Explore the vast range of titles available.

ObjectiveTo evaluate the impact of a postoperative baseline (PB) MRI on diagnostic confidence and performance in detecting local recurrence (LR) of soft-tissue sarcoma (STS) of the limb.Materials and methodsA total of 72 patients (8 with LR, 64 without LR) with primary STS of the limb were included. Routine follow-up MRI (1.5 T) at 6 and approximately 36 months (meanLR: 39.7 months; meanno LR: 34.9 months) after multimodal therapy or at time of LR were assessed by three independent readers using a 5-point Likert scale. Furthermore, the following imaging parameters were evaluated: presence of a mass, signal characteristics at T2- and T1-weighted imaging, contrast enhancement (CE), and in some of the cases signal intensity on the apparent diffusion coefficient (ADC). U-test, McNemar test, and ROC-analysis were applied. Interobserver reliability was calculated using Fleiss kappa statistics. A p value of 0.05 was considered statistically significant.ResultsThe presence of a PB MRI significantly improved diagnostic confidence in detecting LR of STS (p < 0.001) and slightly increased specificity (mean specificity without PE 74.1% and with presence of PB MRI 81.2%); however, not to a significant level. The presence of a mass showed highest diagnostic performance and highest interreader agreement (AUC [%]; κ: 73.1–83.6; 0.34) followed by T2-hyperintensity (50.8–66.7; 0.08), CE (52.4–62.5; 0.13), and T1-hypointensity (54.7–77.3; 0.23). ADC showed an AUC of 65.6–96.6% and a κ of 0.55.ConclusionThe presence of a PB MRI increases diagnostic confidence in detecting LR of STS of the limb.

Background: Our retrospective single-center study aims to evaluate the impact of structured reporting (SR) using a CEUS LI-RADS template on report quality compared to conventional free-text reporting (FTR) in contrast-enhanced ultrasound (CEUS) for the diagnosis of hepatocellular carcinoma (HCC). Methods: We included 50 patients who underwent CEUS for HCC staging. FTR created after these examinations were compared to SR retrospectively generated by using template-based online software with clickable decision trees. The reports were evaluated regarding report completeness, information extraction, linguistic quality and overall report quality by two readers specialized in internal medicine and visceral surgery. Results: SR significantly increased report completeness with at least one key feature missing in 31% of FTR vs. 2% of SR (p < 0.001). Information extraction was considered easy in 98% of SR vs. 86% of FTR (p = 0.004). The trust of referring physicians in the report was significantly increased by SR with a mean of 5.68 for SR vs. 4.96 for FTR (p < 0.001). SR received significantly higher ratings regarding linguistic quality (5.79 for SR vs. 4.83 for FTR (p < 0.001)) and overall report quality (5.75 for SR vs. 5.01 for FTR (p < 0.001)). Conclusions: Using SR instead of conventional FTR increases the overall quality of reports in CEUS examinations of HCC patients and may represent a valuable tool to facilitate clinical decision-making and improve interdisciplinary communication in the future.

Objective: In suspected acute ischemic stroke, it is now reasonable to expand the conventional “stroke protocol” (non-contrast computed tomography (NCCT), arterial CT angiography (CTA), and optionally CT perfusion (CTP)) to early and late venous head scans yielding a multiphase CTA (MP-CTA) to increase diagnostic confidence. Diagnostic reference levels (DRLs) have been defined for neither MP-CTA nor CTP. We therefore present dosimetry data, while also considering image quality, for a large, unselected patient cohort. Methods: A retrospective single-center study of 1790 patients undergoing the extended stroke protocol with three scanners (2× dual-source, DSCT; 1× single-source, SSCT) between 07/21 and 12/23 was conducted. For each sequence, we analyzed the radiation dose (volumetric CT dose index (CTDIvol); dose length product; effective dose); objective image quality using manually placed regions of interest (contrast-to-noise ratio (CNR)); and subjective image quality (4-point scale: 1 = non-diagnostic, 4 = excellent). The DRL was defined as the 75% percentile of the CTDIvol distribution. The Kruskal-Wallis test was used initially to test for overall equality of median values in each data group. Single post-test comparisons were performed with Dunn’s test, with an overall statistical significance level of 0.05. Results: Dosimetry values were significantly higher for SSCT (p < 0.001, each). Local DRLs ranged between 37.3 and 49.1 mGy for NCCT, 3.6–5.5 mGy for arterial CTA, 1.2–2.5 mGy each for early/late venous CTA, and 141.1–220.5 mGy for CTP. Protocol adjustment (DSCT-1: CTP) yielded a 28.2% dose reduction. The highest/lowest CNRs (arterial/early venous CTA, respectively) were recorded for SSCT/DSCT-2 (p < 0.001). Subjective image quality was rated excellent except for slightly increased MP-CTA noise at DSCT-2 (median = 3). Conclusions: Our data imply that additive MP-CTA scans only yield a minor increase in radiation exposure, particularly when using DSCT. CTP should be limited to selected patients.

