BMC Medical Imaging最新文献

{"title":"Development and validation of a nomogram for diabetic tibial neuropathy based on ultrasound radiomics: a multicenter study.","authors":"Yanqiu Chen, Zhen Sun, Yuwei Chen, Huohu Zhong, Xiuming Wu, Liyang Su, Tao Zheng, Guorong Lyu, Qichen Su","doi":"10.1186/s12880-025-01896-7","DOIUrl":"https://doi.org/10.1186/s12880-025-01896-7","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"355"},"PeriodicalIF":3.2,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12382110/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144941629","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":"The effect of lesion filling on brain age estimation in multiple sclerosis.","authors":"Salem Hannoun, Grace Fayad, Nabil K El Ayoubi, Samia J Khoury","doi":"10.1186/s12880-025-01897-6","DOIUrl":"https://doi.org/10.1186/s12880-025-01897-6","url":null,"abstract":"<p><strong>Background: </strong>Brain age estimation is an emerging biomarker for assessing neurodegeneration in multiple sclerosis (MS). However, MS-related lesions can distort structural measurements, potentially leading to inaccuracies in age prediction models. Lesion filling has been proposed as a corrective step, but its impact on brain age estimation and its associations with clinical and structural markers remains unclear.</p><p><strong>Methods: </strong>We analyzed 571 relapsing-remitting MS patients using the BrainAgeR pipeline to estimate brain age from both non-lesion-filled and lesion-filled T1-weighted images. Bias correction was applied to remove age-related prediction bias. Brain Age Gap (BAG) was computed as the difference between corrected predicted brain age and chronological age. Multivariable linear regression models were used to assess associations between BAG and clinical outcomes (EDSS, 9HPT, SDMT, 25FWT) and volumetric measures.</p><p><strong>Results: </strong>Non-lesion-filled and lesion-filled brain age estimates showed excellent agreement (r = 0.97; ICC = 0.962), with a mean difference of 1.23 years and slightly lower mean absolute error for lesion-filled predictions (8.12 vs. 9.40 years). Both BAG measures were significantly associated with EDSS, 9HPT, and SDMT, though effect sizes were modest. Lesion-filled BAG showed stronger and more consistent associations with gray matter, thalamic, and hippocampal volumes, and these associations remained significant after Bonferroni correction.</p><p><strong>Conclusion: </strong>Lesion filling modestly improves structural interpretability of brain age estimates in MS but has limited effect on clinical correlations. The high concordance between lesion-filled and non-lesion-filled estimates confirms the robustness of brain age as a biomarker, while supporting the use of lesion correction when structural precision is essential.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"356"},"PeriodicalIF":3.2,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12382106/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144941781","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":"Late enhancement and wash-out maps for differentiation of glioblastoma and metastases.","authors":"Leon Schmidt, Eya Khadhraoui, Stefan Klebingat, I Erol Sandalcioglu, Roland Schwab, Belal Neyazi, Daniel Behme, Klaus-Peter Stein, Sebastian Johannes Müller","doi":"10.1186/s12880-025-01889-6","DOIUrl":"https://doi.org/10.1186/s12880-025-01889-6","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"353"},"PeriodicalIF":3.2,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12382173/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144941613","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":"A percutaneous core needle biopsy of deep suprahyoid head and neck lesions with CT-guided: study of diagnostic performance and factors associated with diagnostic failure.","authors":"Yingyu Pan, Zhe Ren, Hongbo Zhao, Weiqing Tang","doi":"10.1186/s12880-025-01899-4","DOIUrl":"https://doi.org/10.1186/s12880-025-01899-4","url":null,"abstract":"<p><strong>Purpose: </strong>Pathological diagnosis is important for the treatment of deep suprahyoid head and neck lesions, and tissue sampling needs to balance minimal invasiveness and accuracy. The purpose of this study was to evaluate diagnostic accuracy and factors associated with diagnostic failure of core needle biopsy (CNB) with CT-guided in deep suprahyoid head and neck lesions.