European Radiology Experimental最新文献

{"title":"Deep learning-based Intraoperative MRI reconstruction.","authors":"Jon André Ottesen, Tryggve Storas, Svein Are Sirirud Vatnehol, Grethe Løvland, Einar Osland Vik-Mo, Till Schellhorn, Karoline Skogen, Christopher Larsson, Atle Bjørnerud, Inge Rasmus Groote-Eindbaas, Matthan W A Caan","doi":"10.1186/s41747-024-00548-9","DOIUrl":"https://doi.org/10.1186/s41747-024-00548-9","url":null,"abstract":"<p><strong>Background: </strong>We retrospectively evaluated the quality of deep learning (DL) reconstructions of on-scanner accelerated intraoperative MRI (iMRI) during respective brain tumor surgery.</p><p><strong>Methods: </strong>Accelerated iMRI was performed using dual surface coils positioned around the area of resection. A DL model was trained on the fastMRI neuro dataset to mimic the data from the iMRI protocol. The evaluation was performed on imaging material from 40 patients imaged from Nov 1, 2021, to June 1, 2023, who underwent iMRI during tumor resection surgery. A comparative analysis was conducted between the conventional compressed sense (CS) method and the trained DL reconstruction method. Blinded evaluation of multiple image quality metrics was performed by two neuroradiologists and one neurosurgeon using a 1-to-5 Likert scale (1, nondiagnostic; 2, poor; 3, acceptable; 4, good; and 5, excellent), and the favored reconstruction variant.</p><p><strong>Results: </strong>The DL reconstruction was strongly favored or favored over the CS reconstruction for 33/40, 39/40, and 8/40 of cases for readers 1, 2, and 3, respectively. For the evaluation metrics, the DL reconstructions had a higher score than their respective CS counterparts for 72%, 72%, and 14% of the cases for readers 1, 2, and 3, respectively. Still, the DL reconstructions exhibited shortcomings such as a striping artifact and reduced signal.</p><p><strong>Conclusion: </strong>DL shows promise in allowing for high-quality reconstructions of iMRI. The neuroradiologists noted an improvement in the perceived spatial resolution, signal-to-noise ratio, diagnostic confidence, diagnostic conspicuity, and spatial resolution compared to CS, while the neurosurgeon preferred the CS reconstructions across all metrics.</p><p><strong>Relevance statement: </strong>DL shows promise to allow for high-quality reconstructions of iMRI, however, due to the challenging setting of iMRI, further optimization is needed.</p><p><strong>Key points: </strong>iMRI is a surgical tool with a challenging image setting. DL allowed for high-quality reconstructions of iMRI. Additional optimization is needed due to the challenging intraoperative setting.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"9 1","pages":"29"},"PeriodicalIF":3.7,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143493566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI for image quality and patient safety in CT and MRI.","authors":"Luca Melazzini, Chandra Bortolotto, Leonardo Brizzi, Marina Achilli, Nicoletta Basla, Alessandro D'Onorio De Meo, Alessia Gerbasi, Olivia Maria Bottinelli, Riccardo Bellazzi, Lorenzo Preda","doi":"10.1186/s41747-025-00562-5","DOIUrl":"10.1186/s41747-025-00562-5","url":null,"abstract":"<p><p>Substantial endeavors have been recently dedicated to developing artificial intelligence (AI) solutions, especially deep learning-based, tailored to enhance radiological procedures, in particular algorithms designed to minimize radiation exposure and enhance image clarity. Thus, not only better diagnostic accuracy but also reduced potential harm to patients was pursued, thereby exemplifying the intersection of technological innovation and the highest standards of patient care. We provide herein an overview of recent AI developments in computed tomography and magnetic resonance imaging. Major AI results in CT regard: optimization of patient positioning, scan range selection (avoiding \"overscanning\"), and choice of technical parameters; reduction of the amount of injected contrast agent and injection flow rate (also avoiding extravasation); faster and better image reconstruction reducing noise level and artifacts. Major AI results in MRI regard: reconstruction of undersampled images; artifact removal, including those derived from unintentional patient's (or