Neuroradiology最新文献

{"title":"Radiomics based on preoperative magnetic resonance imaging predict the cell lineages of nonfunctioning pituitary neuroendocrine tumors.","authors":"Xuening Zhao, Xu Fu, Xiaochen Wang, Sihui Wang, Lingxu Chen, Mengyuan Yuan, Jiangang Liu, Shengjun Sun","doi":"10.1007/s00234-025-03593-2","DOIUrl":"https://doi.org/10.1007/s00234-025-03593-2","url":null,"abstract":"<p><strong>Objective: </strong>Accurate preoperative predict the cell lineages of non-functioning pituitary neuroendocrine tumors (NFPitNETs) can help neurosurgeons develop treatment strategies. This study aimed to predict the three cell lineages of NFPitNETs using radiomics based on MRI.</p><p><strong>Methods: </strong>NFPitNETs patients from January 2019 and January 2023 were retrospectively enrolled, with adenoma lineages including SF-1 (n = 239), TPIT (n = 204), and PIT-1 (n = 100). Sagittal T1-weighted images (T1WI), contrast-enhanced (CE) sagittal T1WI, CE-coronal T1WI, and axial T2WI were obtained for tumor segmentation on ITK-SNAP. Pyradiomics was used for features extracted. Variance threshold method, t-test, and LASSO were used for feature selection. Support vector machine (SVM) and random forest (RF) were used to predict the three-lineages adenomas based on their radiomics and semantic features. Receiver operating characteristic curve-area under the curve (ROC-AUC) analysis was used to assess the model's performance.</p><p><strong>Results: </strong>A total of 543 patients with NFPitNETs (mean age, 49.46 ± 12.39) were included. Patients with SF-1 adenomas had a higher mean age than those with TPIT and PIT-1 adenomas (52.84 ± 11.56 vs 49.94 ± 10.54 vs 40.42 ± 13.41, p < 0.001). Female patients are more common in TPIT and PIT-1 adenomas than SF-1 ones (96.57% vs 69% vs 41%, p < 0.001). The SVM model incorporating semantic and radiomics features based on CE-coronal T1WI performed the best, with a macro-average AUC of 0.899. CE-coronal T1WI were the best among all the MR sequences for predicting the cell lineages of NFPitNETs.</p><p><strong>Conclusion: </strong>Radiomics based on preoperative MRI can help predict the cell lineages of NFPitNETs, which prove useful to neurosurgeons to develop treatment strategies.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143674328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Usefulness of 3T split acquisition fast spin-echo diffusion-weighted imaging for differentiating pituitary abscess from other sellar cystic lesions: a preliminary study.","authors":"Soichiro Ishiuchi, Hiroyuki Uetani, Naoki Shinojima, Takeshi Nakaura, Mika Kitajima, Kosuke Morita, Kouji Ogasawara, Masami Yoneyama, Akitake Mukasa, Toshinori Hirai","doi":"10.1007/s00234-024-03531-8","DOIUrl":"https://doi.org/10.1007/s00234-024-03531-8","url":null,"abstract":"<p><strong>Purpose: </strong>Pituitary abscess is a rare condition that can be challenging to distinguish from other sellar cystic lesions (OSCLs) due to no specific symptoms and overlapping imaging features. Accurate differentiation is crucial for appropriate treatment planning. This study aimed to evaluate the usefulness of 3T split acquisition fast spin-echo diffusion-weighted imaging (SPLICE-DWI) in differentiating pituitary abscesses from OSCLs.</p><p><strong>Methods: </strong>We retrospectively analyzed magnetic resonance imaging (MRI) data from 32 patients with sellar cystic lesions, including 5 with pathologically confirmed pituitary abscesses and 27 with OSCLs. Conventional MRI sequences and SPLICE-DWI were performed, and apparent diffusion coefficient (ADC) values were calculated. Qualitative assessments of signal intensity on SPLICE-DWI and conventional MRI were conducted by two neuroradiologists. The diagnostic performance of these imaging parameters was evaluated using receiver operating characteristic (ROC) analysis.