reviewed. Potentially dangerous injuries were present in 7%, minor injuries in 22%, and no injuries in 71% of patients. Sensitivity and specificity of ORR were 78% and 97% for MRI and 30% and 98% for CT. Discrepancies between ORR and EXR occurred in 18% of all patients, or 62% of injured patients, with a substantial number of unreported injuries on CT. Conclusions: The results indicate that MRI is more appropriate than CT for alert patients presenting after non-self-inflicted strangulation and underline the need for radiologists with specialist knowledge to report these cases in order to add value to both patient care and potential future medico-legal investigations. Clinical relevance statement: MRI should be preferred over CT for the investigation of strangulation related injuries in alert patients because MRI has a higher accuracy than CT and does not expose this usually young patient population to ionizing radiation.
  • Infratentorial lesions in multiple sclerosis patients: intra- and inter-rater variability in comparison to a fully automated segmentation using 3D convolutional neural networks
    Item type: Journal Article
    Krüger, Julia; Ostwaldt, Ann-Christin; Spies, Lothar; et al. (2022)
    European Radiology
    Objective Automated quantification of infratentorial multiple sclerosis lesions on magnetic resonance imaging is clinically relevant but challenging. To overcome some of these problems, we propose a fully automated lesion segmentation algorithm using 3D convolutional neural networks (CNNs). Methods The CNN was trained on a FLAIR image alone or on FLAIR and T1-weighted images from 1809 patients acquired on 156 different scanners. An additional training using an extra class for infratentorial lesions was implemented. Three experienced raters manually annotated three datasets from 123 MS patients from different scanners. Results The inter-rater sensitivity (SEN) was 80% for supratentorial lesions but only 62% for infratentorial lesions. There was no statistically significant difference between the inter-rater SEN and the SEN of the CNN with respect to the raters. For supratentorial lesions, the CNN featured an intra-rater intra-scanner SEN of 0.97 (R1 = 0.90, R2 = 0.84) and for infratentorial lesion a SEN of 0.93 (R1 = 0.61, R2 = 0.73). Conclusion The performance of the CNN improved significantly for infratentorial lesions when specifically trained on infratentorial lesions using a T1 image as an additional input and matches the detection performance of experienced raters. Furthermore, for infratentorial lesions the CNN was more robust against repeated scans than experienced raters.
  • What can European radiologists learn from the outbreak of COVID-19 in China? A discussion with a radiologist from Wuhan
    Item type: Other Journal Item
    Gutzeit, Andreas; Li, Qiubai; Matoori, Simon; et al. (2020)
    European Radiology
  • Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study
    Item type: Journal Article
    Rodriguez-Ruiz, Alejandro; Lång, Kristina; Gubern-Merida, Albert; et al. (2019)
    European Radiology
    Purpose To study the feasibility of automatically identifying normal digital mammography (DM) exams with artificial intelligence (AI) to reduce the breast cancer screening reading workload. Methods and materials A total of 2652 DM exams (653 cancer) and interpretations by 101 radiologists were gathered from nine previously performed multi-reader multi-case receiver operating characteristic (MRMC ROC) studies. An AI system was used to obtain a score between 1 and 10 for each exam, representing the likelihood of cancer present. Using all AI scores between 1 and 9 as possible thresholds, the exams were divided into groups of low- and high likelihood of cancer present. It was assumed that, under the pre-selection scenario, only the high-likelihood group would be read by radiologists, while all low-likelihood exams would be reported as normal. The area under the reader-averaged ROC curve (AUC) was calculated for the original evaluations and for the pre-selection scenarios and compared using a non-inferiority hypothesis. Results Setting the low/high-likelihood threshold at an AI score of 5 (high likelihood > 5) results in a trade-off of approximately halving (− 47%) the workload to be read by radiologists while excluding 7% of true-positive exams. Using an AI score of 2 as threshold yields a workload reduction of 17% while only excluding 1% of true-positive exams. Pre-selection did not change the average AUC of radiologists (inferior 95% CI > − 0.05) for any threshold except at the extreme AI score of 9. Conclusion It is possible to automatically pre-select exams using AI to significantly reduce the breast cancer screening reading workload.
  • Optimizing radiation dose by using advanced modelled iterative reconstruction in high-pitch coronary CT angiography
    Item type: Journal Article
    Gordic, Sonja; Desbiolles, Lotus; Sedlmair, Martin; et al. (2016)
    European Radiology
  • In-vivo flow simulation in coronary arteries based on computed tomography datasets
    Item type: Journal Article
    Frauenfelder, Thomas; Boutsianis, Evangelos; Schertler, Thomas; et al. (2007)
    European Radiology
  • Serum albumin, total bilirubin, and patient age are independent confounders of hepatobiliary-phase gadoxetate parenchymal liver enhancement
    Item type: Journal Article
    Matoori, Simon; Froehlich, Johannes M.; Breitenstein, Stefan; et al. (2019)
    European Radiology
  • Differential NMR spectroscopy reactions of anterior / posterior and right / left insular subdivisions due to acute dental pain
    Item type: Journal Article
    Gutzeit, Andreas; Meier, Dieter; Froehlich, Johannes M.; et al. (2013)
    European Radiology
  • Vertebral body insufficiency fractures: detection of vertebrae at risk on standard CT images using texture analysis and machine learning
    Item type: Journal Article
    Muehlematter, Urs J.; Mannil, Manoj; Becker, Anton S.; et al. (2019)
    European Radiology
    Purpose To evaluate the diagnostic performance of bone texture analysis (TA) combined with machine learning (ML) algorithms in standard CT scans to identify patients with vertebrae at risk for insufficiency fractures. Materials and methods Standard CT scans of 58 patients with insufficiency fractures of the spine, performed between 2006 and 2013, were analyzed retrospectively. Every included patient had at least two CT scans. Intact vertebrae in a first scan that either fractured (Bunstable^) or remained intact (Bstable^) in the consecutive scan were manually seg mented on mid-sagittal reformations. TA features for all vertebrae were extracted using open-source software (MaZda). In a paired control study, all vertebrae of the study cohort Bcases^ and matched controls were classified using ROC analysis of Hounsfield unit (HU) measurements and supervised ML techniques. In a within-subject vertebra comparison, vertebrae of the cases were classified into Bunstable^ and Bstable^ using identical techniques. Results One hundred twenty vertebrae were included. Classification of cases/controls using ROC analysis of HU mea surements showed an AUC of 0.83 (95% confidence interval [CI], 0.77–0.88), and ML-based classification showed an AUC of 0.97 (CI, 0.97–0.98). Classification of unstable/stable vertebrae using ROC analysis showed an AUC of 0.52 (CI, 0.42–0.63), and ML-based classification showed an AUC of 0.64 (CI, 0.61–0.67). Conclusion TA combined with ML allows to identifying patients who will suffer from vertebral insufficiency fractures in standard CT scans with high accuracy. However, identification of single vertebra at risk remains challenging.
Publications 1 - 10 of 46