fetal) movement or from heart motion; up to 80-90% reduction of GBCA dose. Challenges include limited generalizability, lack of external validation, insufficient explainability of models, and opacity of decision-making. Developing explainable AI algorithms that provide transparent and interpretable outputs is essential to enable seamless AI integration into CT and MRI practice. RELEVANCE STATEMENT: This review highlights how AI-driven advancements in CT and MRI improve image quality and enhance patient safety by leveraging AI solutions for dose reduction, contrast optimization, noise reduction, and efficient image reconstruction, paving the way for safer, faster, and more accurate diagnostic imaging practices. KEY POINTS: Advancements in AI are revolutionizing the way radiological images are acquired, reconstructed, and interpreted. AI algorithms can assist in optimizing radiation doses, reducing scan times, and enhancing image quality. AI techniques are paving the way for a future of more efficient, accurate, and safe medical imaging examinations.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"9 1","pages":"28"},"PeriodicalIF":3.7,"publicationDate":"2025-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11847764/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143484201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Contrast-enhanced photon-counting detector CT for discriminating local recurrence from postoperative changes after resection of pancreatic ductal adenocarcinoma.","authors":"Zlatan Alagic, Carlos Valls Duran, Anders Svensson-Marcial, Seppo K Koskinen","doi":"10.1186/s41747-025-00567-0","DOIUrl":"10.1186/s41747-025-00567-0","url":null,"abstract":"<p><strong>Background: </strong>We evaluated the diagnostic capability of photon-counting detector computed tomography (PCD-CT) spectral variables in late arterial phase (LAP) and portal venous phase (PVP) to discriminate between local tumor recurrence (LTR) and postoperative changes (POC) after pancreatic ductal adenocarcinoma (PDAC) resection.</p><p><strong>Methods: </strong>Seventy-three consecutive PCD-CT scans in 73 patients with postoperative soft-tissue lesions (PSLs) were included, 42 with POC and 31 with LTR. Regions of interest were drawn in each PSL, and spectral variables were calculated: iodine concentration (IC), normalized IC (NIC), fat fraction, attenuation at 40, 70, and 90 keV, and slope of the spectral curve between 40-90 keV. Multivariable binary logistic regression models were constructed. Diagnostic performance was assessed for LAP and PVP using receiver operating characteristic analysis.</p><p><strong>Results: </strong>In LAP, all variables except fat fraction showed significant differences between LTR and POC (p ≤ 0.025). In PVP, all variables except NIC and fat fraction demonstrated significant differences between LTR and POC (p ≤ 0.005). Logistic regression analysis included NIC and 70 keV in the LAP-based model and IC and 90 keV in the PVP-based model. Both models achieved a higher area under the curve (AUC) than individual spectral variables in each phase. The LAP-based model achieved an AUC of 0.919 with 94% sensitivity, 84% specificity, and 87% accuracy, while the PVP-based model reached 0.820, 71%, 88%, and 81%, respectively.</p><p><strong>Conclusion: </strong>Spectral variables from PCD-CT help distinguish between LTR and POC in LAP and PVP post-PDAC resection. Multivariable logistic regression improves diagnostic performance, especially in LAP.</p><p><strong>Relevance statement: </strong>Measuring normalized iodine concentration and attenuation at 70 keV in late arterial phase, or iodine concentration and attenuation at 90 keV in portal venous phase, and incorporating these values into a logistic regression model can help differentiate between local tumor recurrence and postoperative changes after pancreatic ductal adenocarcinoma resection.</p><p><strong>Key points: </strong>Distinguishing recurrence from postoperative changes on CT after pancreatic ductal adenocarcinoma resection is challenging. PCD-CT spectral variable values differed significantly between local tumor recurrence (LTR) and postoperative changes (POC). Logistic regression of spectral variables can help distinguish LTR from POC. The late arterial phase-based model reached an AUC of 0.919 with 94% sensitivity and 84% specificity.