Neuroradiology最新文献

{"title":"FET PET to differentiate between post-treatment changes and recurrence in high-grade gliomas: a single center multidisciplinary clinic controlled study.","authors":"Ameya D Puranik, Indraja D Dev, Venkatesh Rangarajan, Yash Jain, Sukriti Patra, Nilendu C Purandare, Arpita Sahu, Amitkumar Choudhary, Kajari Bhattacharya, Tejpal Gupta, Abhishek Chatterjee, Archya Dasgupta, Aliasgar Moiyadi, Prakash Shetty, Vikas Singh, Epari Sridhar, Ayushi Sahay, Aekta Shah, Nandini Menon, Suchismita Ghosh, Sayak Choudhury, Sneha Shah, Archi Agrawal, N Lakshminarayanan, Amit Kumar, Arjun Gopalakrishna","doi":"10.1007/s00234-024-03495-9","DOIUrl":"10.1007/s00234-024-03495-9","url":null,"abstract":"<p><strong>Purpose: </strong>The clinico-radiological dilemma in post-treatment high-grade gliomas, between disease recurrence (TR) and treatment-related changes (TRC), still persists. FET (Fluoro-ethyl-tyrosine) PET has been extensively used as problem-solving modality for cases where MR imaging is inconclusive. We incorporated a systematic imaging and clinical follow-up algorithm in a multi-disciplinary clinic (MDC) setting to analyse our cohort of FET PET in post-treatment gliomas.</p><p><strong>Methods: </strong>We retrospectively analyzed 171 patients of post-treatment grade III and IV glioma with equivocal findings on MRI. 185-222 MBq of 18 F-FET was injected and dedicated static imaging of brain was performed at 20 min. TBR (Tumor to background ratio) was used as semi-quantitative parameter. Cutoff of 2.5 was used for image interpretation. Imaging findings were confirmed with histopathological diagnosis, wherever available or in a multidisciplinary joint clinic based on serial imaging.</p><p><strong>Results: </strong>121 of 171 patients showed recurrent disease on FET PET, on follow up, 109 were confirmed with recurrence; 7 patients showed TRC, whereas 5 were treated with bevacizumab, with no further clinico-radiological deterioration, thus confirming TRC. 50 patients showed TRC on FET PET, on follow up on follow up, 40 were confirmed as true-negative. 10 patients who showed TBR less than 2.5 had confirmed TR on subsequent MR imaging. The overall sensitivity and specificity was 91.6 and 76.9% respectively, with a diagnostic accuracy of 87.13%.</p><p><strong>Conclusion: </strong>There is potential for FET PET to be used along with MRI in the post treatment algorithm of high-grade glial tumors.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":"363-369"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11893651/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142622510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence-assisted volume isotropic simultaneous interleaved bright- and black-blood examination for brain metastases.","authors":"Kazufumi Kikuchi, Osamu Togao, Yoshitomo Kikuchi, Koji Yamashita, Daichi Momosaka, Kazunori Fukasawa, Shunsuke Nishimura, Hiroyuki Toyoda, Makoto Obara, Akio Hiwatashi, Kousei Ishigami","doi":"10.1007/s00234-024-03454-4","DOIUrl":"10.1007/s00234-024-03454-4","url":null,"abstract":"<p><strong>Purpose: </strong>To verify the effectiveness of artificial intelligence-assisted volume isotropic simultaneous interleaved bright-/black-blood examination (AI-VISIBLE) for detecting brain metastases.</p><p><strong>Methods: </strong>This retrospective study was approved by our institutional review board and the requirement for written informed consent was waived. Forty patients were included: 20 patients with and without brain metastases each. Seven independent observers (three radiology residents and four neuroradiologists) participated in two reading sessions: in the first, brain metastases were detected using VISIBLE only; in the second, the results of the first session were comprehensively evaluated by adding AI-VISIBLE information. Sensitivity, diagnostic performance, and false positives/case were evaluated. Diagnostic performance was assessed using a figure-of-merit (FOM). Sensitivity and false positives/case were evaluated using McNemar and paired t-tests, respectively.