</p><p><strong>Methods: </strong>The records of 204 patients who underwent CT-guided CNB were retrospectively reviewed. CT-guided CNB was conducted for pathological diagnosis with the use of 18-G coaxial biopsy needles. Diagnostic accuracy for the diagnosis of lesions were calculated by comparing the biopsy results with the operative specimen or based on treatment response and clinical follow-up more than 6 months. Factors associated with biopsy failure was identified by chi-square test and logistics regression of procedure characteristics and lesion features.</p><p><strong>Result: </strong>All 204 specimens were deemed adequate for histological diagnosis, with no immediate or delayed severe complications encountered. The diagnostic performance showed a sensitivity of 89.2% (141/158), specificity of 97.8% (45/46), and overall accuracy of 91.2% (186/204). Respectively, lesions with poorly defined margins or pre-procedural diagnostic imaging were the potential factor for diagnostic failure.</p><p><strong>Conclusion: </strong>CNB with CT-guidance is an effective procedure for tissue diagnosis of patient with primary deep suprahyoid head and neck lesions and skull base lesions. Notably, lesions with poorly defined margins and suboptimal pre-procedural imaging emerged as potential factors contributing to diagnostic failure. Specifically, for lesions with indistinct boundaries-wherein the extent of the lesion is difficult to delineate-pre-procedural assessment using magnetic resonance imaging is recommended to enhance the clarity of lesion margins, thereby potentially improving diagnostic accuracy.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"352"},"PeriodicalIF":3.2,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12382221/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144941935","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":"Predictive value of contrast-enhanced ultrasound in assessing the risk of recurrent in ipsilateral anterior circulation ischemic stroke.","authors":"Jinyong Zhan, Zhifei Ben, Jue Wang, Kaiying Xu","doi":"10.1186/s12880-025-01887-8","DOIUrl":"https://doi.org/10.1186/s12880-025-01887-8","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"350"},"PeriodicalIF":3.2,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12379353/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144941723","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":"Correction: Preoperative FLAIR images for identifying glioblastoma boundaries.","authors":"Bayan Shukir, Laszlo Szivos, Pal Barzo, David Kis","doi":"10.1186/s12880-025-01880-1","DOIUrl":"https://doi.org/10.1186/s12880-025-01880-1","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"351"},"PeriodicalIF":3.2,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12379446/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144941974","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":"A prospective study of transorbital ultrasound multimodal imaging in the detection and evaluation of increased intracranial pressure.","authors":"Peng He, Lanlan Yu, Xingheng Wang, Bo Ren, Peng Gu, Fei Yang, Yuan Zou","doi":"10.1186/s12880-025-01893-w","DOIUrl":"https://doi.org/10.1186/s12880-025-01893-w","url":null,"abstract":"<p><strong>Background: </strong>To develop and validate a multimodal transorbital ultrasound model for noninvasive detection of increased intracranial pressure (IICP) by integrating anatomical and hemodynamic parameters.</p><p><strong>Methods: </strong>In this prospective diagnostic study, 136 neurology patients scheduled for lumbar puncture underwent pre-procedural ultrasound measurement of optic nerve sheath diameter (ONSD), ONSD-to-eyeball transverse diameter ratio (ONSD/ETD), and central retinal artery hemodynamics (peak systolic velocity [PSV], resistance index [RI]). Patients were classified as IICP (CSF pressure > 200 mmH₂O) or normal ICP (NICP) groups. Parameter performance was analyzed via ROC curves; multivariate logistic regression constructed a predictive model.</p><p><strong>Results: </strong>The IICP group (n = 52) showed significantly higher ONSD (5.06 ± 0.49 vs. 4.19 ± 0.82 mm), ONSD/ETD (0.24 ± 0.02 vs.0.19 ± 0.04), and RI (0.66 ± 0.07vs.0.56 ± 0.09) but lower PSV (9.45 ± 1.38 vs.10.86 ± 2.14 cm/s) versus NICP (n = 84) (all P < 0.001). The integrated model (ONSD + ONSD/ETD + PSV + RI) achieved superior diagnostic accuracy: AUC 0.95 (95% CI: 0.922-0.988), sensitivity 88.1%, specificity 98.0%, Youden's index 0.86-significantly outperforming any single parameter (AUC 0.67-0.87, P < 0.001)-with the predictive equation: Logit(P) = 1.94×ONSD-84.6×ONSD/ETD + 0.79×PSV-3.8×RI + 11.05.