BMC Medical Imaging最新文献

{"title":"Quantitative ultrasound evaluation of medial compartment knee osteoarthritis under standing weight-bearing condition.","authors":"Qilong Jiang, Yajun Li, Yan Xiao, Na Wang, Junming Lin, Chang Liu, Mingbo Wu, Yusong Liu, Mao Nie, Xianding Sun","doi":"10.1186/s12880-026-02638-z","DOIUrl":"10.1186/s12880-026-02638-z","url":null,"abstract":"<p><strong>Purpose: </strong>To evaluate the diagnostic value of ultrasound for joint space width in knee osteoarthritis under standing weight-bearing conditions and identify reliable sonographic parameters for osteoarthritis severity grading, especially end-stage knee osteoarthritis.</p><p><strong>Methods: </strong>This cross-sectional study enrolled 256 patients with knee pain and suspected knee osteoarthritis from June to December 2025. All participants underwent standing weight-bearing radiography and ultrasound of the affected knee at 20° and 45° flexion. Radiographic assessments (Kellgren-Lawrence grading, joint space width, minimal joint space width) were performed by two senior orthopedists, while ultrasound evaluations (joint space width, total femoral and tibial osteophyte height, medial meniscal extrusion) were conducted by another two experienced orthopedists blinded to radiographic findings. Interrater reliability was analyzed using the weighted kappa coefficient and intraclass correlation coefficient. The Pearson product-moment correlation coefficient quantified the correlation between sonographic and radiographic measurements, and receiver operating characteristic curve analysis determined the diagnostic efficacy of ultrasound parameters for Kellgren-Lawrence grading.</p><p><strong>Results: </strong>Participants had a mean age of 55.9 ± 11.7 years, mean body mass index of 25.22 ± 4.32 kg/m², and 81.6% were female. Interrater reliability for all measurements was moderate to excellent (intraclass correlation coefficient/weighted kappa: 0.54-0.92). With increasing Kellgren-Lawrence grades, radiographic and ultrasound joint space width decreased, while total femoral and tibial osteophyte height and medial meniscal extrusion increased. A total of 29 patients (11.3%) were reclassified to higher Kellgren-Lawrence grades at 45° versus 20° flexion. High correlations were observed between radiographic and sonographic measurements. For differentiating Kellgren-Lawrence Grade 3 from 4, ultrasound joint space width at 45° flexion had a higher area under the curve (0.839, 95% confidence interval: 0.766-0.912; cutoff: 1.75 mm) than at 20° (0.825, 95% confidence interval: 0.745-0.905; cutoff: 1.95 mm).</p><p><strong>Conclusions: </strong>Sonographic joint space width measured at 20° and 45° knee flexion under standing weight-bearing conditions yielded AUC values similar to those obtained from weight-bearing radiographs for diagnosing medial compartment KOA. Ultrasound may act as a potential supplementary imaging alternative to conventional standing radiograph for grading the severity of medial compartment KOA.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"26 1","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13715282/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149285007","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":"Diagnostic accuracy, time window estimation, and prognostic value of diffusion-weighted MRI in acute ischemic stroke: a systematic review and meta-analysis.","authors":"Yueqin Wang, LuXin Guo","doi":"10.1186/s12880-026-02592-w","DOIUrl":"10.1186/s12880-026-02592-w","url":null,"abstract":"<p><strong>Background: </strong>Diffusion-weighted imaging (DWI) is central to acute ischemic stroke (AIS) management; however, its performance varies across different clinical applications. This systematic review and meta-analysis comprehensively evaluated the diagnostic accuracy, time window estimation capability, and prognostic value of DWI in AIS.</p><p><strong>Methods: </strong>This registered systematic review searched three major databases for DWI studies in adult AIS patients published from 2010 to 2025. Risk of bias was assessed using QUADAS-2. The meta-analysis was performed in three distinct phases: (1) diagnostic accuracy, (2) time window estimation, and (3) prognostic value using a bivariate random-effects model. Extensive subgroup analyses were conducted to investigate sources of heterogeneity, including AI assistance, MRI field strength, study design, onset-to-DWI time, sequence type, lesion location, and stroke severity.