</p><p><strong>Results: </strong>The McNemar test revealed a significant difference between VISIBLE with/without AI information (P < 0.0001). Significantly higher sensitivity (94.9 ± 1.7% vs. 88.3 ± 5.1%, P = 0.0028) and FOM (0.983 ± 0.009 vs. 0.972 ± 0.013, P = 0.0063) were achieved using VISIBLE with AI information vs. without. No significant difference was observed in false positives/case with and without AI information (0.23 ± 0.19 vs. 0.18 ± 0.15, P = 0.250). AI-assisted results of radiology residents became comparable to results of neuroradiologists (sensitivity, FOM: 85.9 ± 3.4% vs. 90.0 ± 5.9%, 0.969 ± 0.016 vs. 0.974 ± 0.012 without AI information; 94.8 ± 1.3% vs. 95.0 ± 2.1%, 0.977 ± 0.010 vs. 0.988 ± 0.005 with AI information, respectively).</p><p><strong>Conclusion: </strong>AI-VISIBLE improved the sensitivity and performance for diagnosing brain metastases.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":"351-359"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11893687/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142018183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Retinoblastoma and beyond: pediatric orbital mass lesions.","authors":"Zoran Rumboldt, Doris Dodig, Paolo Galluzzi, Ivan Brumini, Rebekah Clarke, Sumit Singh, Andrea Rossi","doi":"10.1007/s00234-024-03517-6","DOIUrl":"10.1007/s00234-024-03517-6","url":null,"abstract":"<p><p>Various space occupying lesions can arise in the orbit, ranging from developmental anomalies to malignancies, and many of the diseases occurring in children are different from the pathologies in the adult population. As the clinical presentation is frequently nonspecific, radiologic evaluation is essential for lesion detection and characterization as well as patient management. While orbital masses may in some cases involve multiple compartments, a simple compartmental approach is the key for the diagnosis on imaging studies, and MRI is the modality of choice. This pictorial review presents the most common and characteristic non-emergent pediatric orbital lesions, stressing their MRI and CT appearances, including specific differentiating features. The lesions are subdivided into 4 compartments: intraocular, intraconal, extraconal, and orbital walls. Retinoblastoma, Coats disease and persistent fetal vasculature; optic pathway glioma and lymphovascular malformations; rhabdomyosarcoma, infantile hemangioma, neurofibroma and lymphoma; neuroblastoma, leukemia/myeloid sarcoma, Langerhans cell histiocytosis and dermoid are reviewed in their respective compartments.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":"469-492"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11893699/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142896490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"European Society of Neuroradiology (ESNR).","authors":"","doi":"10.1007/s00234-025-03559-4","DOIUrl":"10.1007/s00234-025-03559-4","url":null,"abstract":"","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":"507-508"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143382908","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":"High-resolution vessel wall MRI in Moyamoya disease: a systematic review and meta-analysis of diagnostic and prognostic applications.","authors":"Maryam Shahabi, Negar Zareshahi, Iman Kiani, Mahdi Gouravani, Alireza Beikmarzehei, Yalda Farahmand, Ehsan Ranjbar, Armin Tafazolimoghadam, Mohammadamin Parsaei, Hossein Sanjari Moghaddam, Alejandro M Spiotta","doi":"10.1007/s00234-024-03515-8","DOIUrl":"10.1007/s00234-024-03515-8","url":null,"abstract":"<p><strong>Purpose: </strong>Moyamoya disease (MMD) is a rare cerebrovascular disorder characterized by the narrowing of arteries at the brain's base. While cerebral angiography is the gold standard for diagnosis, high-resolution vessel wall magnetic resonance imaging (VW-MRI) has recently emerged as a non-invasive diagnostic tool. This systematic review aims to provide insights into the role of VW-MRI in enhancing the diagnosis and management of MMD.</p><p><strong>Method: </strong>A systematic search was conducted in PubMed, Embase, Scopus, and Web of Science for relevant articles on December 5, 2023. Demographic data, the outer diameter of the vessel, vessel wall contrast enhancement (VW-CE) and its pattern, vessel wall thickening and its pattern, remodeling index, and vessel area were extracted. In the analysis proportions were pooled using a random-effects model with logit transformation where applicable. Quality assessment was conducted using the Newcastle-Ottawa scale.