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"9 1","pages":"26"},"PeriodicalIF":3.7,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11846822/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143477161","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"3D cinematic reconstructions of cardiovascular CT presented in augmented reality: subjective assessment of clinical feasibility and potential use cases.","authors":"Benjamin Böttcher, Marly van Assen, Roberto Fari, Philipp L von Knebel Doeberitz, Gabrielle Gershon, Felix G Meinel, Carlo N De Cecco","doi":"10.1186/s41747-025-00566-1","DOIUrl":"10.1186/s41747-025-00566-1","url":null,"abstract":"<p><p>Augmented reality (AR) is a new technique enabling interaction with three-dimensional (3D) holograms of cinematic rendering (CR) reconstructions. Research in this field is in its very early steps, and data is scarce. We evaluated image quality, usability, and potential applications of AR in cardiovascular image datasets. Ten CR reconstructions of cardiovascular computed tomography (CT) datasets with complex anatomical abnormalities were presented to six radiologists and three cardiologists first on diagnostic screens and subsequently in AR. Subjective image quality and user experience were rated on 5-point Likert scales to assess usability and potential applications of AR. CR of CT datasets covering multiple images series of the same exam with differing kernels was performed in 143 ± 31 s (mean ± standard deviation); reconstruction of single CT image series took 84 ± 30 s. Mean subjective image quality was excellent, and observers showed high endorsement of the intuitive usability of the AR device and improvement of anatomical comprehensibility. AR devices were expected to have the greatest impact on patient and student education as well as multidisciplinary discussions, with less potential in clinical care. Clinical testing and preclinical implementation of AR seem feasible due to reasonable computation times and intuitive usability even for first-time users. RELEVANCE STATEMENT: The presentation of 3D cinematic rendering in augmented reality provides excellent image quality, facilitating the comprehension of anatomical structures in CT datasets. Concurrently, reasonable computation times and the intuitive usability of augmented reality devices make preclinical implementation and clinical testing feasible. KEY POINTS: 3D cinematic reconstructions presented in augmented reality improve the anatomical comprehensibility of chest CT scans. Augmented reality devices are expected to be highly beneficial in educational settings and multidisciplinary discussions. Usability and computation times are feasible for initial preclinical use cases.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"9 1","pages":"27"},"PeriodicalIF":3.7,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11846813/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143477156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping of prostate cancer microvascular patterns using super-resolution ultrasound imaging.","authors":"Mairead B Butler, Georgios Papageorgiou, Evangelos D Kanoulas, Vasiliki Voulgaridou, Hessel Wijkstra, Massimo Mischi, Christophe K Mannaerts, Steven McDougall, William Colin Duncan, Weiping Lu, Vassilis Sboros","doi":"10.1186/s41747-025-00561-6","DOIUrl":"10.1186/s41747-025-00561-6","url":null,"abstract":"<p><strong>Background: </strong>Super-resolution ultrasound imaging (SRUI) is a rapidly expanding field with the potential to impact cancer management. Image processing algorithms applied to contrast-enhanced ultrasound (CEUS) video data can track the path of the contrast agent and produce high-resolution maps of vascular networks. Our aim was to develop SRUI for mapping prostate vascular dynamics and to assess the feasibility of identifying vascular patterns associated with prostate cancer.</p><p><strong>Methods: </strong>Tracking algorithms for SRUI were developed using in silico data and validated in pre-clinical CEUS video collected from the sheep ovary. Algorithm performance was then assessed in a retrospective study of 54 image planes within 14 human prostates. CEUS data was collected for each plane, and regions of suspected cancer in each were identified from biopsy data.