</p><p><strong>Results: </strong>SPLICE-DWI successfully differentiated pituitary abscesses from OSCLs, showing significantly lower ADC values in the abscess group compared to OSCLs (0.62 ± 0.07 × 10^- 3 mm²/s vs. 1.83 ± 0.70 × 10^- 3 mm²/s, P = 0.002). ROC analysis revealed high diagnostic accuracy for DWI signal intensity (AUC = 0.89) and ADC values (AUC = 0.95). No significant differences were found in contrast-enhanced T1-weighted imaging (T1WI) features such as ring enhancement, pituitary stalk enlargement, or sphenoid sinus mucosal thickening between the two groups.</p><p><strong>Conclusion: </strong>SPLICE-DWI is a valuable tool for the differentiation of pituitary abscesses from OSCLs, offering high diagnostic accuracy.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143674278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Use of amide proton transfer (APT) imaging in the differentiation of pediatric low-grade brain tumors from tumor-like brain lesions.","authors":"Antonia Ramaglia, Costanza Parodi, Claudia Milanaccio, Antonio Verrico, Marta Molteni, Maria Luisa Garrè, Mattia Pacetti, Stephanie Vella, Martina Resaz, Domenico Tortora, Mariasavina Severino, Andrea Rossi","doi":"10.1007/s00234-025-03582-5","DOIUrl":"https://doi.org/10.1007/s00234-025-03582-5","url":null,"abstract":"<p><strong>Background and purpose: </strong>Low grade tumors (LGT) are the most frequent central nervous system lesions observed in children. Despite the high-throughput research, differentiating LGT from tumor- like lesions (TLL) and providing an accurate differential diagnosis based on conventional MRI remains a challenge. For this reason, advanced MR sequences are routinely investigated and applied in clinical practice. The aim of this study is to explore the potential of the amide proton transfer (APTw) sequence as a tool for discriminating LGT from TLL.</p><p><strong>Materials and methods: </strong>In this single-center retrospective study, we recruited 35 patients (20 with a histologically confirmed LGT, and 15 with a TLL) with both conventional and APT MRI images obtained on a 3T clinical scanner at onset or prior to treatment/surgery. Two volumes of interest (VOI), namely the whole lesion and the normal appearing white matter (NAWM), were defined using the semi-automatic segmentation tool from Philips Intellispace portal for Windows (v. 8). The mean APTw (mAPTw) and difference between the mAPTw lesion and the NAWM (dAPTw) were measured and compared between the two groups.</p><p><strong>Results: </strong>Lower values were found in the TLL group compared to the LGT group for both the mAPTw (1.51 ± 0.64% vs. 2.87 ± 0.96%) and dAPTw (0.24 ± 0.72% vs. 1.53 ± 1.08%) (p-value < 0.001). Based on ROC curve analysis, optimal cut-offs value for mAPTw and dATPw were 1.79 and 0.53, respectively.</p><p><strong>Conclusion: </strong>APT imaging may prove useful to discriminate between LGT and TLL in pediatric patients.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143674257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning-assisted detection of intracranial hemorrhage: validation and impact on reader performance.","authors":"Dong-Wan Kang, Museong Kim, Gi-Hun Park, Yong Soo Kim, Moon-Ku Han, Myungjae Lee, Dongmin Kim, Wi-Sun Ryu, Han-Gil Jeong","doi":"10.1007/s00234-025-03560-x","DOIUrl":"https://doi.org/10.1007/s00234-025-03560-x","url":null,"abstract":"<p><strong>Purpose: </strong>Intracranial hemorrhage (ICH) requires urgent treatment, and accurate and timely diagnosis is essential for improving outcomes. This pivotal clinical trial aimed to validate a deep learning algorithm for ICH detection and assess its clinical utility through a reader performance test.</p><p><strong>Methods: </strong>Retrospective CT scans from patients with and without ICH were collected from a tertiary hospital. Two experts evaluated all scans, with a third expert reviewing disagreements for the final diagnosis. We analyzed the performance of the deep learning algorithm, JLK-ICH, for all cases and ICH subtypes. Additional external validation was performed using a multi-ethnic U.S.