</p><p><strong>Conclusion: </strong>Transorbital multimodal ultrasound combining structural and vascular parameters enables highly accurate, rapid IICP screening, offering a clinically viable noninvasive alternative to conventional monitoring.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"349"},"PeriodicalIF":3.2,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12379483/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144941921","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":"Development and evaluation of a convolutional neural network model for sex prediction using cephalometric radiographs and cranial photographs.","authors":"Vitria Wuri Handayani, Mieke Sylvia Margareth Amiatun Ruth, Riries Rulaningtyas, Muhammad Rasyad Caesarardhi, Bayu Azra Yudhantorro, Ahmad Yudianto","doi":"10.1186/s12880-025-01892-x","DOIUrl":"https://doi.org/10.1186/s12880-025-01892-x","url":null,"abstract":"<p><strong>Background: </strong>Accurately determining sex using features like facial bone profiles and teeth is crucial for identifying unknown victims. Lateral cephalometric radiographs effectively depict the lateral cranial structure, aiding the development of computational identification models.</p><p><strong>Objective: </strong>This study develops and evaluates a sex prediction model using cephalometric radiographs with several convolutional neural network (CNN) architectures. The primary goal is to evaluate the model's performance on standardized radiographic data and real-world cranial photographs to simulate forensic applications.</p><p><strong>Methods: </strong>Six CNN architectures-VGG16, VGG19, MobileNetV2, ResNet50V2, InceptionV3, and InceptionResNetV2-were employed to train and validate 340 cephalometric images of Indonesian individuals aged 18 to 40 years. The data were divided into training (70%), validation (15%), and testing (15%) subsets. Data augmentation was implemented to mitigate class imbalance. Additionally, a set of 40 cranial images from anatomical specimens was employed to evaluate the model's generalizability. Model performance metrics included accuracy, precision, recall, and F1-score.</p><p><strong>Results: </strong>CNN models were trained and evaluated on 340 cephalometric images (255 females and 85 males). VGG19 and ResNet50V2 achieved high F1-scores of 95% (females) and 83% (males), respectively, using cephalometric data, highlighting their strong class-specific performance. Although the overall accuracy exceeded 90%, the F1-score better reflected model performance in this imbalanced dataset. In contrast, performance notably decreased with cranial photographs, particularly when classifying female samples. That is, while InceptionResNetV2 achieved the highest F1-score for cranial photographs (62%), misclassification of females remained significant. Confusion matrices and per-class metrics further revealed persistent issues related to data imbalance and generalization across imaging modalities.</p><p><strong>Conclusions: </strong>Basic CNN models perform well on standardized cephalometric images but less effectively on photographic cranial images, indicating a domain shift between image types that limits generalizability. Improving real-world forensic performance will require further optimization and more diverse training data.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"348"},"PeriodicalIF":3.2,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12379395/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144941242","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":"Multiparametric MRI for differential diagnosis of primary central nervous system lymphoma and atypical glioblastoma: an analysis incorporating DWI, DCE-MRI, and contrast agent preload DSC-PWI.","authors":"Lan Yu, Shujie Yu, Feng Wang, Xiaofang Zhou, Feiman Yang, Dairong Cao, Zhen Xing","doi":"10.1186/s12880-025-01886-9","DOIUrl":"https://doi.org/10.1186/s12880-025-01886-9","url":null,"abstract":"<p><strong>Purpose: </strong>The differential diagnosis of primary central nervous system lymphoma (PCNSL) and atypical glioblastoma (aGBM) exhibiting homogeneous enhancement and negligible necrosis poses a significant challenge for conventional MRI. The study aims to investigate diffusion-weighted imaging (DWI), dynamic contrast-enhanced (DCE) MRI, and contrast agent (CA) preload dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) to differentiate aGBM and PCNSL.