</p><p><strong>Results: </strong>Of three algorithms assessed, utilising vascular knowledge was found to be the most robust method. Regions of suspected cancer were associated with increased blood flow volume and speed while avascular regions were also identified. Ten scan planes had confirmed Gleason 7 cancer; of these 10 planes, 7 had distinct regions of fast and high-volume flow, while 6 had both avascular and high flow regions. The cancer-free planes had more consistent, low blood flow values across the plane.</p><p><strong>Conclusion: </strong>SRUI can be used to identify imaging biomarkers associated with vascular architecture and dynamics. These multiparameter biomarkers may be useful in pinpointing regions of significant prostate cancer.</p><p><strong>Relevance statement: </strong>Super-resolution ultrasound imaging can generate microvascular maps of the prostate, revealing tissue patterns and presenting significant potential for the identification of multiple biomarkers associated with the localisation of prostate cancer.</p><p><strong>Trial registration: </strong>Retrospectively registered NCT02831920, date 5/7/2016 https://www.</p><p><strong>Clinicaltrials: </strong>gov/study/NCT02831920 .</p><p><strong>Key points: </strong>An algorithm was developed and tested in synthetic pre-clinical and clinical data. Maps of blood vessels were created using contrast-enhanced ultrasound imaging. Specific presentations of vasculature at regions of prostate cancer have been identified.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"9 1","pages":"25"},"PeriodicalIF":3.7,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11842657/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143459817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Placental quantitative susceptibility mapping and T2* characteristics for predicting birth weight in healthy and high-risk pregnancies.","authors":"Morteza Pishghadam, Lylach Haizler-Cohen, Julius S Ngwa, Wu Yao, Kushal Kapse, Sara N Iqbal, Catherine Limperopoulos, Nickie N Andescavage","doi":"10.1186/s41747-025-00565-2","DOIUrl":"10.1186/s41747-025-00565-2","url":null,"abstract":"<p><strong>Background: </strong>The human placenta is critical in supporting fetal development, and placental dysfunction may compromise maternal-fetal health. Early detection of placental dysfunction remains challenging due to the lack of reliable biomarkers. This study compares placental quantitative susceptibility mapping and T2* values between healthy and high-risk pregnancies and investigates their association with maternal and fetal parameters and their ability to predict birth weight (BW).</p><p><strong>Methods: </strong>A total of 105 pregnant individuals were included: 68 healthy controls and 37 high-risk due to fetal growth restriction (FGR), chronic or gestational hypertension, and pre-eclampsia. Placental magnetic resonance imaging data were collected using a three-dimensional multi-echo radiofrequency-spoiled gradient-echo, and mean susceptibility and T2* values were calculated. To analyze associations and estimate BW, we employed linear regression and regression forest models.</p><p><strong>Results: </strong>No significant differences were found in susceptibility between high-risk pregnancies and controls (p = 0.928). T2* values were significantly lower in high-risk pregnancies (p = 0.013), particularly in pre-eclampsia and FGR, emerging as a predictor of BW. The regression forest model showed placental T2* as a promising mode for BW estimation.</p><p><strong>Conclusion: </strong>Our findings underscore the potential of mean placental T2* as a more sensitive marker for detecting placental dysfunction in high-risk pregnancies than mean placental susceptibility. Moreover, the high-risk status emerged as a significant predictor of BW. These results call for further research with larger and more diverse populations to validate these findings and enhance prediction models for improved pregnancy management.</p><p><strong>Relevance statement: </strong>This study highlights the potential of placental T2* magnetic resonance imaging measurements as reliable indicators for detecting placental dysfunction in high-risk pregnancies, aiding in improved prenatal care and birth weight prediction.