</p><p><strong>Dataset: </strong>A reader performance study included six non-expert readers who evaluated 800 CT scans, with and without JLK-ICH assistance, following a washout period. ICH presence and five-point scale confidence level for decisions were rated.</p><p><strong>Results: </strong>A total of 1,370 CT scans were evaluated. The deep learning model showed 98.7% sensitivity (95% confidence interval [CI] 97.8-99.3%), 88.5% specificity (95% CI, 83.6-92.3%), and an area under the receiver operating characteristic curve (AUROC) of 0.936 (95% CI, 0.915-0.957). The model maintained high accuracy across all ICH subtypes, and additional external validation confirmed these results. In the reader performance study, AUROC with JLK-ICH assistance (0.967 [0.953-0.981]) surpassed that without assistance (0.953 [0.938-0.957]; P = 0.009). JLK-ICH particularly improved performance when readers were highly uncertain.</p><p><strong>Conclusion: </strong>The JLK-ICH algorithm demonstrated high accuracy in detecting all ICH subtypes. Non-expert readers significantly improved diagnostic accuracy for brain CT scans with deep learning assistance.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143674299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Safety of emergent carotid stenting after thrombolysis: a multicenter retrospective matched analysis.","authors":"Francesca Colò, Andrea M Alexandre, Valerio Brunetti, Francesco Arba, Luca Scarcia, Alessandro Pedicelli, Mariangela Piano, Maria Ruggiero, Joseph D Gabrieli, Valerio Da Ros, Daniele Romano, Riccardo Russo, Anna Cavallini, Guido Bigliardi, Antonio A Caragliano, Maria P Ganimede, Giancarlo Salsano, Pietro Panni, Emilio Lozupone, Sabrina Anticoli, Monica Ferrante, Andrea Zini, Danilo Toni, Thanh N Nguyen, Frédéric Clarençon, Aldobrando Broccolini","doi":"10.1007/s00234-025-03571-8","DOIUrl":"https://doi.org/10.1007/s00234-025-03571-8","url":null,"abstract":"<p><strong>Purpose: </strong>Mechanical thrombectomy (MT) with emergent carotid artery stenting (eCAS) has been suggested to provide greater benefits for patients with tandem lesions (TL), but there is uncertainty about the most appropriate peri-procedural antiplatelet therapy for patients at higher risk of brain hemorrhage. This study aimed to assess the safety of intravenous thrombolysis (IVT) in patients with acute TL undergoing MT with eCAS.</p><p><strong>Methods: </strong>The databases of 17 stroke centers were retrospectively screened for consecutive patients with acute TL who underwent MT and eCAS. Propensity score matching (PSM) was used to evaluate the safety of IVT, balancing for peri-procedural antiplatelet therapies. Primary outcome measures were the occurrence of parenchymal hemorrhage (PH) type 2 and mortality within 90 days from the index event. Secondary outcome measures included occurrence of PH type 1, extracranial bleeding events, early stent thrombosis, efficient recanalization after MT and the 90-day functional outcome.</p><p><strong>Results: </strong>Among 560 enrolled patients, 47.3% received IVT prior to the endovascular procedure. After PSM, there was no significant difference between patients treated with and without IVT under different antiplatelet regimens concerning the rates of PH type 2 (5.2% versus 6.9%, p = 0.7, respectively) and of mortality of any cause (7.5% vs. 8.2%, p = 0.8). In addition, IVT did not impact recanalization rates or clinical outcome.</p><p><strong>Conclusions: </strong>The safety of MT with eCAS in acute TL is not affected by prior IVT. Furthermore, IVT does not ameliorate recanalization rates and clinical outcome. These findings are exploratory and require validation through future randomized controlled studies.