Background: This study aims to evaluate the potential benefits of structured reporting (SR) compared to conventional free-text reporting (FTR) in contrast-enhanced ultrasound (CEUS) of cystic renal lesions, based on the Bosniak classification. Methods: Fifty patients with cystic renal lesions who underwent CEUS were included in this single-center study. FTR created in clinical routine were compared to SR retrospectively generated by using a structured reporting template. Two experienced urologists evaluated the reports regarding integrity, effort for information extraction, linguistic quality, and overall quality. Results: The required information could easily be extracted by the reviewers in 100% of SR vs. 82% of FTR (p < 0.001). The reviewers trusted the information given by SR significantly more with a mean of 5.99 vs. 5.52 for FTR (p < 0.001). SR significantly improved the linguistic quality (6.0 for SR vs. 5.68 for FTR (p < 0.001)) and the overall report quality (5.98 for SR vs. 5.58 for FTR (p < 0.001)). Conclusions: SR significantly increases the quality of radiologic reports in CEUS examinations of cystic renal lesions compared to conventional FTR and represents a promising approach to facilitate interdisciplinary communication in the future.

Background: Brain volumetry is a key aspect in dementia diagnostics. We applied an artificial intelligence (AI) system based on a Convolutional Neural Network (CNN) which aims to perform lobe-separated rapid brain volumetry (< 1/2 h) of three-dimensional T1-weighted magnetic resonance imaging (MRI) with automated segmentation as well as comparison to age- and gender-adapted percentiles. Our aim was to quantify the added value in the differential diagnostics of dementia. Methods: A total of 55 patients-17 with confirmed diagnosis of Alzheimer's disease (AD), 18 with confirmed diagnosis of frontotemporal dementia (FTD) and 20 healthy controls-received T1-weighted three-dimensional magnetization prepared-rapid gradient echo (MP-RAGE) MRI. Images were retrospectively assessed by one board-certified neuroradiologist (BCNR) and two radiology residents (RR)-one of whom had received 6 months of neuroradiology training (RR1). All cases were evaluated in a two-step reading process-beginning without AI-support and followed by an AI-supported reading (AI tool: md-brain version 3.3.0). For each subject, the suspected diagnostic category (AD, FTD and healthy controls) was determined using a likelihood score (0-5), adding up to a sum of 5 for all three diagnostic categories. Individual reader performance with and without AI support was statistically evaluated using receiver operating characteristics (ROC). Results: AI support substantially improved AD diagnosis in all three readers. The effect was most pronounced for RR2 who had not undergone neuroradiology training (area under the curve [AUC] without AI support [- AI]: 0.629, AI supported [+ AI]: 0.885). But, even for the BCNR, a substantial benefit was measurable (AUCs: BCNR--AI: 0.827, + AI: 0.882; RR1--AI: 0.713, + AI: 0.834). In diagnosing FTD RR2 improved with AI support (AUCs:--AI: 0.610, + AI: 0.754), while BCNR and RR1 had comparable reading performances with and without AI support (AUCs: BCNR--AI: 0.843, + AI: 0.828; RR1--AI: 0.865, + AI: 0.868). Discussion: Even experienced BCNR can improve their diagnostic accuracy for AD by using AI based rapid brain volumetry and comparison with the age- and gender-matched reference cohorts. In diagnosing FTD, especially radiologists who are less experienced in dementia differential diagnosis can strongly benefit from AI support. Conclusion: AI support in the radiological work-up of dementia patients is feasible and can substantially improve diagnostic accuracy, which might lead to earlier diagnosis and therefore optimized patient management.

Federated machine learning (FL) allows to collectively train models on sensitive data as only the clients' models and not their training data need to be shared. However, despite the attention that research on FL has drawn, the concept still lacks broad adoption in practice. One of the key reasons is the great challenge to implement FL systems that simultaneously achieve fairness, integrity, and privacy preservation for all participating clients. To contribute to solving this issue, our paper suggests a FL system that incorporates blockchain technology, local differential privacy, and zero-knowledge proofs. Our implementation of a proof-of-concept with multiple linear regression illustrates that these state-of-the-art technologies can be combined to a FL system that aligns economic incentives, trust, and confidentiality requirements in a scalable and transparent system.