</p><p><strong>Key points: </strong>Placental dysfunction in high-risk pregnancies is evaluated using MRI T2* values. Lower T2* values significantly correlate with pre-eclampsia and fetal growth restriction. T2* MRI may predict birth weight, enhancing prenatal care outcomes.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"9 1","pages":"18"},"PeriodicalIF":3.7,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11836258/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143450523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sub-1-min relaxation-enhanced non-contrast non-triggered cervical MRA using compressed SENSE with deep learning reconstruction in healthy volunteers.","authors":"Jan Paul Janssen, Kenan Kaya, Robert Terzis, Robert Hahnfeldt, Roman Johannes Gertz, Lukas Goertz, Stephan Skornitzke, Juliana Tristram, Thomas Dratsch, Cansin Goezdas, Christoph Kabbasch, Kilian Weiss, Lenhard Pennig, Carsten Herbert Gietzen","doi":"10.1186/s41747-025-00560-7","DOIUrl":"10.1186/s41747-025-00560-7","url":null,"abstract":"<p><strong>Background: </strong>We evaluated the acceleration of a three-dimensional isotropic flow-independent magnetic resonance angiography (MRA) (relaxation-enhanced angiography without contrast and triggering, REACT) of neck arteries using compressed SENSE (CS) combined with deep learning (adaptive intelligence, AI)-based reconstruction (CS-AI).</p><p><strong>Methods: </strong>Thirty-four volunteers received 3-T REACT MRA, acquired threefold: (i) CS acceleration factor 7 (CS7), scan time 1:20 min:s; (ii) CS acceleration factor 10 (CS10), scan time 0:55 min:s; and (iii) CS-AI acceleration factor 10 (CS10-AI), scan time 0:55 min:s. Two radiologists rated the image quality of seven arterial segments and overall image noise. Additionally, a pairwise forced-choice comparison was conducted. Apparent signal-to-noise ratio (aSNR) and contrast-to-noise ratio (aCNR) were measured, and image sharpness was assessed using the edge-rise distance (ERD). Multiple t-tests and nonparametric tests with Bonferroni correction were performed for comparison to CS7 as the reference standard.</p><p><strong>Results: </strong>Compared to CS7, CS10 showed lower image quality (p < 0.001) while CS10-AI obtained higher scores (p = 0.010). Image noise was similar between CS7 and CS10 (p = 0.138) while CS10-AI yielded a lower noise (p = 0.008). Forced choice revealed preferences for CS7 over CS10 (p < 0.001), but no preference between CS7 and CS10-AI (p > 0.999). Compared to CS7, aSNR and aCNR were lower in CS10 (p < 0.001) and the ERD was longer (p = 0.004), while CS10-AI provided better aSNR and aCNR (p = 0.001) and showed no difference in ERD (p = 0.776).</p><p><strong>Conclusion: </strong>Sub-1-min CS-AI cervical REACT MRA was acquired without compromising image quality.</p><p><strong>Relevance statement: </strong>The implementation of a fast and reliable non-contrast MRA has the potential to reduce costs and time while increasing patient comfort and safety. Clinical studies evaluating the diagnostic performance for stenosis or dissection are needed.</p><p><strong>Trial registration: </strong>DRKS00030210 (German Clinical Trials Register; https://drks.de/ ) KEY POINTS: Deep learning reconstruction enables sub-1-min non-contrast-enhanced MRA of extracranial arteries. Acceleration without deep learning reconstruction causes inferior image quality. Acceleration with deep learning reconstruction exceeds, in part, the clinical standard.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"9 1","pages":"19"},"PeriodicalIF":3.7,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11836250/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143450525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intraindividual crossover comparison of gadobenate dimeglumine-enhanced and gadoxetate disodium-enhanced MRI for characterizing focal liver lesions.","authors":"Wenjie Tang, Yuanqiang Xiao, Sichi Kuang, Dailin Rong, Bingjun He, Luigi Grazioli, Shahid M Hussain, Jin Wang","doi":"10.1186/s41747-025-00551-8","DOIUrl":"10.1186/s41747-025-00551-8","url":null,"abstract":"<p><strong>Background: </strong>Gadobenate and gadoxetate are hepatobiliary magnetic resonance imaging (MRI) contrast agents. We intraindividually compared these two agents for the characterization of focal liver lesions (FLLs).