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143674252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prognostic significance of frailty in chronic subdural hematoma: implications for treatment selection in the era of middle meningeal artery embolization.","authors":"Alis J Dicpinigaitis, Gary Kocharian, Michael Covell, Fawaz Al-Mufti, Jared Knopman, Christian A Bowers","doi":"10.1007/s00234-025-03591-4","DOIUrl":"https://doi.org/10.1007/s00234-025-03591-4","url":null,"abstract":"<p><strong>Purpose: </strong>Middle meningeal artery embolization (MMAE) as a standalone or adjunctive therapy has emerged as an efficacious and safe treatment for chronic/subacute subdural hematoma (csaSDH). The objective of this study is to compare the prognostic significance of frailty in csaSDH patients treated with MMAE alone or with craniotomy/burr hole (CBH).</p><p><strong>Methods: </strong>Hospitalization records were identified in the National Inpatient Sample (2016-2020) and the cohort was stratified by increasing frailty thresholds, quantified by the Risk Analysis Index (RAI). Effect sizes of frailty tiers for poor outcome (defined as non-routine discharge disposition) produced from multivariable logistic regression models and discrimination (c-statistic) were evaluated separately in the MMAE only and CBH sub-cohorts.</p><p><strong>Results: </strong>This analysis identified 13,390 csaSDH hospitalizations, of which 595 (5%) documented treatment with MMAE only. Although all frailty tiers of the categorical RAI were significantly associated with poor outcome in the CBH cohort, lower effect sizes were observed in the MMAE cohort. Discrimination of RAI for poor outcome was significantly greater in the CBH cohort compared to the MMAE only cohort.</p><p><strong>Conclusion: </strong>In comparison to surgical evacuation, frailty demonstrated lower effect sizes and worse discrimination for poor outcomes in patients treated with MMAE, suggesting that frail patients may be more likely to achieve better outcomes following this less invasive therapy. MMAE may be considered as a first-line or standalone treatment in certain patients.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143674323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intravoxel incoherent motion imaging and dynamic susceptibility contrast perfusion MRI in differentiation between recurrent intracranial tumor and treatment-induced changes.","authors":"Jussi Hellström, Ishita Huq, Petra Witt Nyström, Erik Blomquist, Sylwia Libard, Raili Raininko, Johan Wikström","doi":"10.1007/s00234-025-03575-4","DOIUrl":"https://doi.org/10.1007/s00234-025-03575-4","url":null,"abstract":"<p><strong>Purpose: </strong>To compare intravoxel incoherent motion (IVIM) imaging to dynamic susceptibility-weighted contrast (DSC) perfusion MRI in differentiating tumor recurrence from treatment-induced changes.</p><p><strong>Methods: </strong>Our prospective study included patients previously treated with radiotherapy for intracranial tumors who later developed a new or increasing contrast-enhancing lesion. The final diagnosis was based on neuropathology or 6-month follow-up. MR examinations were performed for calculation of the perfusion fraction (f) using the IVIM technique and relative blood volume (rCBV) using DSC perfusion. Measurements of f and rCBV were made by two independent readers in hotspots when possible, but otherwise in the whole enhancing region. Measures of rCBV were normalized to the contralateral region. Receiver operating characteristics (ROC) analysis was performed.</p><p><strong>Results: </strong>Sixty patients (35 men, median age 49, range 20-77) were evaluated. Forty-four patients had tumor recurrence and 16 had treatment-induced changes. Mean f was 0.090 for tumors and 0.058 for treatment-induced changes (p = 0.002). Mean rCBV was 3.52 and 1.79, respectively (p = 0.002). The area under the curve (AUC) in the ROC analysis was 0.72 for f and 0.77 for rCBV. Cutoff values of 0.073 for f and 2.26 for rCBV yielded equal values for sensitivity (73%), specificity (75%), and accuracy (73%). The 90th percentile value of rCBV was 4.77 for tumors and 2.53 for treatment-induced changes (p = 0.0004) and yielded the highest AUC (0.79) and a sensitivity/specificity/accuracy of 80%/75%/78% at cutoff value 3.25.