</p><p><strong>Results: </strong>Of 34 eligible studies, 22 independent studies with 30 datasets were included in the meta-analysis across three phases. DWI demonstrated excellent diagnostic accuracy with a pooled sensitivity of 0.912 (95% CI: 0.888-0.932) and specificity of 0.959 (95% CI: 0.940-0.970). For time window estimation, DWI showed moderate performance with a pooled sensitivity of 0.786 (95% CI: 0.688-0.860) and specificity of 0.727 (95% CI: 0.668-0.780), with substantial heterogeneity and markedly lower accuracy in posterior circulation strokes. DWI-derived biomarkers demonstrated good prognostic value for predicting functional outcomes with a pooled sensitivity of 0.702 (95% CI: 0.540-0.825) and specificity of 0.904 (95% CI: 0.821-0.951).</p><p><strong>Conclusion: </strong>DWI offers excellent diagnostic accuracy for AIS (sensitivity: 0.912, specificity: 0.959) but only modest performance for time estimation (sensitivity: 0.786, specificity: 0.727). DWI-derived biomarkers show good prognostic value (sensitivity: 0.702, specificity: 0.904), while AI and ultra-fast MRI protocols demonstrate promise for improving clinical utility.</p><p><strong>Study design: </strong>Registered systematic review and meta-analysis following PRISMA guidelines PROSPERO REGISTRATION: 2026 CRD420261376477.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"26 1","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13711878/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149262396","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":"Myocardial injury patterns on cardiac magnetic resonance: diffuse myocardial damage with prominent septal involvement in adults with severe myocarditis requiring extracorporeal membrane oxygenation.","authors":"Zhongman Zhang, Xiaole Zhu, Yi Zhu, Tianshi Li, Wei Li, Xiaomei Zhu, Xufeng Chen, Sae Rom Lee","doi":"10.1186/s12880-026-02614-7","DOIUrl":"10.1186/s12880-026-02614-7","url":null,"abstract":"<p><strong>Purpose: </strong>Patients with myocarditis suffering from cardiogenic shock may benefit from extracorporeal membrane oxygenation (ECMO). However, the characteristics of myocardial injury in these patients are unclear. Using cardiac magnetic resonance (CMR), we aimed to investigate cardiac changes in survivors with severe myocarditis treated with ECMO.</p><p><strong>Methods: </strong>This retrospective study was conducted at the First Affiliated Hospital with Nanjing Medical University in Nanjing, China, from July 2018 to July 2022. Patients with severe myocarditis who underwent CMR within 30 days after discontinuing ECMO were included in this study.</p><p><strong>Results: </strong>In total, 22 patients (median age: 33 years) were included. Late gadolinium enhancement (LGE) was detected within the interventricular septum (IVS) in all patients. The mean T1, T2, and extracellular volume (ECV) values showed similar distribution patterns to LGE. In an exploratory post-hoc age stratification based on the cohort median age of 33 years, we observed that several quantitative CMR parameters (mean ECV, minimum ECV, maximum ECV, mean T1, maximum T1, and minimum T2) were numerically higher in the older subgroup (p < 0.05). Myocardial injury was widespread in patients with severe myocarditis receiving ECMO.</p><p><strong>Conclusions: </strong>Survivors of severe myocarditis who required ECMO support presented diffuse myocardial injury as the dominant pattern on early post-weaning CMR examination, with the interventricular septum showing notably prominent lesions among all myocardial segments.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"26 1","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13711805/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149262421","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":"Performance of GPT-4o in CT-based crista galli morphological classification: image-only versus morphometric dataset-driven approaches: a controlled comparative study.","authors":"Erdal Komut, Serkan Günay, Ahmet Öztürk, Gurbet Yanarateş, Onur Karacif, Seval Komut","doi":"10.1186/s12880-026-02618-3","DOIUrl":"10.1186/s12880-026-02618-3","url":null,"abstract":"<p><strong>Background: </strong>The aim of this study was to examine whether ChatGPT's performance in a morphological classification task based solely on a single CT slice and without access to any additional health record information varies depending on the inclusion of metric datasets.</p><p><strong>Methods: </strong>This study is based on a CT-based classification system in which categorized the crista galli morphometrically and morphologically. Paranasal CT (PNCT) images of 101 randomly selected patients who underwent PNCT were retrieved from the hospital's database. The PNCT slices used by the radiologists for classification were uploaded individually to GPT-4o in a randomized patient order, and it was asked to perform morphological classification based solely on the CT images. The accuracy of the morphological classifications performed by GPT-4o based on the morphometric data and PNCT slices was statistically compared to the radiologists' gold standard classifications.