</p><p><strong>Result: </strong>Of the 6035 identified studies in the primary search, 19 met the inclusion criteria. Among the reviewed studies, the most commonly reported variations in patients with MMD using VW-MRI was VW-CE (84.21%) and its pattern (52.63%). The pooled prevalence of enhanced lesions in MMD was 0.55 (95% CI: 0.29-0.79), with ratio of concentric lesions being 0.98 (95% CI: 0.72-1.00, I²: 37%). The remodeling index across three studies showed a pooled estimate of 0.41 (95% CI: 0.11-0.72, I²: 99%).</p><p><strong>Discussion: </strong>VW-MRI emerges as a promising non-invasive tool for enhancing diagnosis of MMD, potentially aiding in disease differentiation and predicting complications. However, standardization and further research are essential to solidify VW-MRI's role.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":"299-319"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142896488","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":"Obstructive hydrocephalus due to developmental venous anomalies: a pediatric imaging case series.","authors":"Livja Mertiri, Vikramjeet Singh, Francesca Gentile, Huy Brandon D Tran, Andrea Rossi, Thierry A G M Huisman","doi":"10.1007/s00234-024-03484-y","DOIUrl":"10.1007/s00234-024-03484-y","url":null,"abstract":"<p><strong>Purpose: </strong>Developmental venous anomalies are a rare cause of obstructive hydrocephalus in the pediatric population. In this study, we present the most extensive case series of DVA-induced obstructive hydrocephalus in the pediatric population. We thoroughly describe the imaging findings related to this uncommon entity and comprehensively discuss its clinical presentation and management strategies. The goal is to alert pediatric neuroradiologists to consider this rare condition in the differential diagnosis of hydrocephalus, particularly during prenatal screening or in pediatric cases.</p><p><strong>Methods: </strong>The electronic patient record systems of 2 tertiary care children's hospitals were reviewed to identify pediatric patients with confirmed DVAs leading to obstructive hydrocephalus. Age at diagnosis, gender, MRI findings (including location of the obstruction), clinical presentation, and symptoms were recorded. Data on treatment and follow-up imaging were also collected.</p><p><strong>Results: </strong>The search yielded 5 cases of pediatric patients with DVA-induced obstructive hydrocephalus. The mean age at diagnosis of the DVA was 2.9 years (range: 0-7 years), and in two cases, ventriculomegaly was diagnosed in utero during prenatal cranial ultrasound screenings. In all patients, the DVA caused stenosis of the aqueduct of Sylvius, and one case presented with multiple DVAs.</p><p><strong>Conclusions: </strong>Although aqueductal stenosis caused by a DVA is rare, it is crucial to consider it in the differential diagnosis of hydrocephalus during prenatal screening or in the pediatric population. Brain MRI, especially post-contrast T1WI, and SWI sequences are particularly valuable for visualizing the typical \"caput medusae\" appearance of DVAs and detecting associated complications such as hemorrhages.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":"493-497"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142522571","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":"Dual-energy CT angiography in detecting underlying causes of intracerebral hemorrhage: an observational cohort study.","authors":"Michaël T J Peeters, Alida A Postma, Robert J van Oostenbrugge, Wouter J P Henneman, Julie Staals","doi":"10.1007/s00234-024-03473-1","DOIUrl":"10.1007/s00234-024-03473-1","url":null,"abstract":"<p><strong>Background: </strong>CT angiography (CTA) is often used to detect underlying causes of acute intracerebral hemorrhage (ICH). Dual-energy CT (DECT) is able to distinguish materials with similar attenuation but different compositions, such as hemorrhage and contrast. We aimed to evaluate the diagnostic yield of DECT angiography (DECTA), compared to conventional CTA in detecting underlying ICH causes.