</p><p><strong>Conclusion: </strong>The accuracy of the IVIM parameter f is similar to that of rCBV in differentiating tumor recurrence from treatment-induced changes.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143674321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Qualitative MRI features in the differentiation between primary and secondary CNS lymphoma.","authors":"Yusuf Kenan Cetinoglu, Kazım Ayberk Sinci, Merve Horoz, Fazıl Gelal","doi":"10.1007/s00234-025-03594-1","DOIUrl":"https://doi.org/10.1007/s00234-025-03594-1","url":null,"abstract":"<p><strong>Purpose: </strong>Differentiating between primary CNS lymphomas (PCNSL) and secondary CNS lymphomas (SCNSL) remains a challenge in imaging. The aim of this study was to differentiate histopathologically-proven PCNSL and SCNSL by using 25 qualitative VASARI and five other MRI features.</p><p><strong>Methods: </strong>MRIs of 31 cases (19 PCNSL and 12 SCNSL) obtained between January 2010 and February 2022 were retrospectively reviewed. Two blinded readers independently evaluated images without knowledge of clinical data or whether CNS lymphoma was primary or secondary. The findings of each reader were recorded to assess interreader agreement. The results of two readers were evaluated by a senior neuroradiologist to reach a consensus. A statistical analysis was performed on the collected data.</p><p><strong>Results: </strong>Most VASARI features showed no statistically significant differences between the two groups, except for two features. Tumor location exhibited a statistically different distribution between PCNSL and SCNSL groups (p = 0.036). Proportion of edema was greater in the PCNSL group compared to the SCNSL group (p = 0.049). Among other MRI features, infratentorial involvement was more frequent in the SCNSL group (p = 0.014), while notch sign was more commonly detected in the PCNSL group (p = 0.027). Inter-reader agreement for VASARI features ranged from moderate to almost perfect, and for other MRI features, it ranged from fair to almost perfect.</p><p><strong>Conclusion: </strong>Despite the challenges in distinguishing imaging features of PCNSL and SCNSL; frontal lobe location, a higher proportion of edema and the presence of a notch sign may indicate PCNSL, while infratentorial involvement may suggest SCNSL.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143649795","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neonatal subpial hemorrhage: clinical presentation, neuroimaging findings and outcome.","authors":"Andres Server, Anna Latysheva, Bård Nedregaard, Arild Erland Rønnestad, Pål Bache Marthinsen","doi":"10.1007/s00234-025-03589-y","DOIUrl":"https://doi.org/10.1007/s00234-025-03589-y","url":null,"abstract":"<p><strong>Purpose: </strong>Subpial hemorrhage is a rare form of intracranial hemorrhage (ICH) in neonates that remains underreported and inadequately understood. The aim of this study is to characterize the neuroimaging patterns of subpial hemorrhage, assess changes in the underlying brain parenchyma, and examine its clinical features and outcomes.</p><p><strong>Methods: </strong>We reviewed the medical records and neuroimaging data of neonates with subpial hemorrhage admitted to our hospital between January 2010 and December 2023. Cases of subpial hemorrhages were identified through keywords searches within the hospital´s electronic database.