</p><p><strong>Materials and methods: </strong>This retrospective study analyzed 27 patients with aGBM (solid enhancement without visible necrosis) and 105 patients with PCNSL, all undergoing preoperative DWI, DCE-MRI, and CA preload DSC-PWI. The relative apparent diffusion coefficient (rADC) and relative cerebral blood volume (rCBV) were obtained from DWI and DSC-PWI. The pharmacokinetic parameters (Ktrans, Ve, Kep, and iAUC) were acquired using DCE-MRI. The independent-samples t-test and Mann-Whitney U test were utilized to compare parameters. A binary logistic regression analysis was performed to assess the combined effect of various parameters. Before regression analysis, collinearity analysis of parameters was performed. The diagnostic capability of each parameter and their combination were evaluated by receiver operating characteristic (ROC) with area under the curve (AUC) and compared with DeLong test.</p><p><strong>Results: </strong>In comparison to aGBM, the Ktrans, Ve, and iAUC were significantly elevated in PCNSL, whereas the rCBV and rADC were significantly lower (p < 0.05 for all comparisons). Meanwhile, these parameters allowed excellent diagnostic performance (AUC = 0.817 [rCBV], 0.751 [rADC], 0.808 [Ktrans], 0.765 [Ve], and 0.801 [iAUC]; DeLong test, p > 0.05 for all comparisons). Notably, the combination of all these parameters significantly increased the probability of distinguishing aGBM from PCNSL (AUC = 0.966).</p><p><strong>Conclusions: </strong>DWI, DCE-MRI, and CA preload DSC-PWI can effectively differentiate aGBM from PCNSL, and the combination of all three techniques significantly enhances the discriminatory efficacy.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"345"},"PeriodicalIF":3.2,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12376417/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144941642","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":"Reducing radiomics errors in nasopharyngeal cancer via deep learning-based synthetic CT generation from CBCT.","authors":"Ying Xiao, Weixiang Lin, Fangping Xie, Lipeng Liu, Gaoyin Zheng, Chengjian Xiao","doi":"10.1186/s12880-025-01894-9","DOIUrl":"https://doi.org/10.1186/s12880-025-01894-9","url":null,"abstract":"<p><strong>Purpose: </strong>This study investigates the impact of cone beam computed tomography (CBCT) image quality on radiomic analysis and evaluates the potential of deep learning-based enhancement to improve radiomic feature accuracy in nasopharyngeal cancer (NPC).</p><p><strong>Methods: </strong>The CBAMRegGAN model was trained on 114 paired CT and CBCT datasets from 114 nasopharyngeal cancer patients to enhance CBCT images, with CT images as ground truth. The dataset was split into 82 patients for training, 12 for validation, and 20 for testing. The radiomic features in 6 different categories, including first-order, gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), gray-level size-zone matrix(GLSZM), neighbouring gray tone difference matrix (NGTDM), and gray-level dependence matrix (GLDM), were extracted from the gross tumor volume (GTV) of original CBCT, enhanced CBCT, and CT. Comparing feature errors between original and enhanced CBCT showed that deep learning-based enhancement improves radiomic feature accuracy.</p><p><strong>Results: </strong>The CBAMRegGAN model achieved improved image quality with a peak signal-to-noise ratio (PSNR) of 29.52 ± 2.28 dB, normalized mean absolute error (NMAE) of 0.0129 ± 0.004, and structural similarity index (SSIM) of 0.910 ± 0.025 for enhanced CBCT images. This led to reduced errors in most radiomic features, with average reductions across 20 patients of 19.0%, 24.0%, 3.0%, 19%, 15.0%, and 5.0% for first-order, GLCM, GLRLM, GLSZM, NGTDM, and GLDM features.</p><p><strong>Conclusion: </strong>This study demonstrates that CBCT image quality significantly influences radiomic analysis, and deep learning-based enhancement techniques can effectively improve both image quality and the accuracy of radiomic features in NPC.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"347"},"PeriodicalIF":3.2,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12379482/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144941775","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}