</p><p><strong>Results: </strong>GPT-4o correctly classified CG types in 27.72% of cases using PNCT slices, whereas its classification accuracy reached 100% when using the morphometric dataset. The accuracy of GPT-4o's classification based on PNCT slices was significantly lower compared to its performance with morphometric data (p < 0.001). When examining the classification accuracy of GPT-4o based on PNCT slices by CG type, the highest accuracy was observed for the ossified type at 60%, while the lowest was for the tubular type at 6.06%.</p><p><strong>Conclusions: </strong>Although ChatGPT has demonstrated promising performance in diagnostic radiology when provided with textual or numerical datasets, in this controlled CT-based crista galli morphologic classification task, GPT-4o demonstrated substantially lower performance when relying solely on image input compared with structured morphometric data. These findings suggest that the performance of multimodal LLMs may strongly depend on structured information. Further studies involving broader diagnostic settings are required before conclusions regarding clinical applicability can be drawn.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"26 1","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13711699/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149262384","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":"Radioanatomical analysis for precise harvesting of the pedicled nasoseptal flap in anterior skull base reconstruction during craniofacial surgery.","authors":"Dongsheng Gu","doi":"10.1186/s12880-026-02606-7","DOIUrl":"10.1186/s12880-026-02606-7","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate the role of the vascularized nasoseptal flap (VNSF) and septal flip flap (SFF) in anterior skull base (ASB) reconstruction of craniofacial therapy by studying the radioanatomy of VNSF, SFF and ASB reconstruction data on adult Computed Tomography (CT) multiplanar reconstruction.</p><p><strong>Methods: </strong>The length, width and area of VNSF, SFF, and ASB defects were measured by Computed Tomography CT in 40 adults, and then the above date were statistically analyzed to confirm whether VNSF and SFF can be used to cover the ASB defect region produced after surgery.</p><p><strong>Results: </strong>The area of VNSF far exceeded that of ASB defect (10.21 ± 1.97 cm²), and the anterior and posterior widths, as well as the upper and lower lengths of VNSF were at least 8.4 mm longer than the corresponding width and length of ASB defect to be reconstructed. The VNSF containing vascular pedicle had a total length exceed that required for ASB reconstruction via the anterior wall of the sphenoid sinus (SS) by at least 17.6 mm, but a mean length that was 7.02 ± 8.71 mm less than that required for transsphenoidal reconstruction of ASB. The area of SFF far exceeded that of the ASB defect (8.93 ± 1.49 cm²). The anterior and posterior widths, as well as the lower length of SFF all exceeded the corresponding width and length of the ASB defect to be reconstructed by at least 8.4 mm, and the upper length exceeded the ASB defect length by at least 1.5 mm. The independent sample t test showed no difference between sexes. Pearson correlation analysis showed no age difference except for the difference between SFF anterior width and ASB anterior width (P = 0.016). VNSF can reconstruct the defect of ASB through the anterior wall of the SS.</p><p><strong>Conclusion: </strong>With the assistance of SS packing and other methods, VNSF can transsphenoidally reconstruct the defect of the ASB, and SFF can reconstruct the defect of the ASB.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"26 1","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13676795/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149215044","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":"DSA radiomics and clinical features for hemorrhagic risk assessment in bAVM embolization.","authors":"Ni Zeng, Caihong Li, Jianbin Zhu, Qiuxian Wang, Zhibo Wen","doi":"10.1186/s12880-026-02587-7","DOIUrl":"10.1186/s12880-026-02587-7","url":null,"abstract":"<p><strong>Background: </strong>Hemorrhagic complications (HCs) remain a major cause of morbidity in endovascular treatment (EVT) for brain arteriovenous malformation (bAVM), while reliable EVT-specific risk assessment remains challenging. This study aimed to develop and internally evaluate an exploratory model integrating digital subtraction angiography (DSA) radiomics and clinical features to assess the risk of EVT-related HCs.