</p><p><strong>Methods: </strong>All non-traumatic ICH patients who underwent DECTA (both arterial as well as delayed venous phase) at our center between January 2014 and February 2020 were analyzed. Conventional CTA acquisitions were reconstructed ('merged') from DECTA data. Structural ICH causes were assessed on both reconstructed conventional CTA and DECTA. The final diagnosis was based on all available diagnostic and clinical findings during one-year follow up.</p><p><strong>Results: </strong>Of 206 included ICH patients, 30 (14.6%) had an underlying cause as final diagnosis. Conventional CTA showed a cause in 24 patients (11.7%), DECTA in 32 (15.5%). Both false positive and false negative findings occurred more frequently on conventional CTA. DECTA detected neoplastic ICH in all seven patients with a definite neoplastic ICH diagnosis, whereas conventional CTA only detected four of these cases. Both developmental venous anomalies (DVA) and cerebral venous sinus thrombosis (CVST) were more frequently seen on DECTA. Arteriovenous malformations and aneurysms were detected equally on both imaging modalities.</p><p><strong>Conclusions: </strong>Performing DECTA at clinical presentation of ICH may be of additional diagnostic value in the early detection of underlying causes, especially neoplasms, CVST and DVAs.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":"331-338"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11893716/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142505046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Synthetic MR: Clinical applications in neuroradiology.","authors":"Smily Sharma, Abhishek Nayak, Bejoy Thomas, Chandrasekharan Kesavadas","doi":"10.1007/s00234-025-03547-8","DOIUrl":"https://doi.org/10.1007/s00234-025-03547-8","url":null,"abstract":"<p><strong>Purpose: </strong>Synthetic MR is a quantitative MRI method that measures tissue relaxation times and generates multiple contrast-weighted images using suitable algorithms. The present article principally discusses the multiple dynamic multiple echo (MDME) technique of synthetic MR and briefly describes other quantitative MR sequences.</p><p><strong>Methods: </strong>Using illustrative cases, various applications of the MDME sequence in neuroradiology are explained. The MDME sequence allows rapid quantification of tissue relaxation times in a scan duration of 5-7 minutes for full brain coverage. It also has the additional advantages of myelin quantification and automatic segmentation of brain volumes.</p><p><strong>Results: </strong>Applications including reducing scan time, improved detection of demyelinating plaques in Multiple Sclerosis (MS), objective assessment and follow-up for brain atrophy in neurodegenerative MS and dementia cases, and applications in stroke imaging and neuro-oncology are discussed. Uses in the pediatric population, including assessment of brain development and progression of myelination in children, evaluation of white matter disorders, and evaluation of pediatric and adult epilepsy, are elaborated. Quantitative evaluation by synthetic MR is discussed, which allows homogenization and objectification of the radiology data and can serve as a valuable source for artificial intelligence and future multicentre studies. A brief discussion on the technique, other quantitative MR methods, and limitations of the MDME sequence is also presented.</p><p><strong>Conclusion: </strong>The article intends to provide an explicit and comprehensive review of the applications of synthetic MR in neuroradiology, exploring its potential as a routine sequence in daily neuroimaging practice.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143067014","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":"Perivascular and parenchymal brain fluid diffusivity in patients with a recent small subcortical infarct.","authors":"Salvatore Rudilosso, Emma Muñoz-Moreno, Carlos Laredo, Angels Calvet, Alejandro Rodríguez-Vázquez, Andres Girona, Maria Dels Angels Calderon, Federico Zarco, Francisco Gil-López, Adrià Arboix, Maria Valdes Hernandez, Roberto Duarte Coello, Xabier Urra, Joanna M Wardlaw, Ángel Chamorro","doi":"10.1007/s00234-025-03546-9","DOIUrl":"https://doi.org/10.1007/s00234-025-03546-9","url":null,"abstract":"<p><strong>Purpose: </strong>Fluid exchanges between perivascular spaces (PVS) and interstitium may contribute to the pathophysiology of small vessel disease (SVD). We aimed to analyze water diffusivity measures and their relationship with PVS and other SVD imaging markers.