</p><p><strong>Methods: </strong>A total of 140 adult subjects were randomized to undergo two 3-T MRI exams separated by 7-14 days, one with 0.05 mmol/kg gadobenate and one with 0.025 mmol/kg gadoxetate. For both exams, we acquired the same unenhanced T1-weighted, T2-weighted, and diffusion-weighted sequences, followed by contrast-enhanced T1-weighted sequences during the dynamic and hepatobiliary phases (HBP) (at 20 min for gadoxetate, at 120 min for gadobenate). Three experienced unaffiliated readers independently evaluated each exam in blinded, randomized order for lesion nature (benign/malignant) and specific lesion diagnosis. McNemar test, Wald tests. paired t-tests and κ statistics were used.</p><p><strong>Results: </strong>A total of 208 FLLs (108 malignant and 100 benign) were confirmed at final diagnosis. Sensitivity and specificity for malignant/benign differentiation ranged from 91.6% to 99.1% and from 87.5% to 90.5% for gadobenate, and from 86.0% to 91.6% and from 79.7% to 83.6% for gadoxetate. Significantly (p ≤ 0.025) higher values for gadobenate were determined for all diagnostic performance parameters except for sensitivity and negative predictive value for one reader. Significantly (p < 0.001) greater accuracy and confidence for specific lesion diagnosis was achieved with gadobenate for two of three blinded readers. Interreader agreement for malignant/benign differentiation was better with gadobenate (κ = 0.91 versus κ = 0.72).</p><p><strong>Conclusion: </strong>Gadobenate was superior to gadoxetate for the differentiation and diagnosis of malignant and benign FLLs for two of three readers. Further confirmatory studies that include a wider representation of different types of FLLs are warranted.</p><p><strong>Relevance statement: </strong>Better diagnostic performance and greater confidence in the characterization of FLLs with gadobenate might improve patient management decisions and timings, and potentially lead to better patient outcomes.</p><p><strong>Key points: </strong>Better diagnostic performance for the differentiation of FLLs was achieved with gadobenate for two of three readers. Reader confidence for lesion diagnosis was greater with gadobenate. Superior dynamic phase imaging with gadobenate was crucial for accurate lesion diagnosis.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"9 1","pages":"23"},"PeriodicalIF":3.7,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11836252/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143450420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cer-ConvN3Unet: an end-to-end multi-parametric MRI-based pipeline for automated detection and segmentation of cervical cancer.","authors":"Shao-Jun Xia, Bo Zhao, Yingming Li, Xiangxing Kong, Zhi-Nan Wang, Qingmo Yang, Jia-Qi Wu, Haijiao Li, Kun Cao, Hai-Tao Zhu, Xiao-Ting Li, Xiao-Yan Zhang, Ying-Shi Sun","doi":"10.1186/s41747-025-00557-2","DOIUrl":"10.1186/s41747-025-00557-2","url":null,"abstract":"<p><strong>Background: </strong>We established and validated an innovative two-phase pipeline for automated detection and segmentation on multi-parametric cervical cancer magnetic resonance imaging (MRI) and investigated the clinical efficacy.</p><p><strong>Methods: </strong>The retrospective multicenter study included 125 cervical cancer patients enrolled in two hospitals for 14,547 two-dimensional images. All the patients underwent pelvic MRI examinations consisting of diffusion-weighted imaging (DWI), T2-weighted imaging (T2WI), and contrast-enhanced T1-weighted imaging (CE-T1WI). The deep learning framework involved a multiparametric detection module utilizing ConvNeXt blocks and a subsequent segmentation module utilizing 3-channel DoubleU-Nets. The pipeline was trained and tested (80:20 ratio) on 3,077 DWI, 2,990 T2WI, and 8,480 CE-T1WI slices.</p><p><strong>Results: </strong>In terms of reference standards from gynecologic radiologists, the first automated detection module achieved overall results of 93% accuracy (95% confidence interval 92-94%), 93% precision (92-94%), 93% recall (92-94%), 0.90 κ (0.89-0.91), and 0.93 F1-score (0.92-0.94). The second-stage segmentation exhibited Dice similarity coefficients and Jaccard values of 83% (81-85%) and 71% (69-74%) for DWI, 79% (75-82%), and 65% (61-69%) for T2WI, 74% (71-76%) and 59% (56-62%) for CE-T1WI.