</p><p><strong>Methods: </strong>This retrospective study included 620 consecutive bAVM patients who underwent first-time EVT between 2011 and 2024. Radiomics features were extracted from anteroposterior and lateral DSA images of the nidus. Clinical-only, radiomics-only, and combined models were developed using four algorithms with stratified five-fold cross-validation on the training set and evaluated on the test set. Model interpretability was performed using SHapley Additive exPlanations (SHAP).</p><p><strong>Results: </strong>HCs occurred in 100 patients (16.1%). On the test set, the XGBoost-based fusion model achieved the best overall performance (AUC 0.81), showing a modest improvement over the radiomics-only XGBoost model while outperforming all clinical-only models. Radiomics features contributed substantially to model performance, with clinical variables providing complementary information.</p><p><strong>Conclusions: </strong>A model integrating DSA radiomics and clinical features provides an exploratory approach to assessing the risk of EVT-related HCs in patients with bAVM. These findings suggest the potential value of DSA-derived radiomics for individualized peri-procedural risk assessment, although external validation is required before clinical application.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"26 1","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13712068/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149262441","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":"Whole-phase DCE-MRI radiomics for differentiating benign and malignant BI-RADS 4 breast lesions: a comparative machine learning study.","authors":"Yantao Yang, Xuewei Ding, Ruixuan Wang, Shiwei Wang, Mengxin Liu, Huan Lu","doi":"10.1186/s12880-026-02609-4","DOIUrl":"10.1186/s12880-026-02609-4","url":null,"abstract":"<p><strong>Background: </strong>Breast Imaging Reporting and Data System (BI-RADS) category 4 breast lesions have a wide probability of malignancy, with substantial overlap in imaging findings between benign and malignant lesions. Whole-phase dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics may provide information on tumor enhancement and heterogeneity. This study primarily aimed to evaluate whole-phase DCE-MRI radiomics for differentiating benign from malignant BI-RADS 4 breast lesions and secondarily explored its feasibility for HER-2 status prediction in malignant lesions.</p><p><strong>Methods: </strong>This retrospective study included 484 women with BI-RADS 4 breast lesions who underwent DCE-MRI at the First Affiliated Hospital of Zhejiang Chinese Medical University between January 2022 and October 2024, including 264 benign and 220 malignant lesions. Among the malignant lesions, 52 were HER-2 positive and 168 were HER-2 negative. Patients were randomly divided into training and internal test sets at a ratio of 7:3. Whole-phase DCE-MRI radiomics features were extracted. Eight machine-learning algorithms were used to build radiomics models, clinical models, and combined models. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score. Decision curve analysis (DCA) was performed as an exploratory assessment of potential net benefit.</p><p><strong>Results: </strong>For differentiating benign from malignant BI-RADS 4 lesions, the support vector machine (SVM) radiomics model achieved the best radiomics performance, with a test-set AUC of 0.893. The combined model further improved the AUC to 0.913. In the secondary exploratory HER-2 analysis, the random forest (RF) radiomics model yielded a test-set AUC of 0.879, whereas the combined model showed a lower AUC of 0.830. Owing to the limited number of HER-2-positive cases and the internal validation design, these HER-2 findings should be interpreted as preliminary and hypothesis-generating.</p><p><strong>Conclusions: </strong>Whole-phase DCE-MRI radiomics showed favorable internal performance for differentiating benign from malignant BI-RADS 4 breast lesions. The SVM-based combined model performed favorably for the primary malignancy task, whereas the HER-2 analysis should be regarded only as a secondary exploratory observation requiring further validation.</p><p><strong>Trial registration: </strong>Not applicable. This was a retrospective single-center imaging study and did not prospectively assign participants to any intervention.