</p><p><strong>Methods: </strong>We enrolled 50 consecutive patients with a recent small subcortical infarct. We collected clinical variables, including vascular risk factors and sleep quality scales. All patients underwent a 3-Tesla MRI with standard structural sequences and multishell-diffusion images to obtain extracellular free water content (FW) and water diffusivity along the perivascular space (ALPS) index. We obtained volumetric measurements of white matter hyperintensities (WMH) and PVS, and the number of lacunes and microbleeds. To analyze the association between PVS, ALPS index, FW, and SVD imaging features, we utilized linear regression models including age, sex, history of hypertension and diabetes, Pittsburgh Sleep Quality Index, WMH, and brain volume.</p><p><strong>Results: </strong>All patients (mean age 70 years, 36% women) had usable data. FW and PVS were strongly associated in all models (0.008 < Beta < 0.054; P < 0.045). Higher FW was related to the other SVD features in univariable models and remained significant for WMH (1.175 < Beta < 1.262; P < 0.001) and brain volume (Beta < 0.0001; P < 0.002) in multivariable models. ALPS index was not associated with FW, PVS, or any other SVD markers.</p><p><strong>Conclusions: </strong>The increased extracellular water in SVD suggests that impaired brain fluid exchanges, PVS dilation, and other SVD features are linked. Further investigation is needed to determine the specificity of the ALPS index to PVS diffusion.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143033752","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":"Detecting B-cell lymphoma-6 overexpression status in primary central nervous system lymphoma using multiparametric MRI-based machine learning.","authors":"Mingxiao Wang, Guoli Liu, Nan Zhang, Yanhua Li, Shuo Sun, Yahong Tan, Lin Ma","doi":"10.1007/s00234-025-03551-y","DOIUrl":"https://doi.org/10.1007/s00234-025-03551-y","url":null,"abstract":"<p><strong>Purpose: </strong>In primary central nervous system lymphoma (PCNSL), B-cell lymphoma-6 (BCL-6) is an unfavorable prognostic biomarker. We aim to non-invasively detect BCL-6 overexpression in PCNSL patients using multiparametric MRI and machine learning techniques.</p><p><strong>Methods: </strong>65 patients (101 lesions) with primary central nervous system lymphoma (PCNSL) diagnosed from January 2013 to July 2023, and all patients were randomly divided into a training set and a validation set according to a ratio of 8 to 2. ADC map derived from DWI (b = 0/1000 s/mm2), fast spin echo T2WI, T2FLAIR, were collected at 3.0 T. A total of 2234 radiomics features from the tumor segmentation area were extracted and LASSO were used to select features. Logistic regression (LR), Naive bayes (NB), Support vector machine (SVM), K-nearest Neighbor, (KNN) and Multilayer Perceptron (MLP), were used for machine learning, and sensitivity, specificity, accuracy F1-score, and area under the curve (AUC) was used to evaluate the detection performance of five classifiers, 6 groups with combinations of different sequences were fitted to 5 classifiers, and optimal classifier was obtained.</p><p><strong>Results: </strong>BCL-6 status could be identified to varying degrees with 30 models based on radiomics, and model performance could be improved by combining different sequences and classifiers. Support vector machine (SVM) combined with three sequence group had the largest AUC (0.95) in training set and satisfactory AUC (0.87) in validation set.</p><p><strong>Conclusion: </strong>Multiparametric MRI based machine learning is promising in detecting BCL-6 overexpression.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.4,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143033751","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}