</p><p><strong>Conclusion: </strong>Independent experiments demonstrated that the pipeline could get high recognition and segmentation accuracy without human intervention, thus effectively reducing the delineation burden for radiologists and gynecologists.</p><p><strong>Relevance statement: </strong>The proposed pipeline is potentially an alternative tool in imaging reading and processing cervical cancer. Meanwhile, this can serve as the basis for subsequent work related to tumor lesions. The pipeline contributes to saving the working time of radiologists and gynecologists.</p><p><strong>Key points: </strong>An AI-assisted multiparametric MRI-based pipeline can effectively support radiologists in cervical cancer evaluation. The proposed pipeline shows high recognition and segmentation performance without manual intervention. The proposed pipeline may become a promising auxiliary tool in gynecological imaging.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"9 1","pages":"20"},"PeriodicalIF":3.7,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11836247/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143450450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pulmonary regional blood flow: validation of low-dose two-volume dynamic CT perfusion imaging in a swine model.","authors":"Yixiao Zhao, Nile Luu, Logan Hubbard, Shant Malkasian, Sabee Molloi","doi":"10.1186/s41747-025-00556-3","DOIUrl":"10.1186/s41747-025-00556-3","url":null,"abstract":"<p><strong>Background: </strong>We aimed to validate a low-dose two-volume pulmonary computed tomography (CT) perfusion technique.</p><p><strong>Methods: </strong>Five Yorkshire swine (weight 53.6 ± 2.6 kg) underwent 21 independent CT perfusion acquisitions. Intravenous contrast material (370 mg/mL iodine, 0.5 mL/kg) and saline chaser (0.5 mL/kg) were injected at 5 mL/s for each acquisition. Two-volume and multivolume dynamic CT perfusion data were acquired using a 320-slice CT, with multivolume measurements serving as the reference standard. The two-volume CT perfusion involved a low-dose (50 mA) volume scan before contrast injection and a diagnostic (300 mA) volume scan after bolus-tracking in the main pulmonary artery at the peak contrast enhancement. Multivolume CT perfusion included 15-20 volume scans for blood flow measurement. Paired sample t-test, linear regression, and Bland-Altman analysis compared both global and regional two-volume perfusion measurements to the reference standard. The reproducibility of the two-volume CT perfusion was assessed from two independent measurements under the same perfusion condition.</p><p><strong>Results: </strong>Two-volume global perfusion measurements (P_2V) were related to reference multivolume (P_MV) measurements by P_2V = 0.96 × P_MV + 0.45 (r = 0.92), with a root-mean-square error of 1.29 mL/min/g and a root-mean-square deviation of 1.29 mL/min/g. The CT dose index for the two-volume and multivolume CT perfusion measurements were 9.3 mGy and 184.8 mGy, respectively.</p><p><strong>Conclusion: </strong>We successfully validated a prospective, two-volume CT perfusion technique in a swine model. The findings affirm the feasibility of accurate and reproducible pulmonary blood flow measurement.</p><p><strong>Relevance statement: </strong>This two-volume CT pulmonary perfusion technique, validated in a swine model, demonstrates the feasibility of blood flow measurement with a substantial reduction in radiation exposure. It could allow low-dose regional blood flow measurement in the assessment of pulmonary artery disease in humans.</p><p><strong>Key points: </strong>Lung perfusion can be measured in mL/min/g using a prospective, two-volume CT technique. Flow measurement is achievable in a swine model with a radiation dose as low as 9.3 mGy. CT angiography and perfusion can be acquired following a single contrast injection.</p>","PeriodicalId":36926,"journal":{"name":"European Radiology Experimental","volume":"9 1","pages":"17"},"PeriodicalIF":3.7,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11836245/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143450524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}