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"26 1","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13715199/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149285146","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":"Machine learning-based radiomic analysis of T2-FLAIR white matter hyperintensity predicts hemorrhagic transformation after endovascular thrombectomy for acute ischemic stroke.","authors":"Qi Wu, Yandan Shi, Zhihao Zhang, Jupeng Zhang, Jiayu Wu, Ziyuan Yang, Yuyao He, Jinqin Su, Xiyuan Wang, Changhui Huang, Xiqi Zhu","doi":"10.1186/s12880-026-02599-3","DOIUrl":"10.1186/s12880-026-02599-3","url":null,"abstract":"<p><strong>Objective: </strong>Hemorrhagic transformation (HT) remains a major complication after endovascular therapy (EVT) in patients with acute ischemic stroke (AIS). This study aimed to develop and validate a machine-learning model based on T2-FLAIR white matter hyperintensity (WMH) radiomics combined with clinical variables to predict HT after EVT.</p><p><strong>Methods: </strong>In this dual-center retrospective study, 446 patients (mean age 61.88 ± 10.98 years; 332 [74.4%] male) with AIS who underwent EVT were enrolled from two centers. Patients from the primary center were randomly assigned to a training cohort and an internal test cohort, and patients from the second center served as an independent external validation cohort. Clinical risk factors were identified by univariate and multivariate logistic regression. Preoperative T2-FLAIR images were used to segment WMH lesions and extract radiomics features. After feature selection, three predictive models were then developed: a clinical model based on the independent clinical predictors, a radiomics model based on the radiomics signature, and a combined model integrating both. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration analysis, DeLong testing, and decision curve analysis.</p><p><strong>Results: </strong>Among the 446 patients, 153 (34.3%) developed HT within 24-48 h after EVT. Multivariate analysis identified NIHSS score, occlusion site, and atrial fibrillation as independent clinical predictors of HT. In the internal test cohort, the combined model achieved the best discriminative performance (AUC = 0.818, 95% CI: 0.651-0.986), outperforming the clinical model (AUC = 0.740, 95% CI: 0.562-0.917) and the radiomics model (AUC = 0.806, 95% CI: 0.621-0.990). In the external validation cohort, the combined model maintained robust performance (AUC = 0.817, 95% CI: 0.746-0.889), which was comparable to the clinical model (AUC = 0.818, 95% CI: 0.742-0.894) and higher than the radiomics model alone (AUC = 0.764, 95% CI: 0.682-0.845).</p><p><strong>Conclusions: </strong>A combined model incorporating T2-FLAIR WMH radiomics and key clinical variables provides a feasible tool for individualized prediction of HT after EVT in patients with AIS, although its incremental discriminatory value over the clinical model alone was limited in the external validation cohort. This approach may help improve perioperative risk stratification and support personalized clinical decision-making.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"26 1","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13700525/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149262382","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":"Preoperative tumor cerebral blood flow measured by arterial spin labeling predicts enhancing tumor volume progression in gliomas: a single-center retrospective study.","authors":"Thomas Lindner, Jens Fiehler","doi":"10.1186/s12880-026-02612-9","DOIUrl":"10.1186/s12880-026-02612-9","url":null,"abstract":"<p><strong>Background: </strong>Arterial spin labeling (ASL) enables non-invasive quantification of cerebral blood flow (CBF). The preoperative prognostic value of tumor-specific CBF for subsequent enhancing tumor (ET) volume progression in gliomas remains poorly characterized.</p><p><strong>Methods: </strong>In this study 60 glioma patients (predominantly glioblastoma, WHO grade 4) with preoperative 3T ASL MRI and paired follow-up structural MRI were analyzed. Tumor CBF, surrounding CBF, and whole-brain CBF were quantified from the segmented regions of interest. ET and surrounding non-enhancing FLAIR-hyperintense (SNFH) volume changes were calculated and correlated with preoperative perfusion data. Spearman correlations, Kruskal-Wallis tests, multivariable linear and logistic regression, and ROC analyses were performed.