</p><p><strong>Results: </strong>Twenty-eight patients were included in this retrospective study, 82% of whom were born at term. The most common clinical indication for imaging was a combination of apneas and seizures, ocurring in 50%. Hematologic abnormalities were present in 58% of patients. Magnetic resonance imaging (MRI) was performed acutely at the time of presentation between days 1 and 9 of life in 85% of cases. Subpial hemorrhages were unilateral in 86% of neonates, most commonly located in the temporal lobe (44%), and associated with other type of intracranial hemorrhage in 96% of cases, most often parenchymal (86%) and subdural (64%) hemorrhages. We identified three imaging patterns of subpial hemorrhage and two patterns of changes in the underlying brain parenchyma. Additionally, the hyperintense pia mater sign (HPm-sign) was observed on time-of-flight MR angiography (TOF-MRA) in 12 of 18 patients. Neurologic sequelae were noted in 28% of survivors.</p><p><strong>Conclusion: </strong>Subpial hemorrhage has a distinctive MR pattern, often accompanied with cortical infarction and in most cases underlying parenchymal hemorrhage. In this study, we identified the HPm-sign that may be used to differentiate subpial hemorrhage from other types of hemorrhages. Additionally, we found a correlation between prominent medullary veins (PMV) and intraparenchymal hemorrhage (IPH).</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143649794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accelerated intracranial time-of-flight MR angiography with image-based deep learning image enhancement reduces scan times and improves image quality at 3-T and 1.5-T.","authors":"Young Hun Jeon, Chanrim Park, Kyung Hoon Lee, Kyu Sung Choi, Ji Ye Lee, Inpyeong Hwang, Roh-Eul Yoo, Tae Jin Yun, Seung Hong Choi, Ji-Hoon Kim, Chul-Ho Sohn, Koung Mi Kang","doi":"10.1007/s00234-025-03564-7","DOIUrl":"https://doi.org/10.1007/s00234-025-03564-7","url":null,"abstract":"<p><strong>Purpose: </strong>Three-dimensional time-of-flight magnetic resonance angiography (TOF-MRA) is effective for cerebrovascular disease assessment, but clinical application is limited by long scan times and low spatial resolution. Recent advances in deep learning-based reconstruction have shown the potential to improve image quality and reduce scan times. This study aimed to evaluate the effectiveness of accelerated intracranial TOF-MRA using deep learning-based image enhancement (TOF-DL) compared to conventional TOF-MRA (TOF-Con) at both 3-T and 1.5-T.</p><p><strong>Materials and methods: </strong>In this retrospective study, patients who underwent both conventional and 40% accelerated TOF-MRA protocols on 1.5-T or 3-T scanners from July 2022 to March 2023 were included. A commercially available DL-based image enhancement algorithm was applied to the accelerated MRA. Quantitative image quality assessments included signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), contrast ratio (CR), and vessel sharpness (VS), while qualitative assessments were conducted using a five-point Likert scale. Cohen's d was used to compare the quantitative image metrics, and a cumulative link mixed regression model analyzed the readers' scores.</p><p><strong>Results: </strong>A total of 129 patients (mean age, 64 years ± 12 [SD], 99 at 3-T and 30 at 1.5-T) were included. TOF-DL showed significantly higher SNR, CNR, CR, and VS compared to TOF-Con (CNR = 183.89 vs. 45.58; CR = 0.63 vs. 0.59; VS = 0.73 vs. 0.61; all p < 0.001). The improvement in VS was more pronounced at 1.5-T (Cohen's d = 2.39) compared to 3-T HR and routine (Cohen's d = 0.83 and 0.75, respectively). TOF-DL also outperformed TOF-Con in qualitative image parameters, enhancing the visibility of small- and medium-sized vessels, regardless of the degree of resolution and field strength. TOF-DL showed comparable diagnostic accuracy (AUC: 0.77-0.85) to TOF-Con (AUC: 0.79-0.87) but had higher specificity for steno-occlusive lesions.</p><p><strong>Conclusions: </strong>Accelerated intracranial MRA with deep learning-based reconstruction reduces scan times by 40% and significantly enhances image quality over conventional TOF-MRA at both 3-T and 1.5-T.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143649793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}