</p><p><strong>Results: </strong>Higher preoperative tumor CBF strongly predicted net ET volume increase (Spearman r = 0.531, p < 0.0001) and ET progression category (Kruskal-Wallis p = 0.0005). Mean tumor CBF was 147.7 ml/100 g/min in ET-increased versus 124.4 ml/100 g/min in unchanged and 115.8 ml/100 g/min in decreased cases. Tumor CBF remained an independent predictor after adjusting for age, scan interval, and MGMT status (linear regression p = 0.002; logistic regression OR = 2.02 per ml/100 g/min, p = 0.001). Associations with SNFH volume changes were weak and non-significant. Surrounding CBF closely matched whole-brain CBF (Pearson r ≈ 1.00). Tumor CBF alone yielded 5-fold CV AUC = 0.805 for predicting ET progression; the combined model (tumor CBF + ET volume) improved to AUC = 0.858.</p><p><strong>Conclusion: </strong>Preoperative ASL-derived tumor CBF appears to be an independent non-contrast imaging biomarker for early enhancing tumor progression risk in gliomas.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"26 1","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13421742/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148618008","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":"Medical Segment Anything Model (MedSAM): methodological innovations, evaluation practices, and clinical applications.","authors":"Wenjie Zhang, Liming Luo, Mengnan He, Molly Beestrum, Jiancheng Ye","doi":"10.1186/s12880-026-02600-z","DOIUrl":"10.1186/s12880-026-02600-z","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;The Medical Segment Anything Model (MedSAM) has emerged as a prominent foundation model for medical image segmentation, prompting rapid growth in related research. Despite this proliferation, the literature remains fragmented across multimodal paradigms and lacks rigorous synthesis of methodological innovations, clinical safety evidence, algorithmic bias, and real-world implementation barriers-gaps that limit the field's ability to translate algorithmic progress into clinical impact.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;To systematically identify, classify, and synthesize published research on MedSAM and its derivatives, providing a comprehensive overview of methodological developments, evaluation findings, and clinical translation progress.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This scoping review followed the PRISMA-ScR guideline. We conducted a systematic search across six major databases (PubMed, Embase, Web of Science, Scopus, IEEE Xplore, ACM Digital Library) through June 2025.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;From 1,482 initial records, 45 studies met inclusion criteria. Innovation-oriented studies (n = 32) were classified along four methodological axes spanning multimodal paradigms: Architecture Enhancement (encoder/decoder refinements for efficiency and precision), Prompt Strategy (textual, spatial, and multimodal prompting mechanisms), Efficiency and Deployability (quantization, distillation, and system integration), and Pipeline and Application (integration into clinical workflows). Evaluation-oriented studies (n = 13) revealed that MedSAM outperforms general-purpose SAM by 5-20% on structured modalities (CT/MRI) but lags behind task-specific networks for delicate structures. Notably, fairness analyses from two studies (combined n = 1,757 subjects) report Dice disparities of up to 10% across sex, age, and BMI strata, raising concerns about potential demographic bias that warrants further investigation in larger, multi-center cohorts before firm clinical-safety conclusions can be drawn. Real-world deployment is further constrained by prompt sensitivity (5-15% Dice variation), cross-modality domain shift, regulatory compliance gaps (FDA/CE marking, HIPAA, GDPR), and absent multi-center prospective validation, all of which represent principal implementation hurdles for clinical adoption.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;MedSAM represents a significant advancement in medical image segmentation, demonstrating a clear trajectory from large-scale architectures toward lightweight, prompt-aware, and deployable models. This synthesis provides a structured critical appraisal indicating that the evidence base remains at the proof-of-concept stage, with most studies retrospective and single-center, and emerging signals of algorithmic bias, unresolved cross-modality failure modes, and incomplete regulatory pathways represent safety and implementation considerations that should be addressed before multimodal MedSAM-based syst","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"26 1","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13700131/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149262414","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}