BMC Medical Imaging最新文献

{"title":"Comparative analysis of preoperative contrast-enhanced cone beam breast CT (CE-CBBCT) and MRI for differentiating pathological complete response from minimal residual disease in breast cancer.","authors":"Yafei Wang, Fang Wang, Yue Ma, Aidi Liu, Mengran Zhao, Keyi Bian, Yueqiang Zhu, Lu Yin, Hong Lu, Zhaoxiang Ye","doi":"10.1186/s12880-025-01926-4","DOIUrl":"10.1186/s12880-025-01926-4","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>To evaluate the performance of contrast-enhanced cone-beam breast CT (CE-CBBCT) using visual, quantitative, and combined models in distinguishing pathological complete response (pCR) from minimal residual disease (MRD) after neoadjuvant therapy (NAT), and to compare its diagnostic efficacy with MRI.</p><p><strong>Materials and methods: </strong>This study enrolled 65 female patients who underwent both CE-CBBCT and MRI after NAT and were classified as having either pCR or MRD. Univariate and multivariate logistic regression analyses were performed to identify independent visual and quantitative features from CE-CBBCT and MRI associated with pCR. Model performance was assessed and compared using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), DeLong's test, and McNemar's test. The bootstrap method was employed to assess the stability of each model.</p><p><strong>Results: </strong>Multivariate analysis identified fine and branched calcification morphology on CE-CBBCT (visual model: odds ratio [OR] = 4.500; combined model: OR = 4.527), enhanced degree (ΔHU, quantitative model: OR = 1.036; combined model: OR = 1.035), radiographic complete response (rCR; visual model: OR = 0.103; combined model: OR = 0.097), and delayed-phase MRI enhancement ratio (ER_dpMRI; quantitative model: OR = 5.048; combined model: OR = 5.583) as independent predictors of pCR. The CE-CBBCT combined model demonstrated a significantly higher AUC than the visual model (0.805 vs. 0.698, p = 0.017) and performed comparably to the MRI combined model (0.805 vs. 0.819, p = 0.811). In the HER2-enriched subgroup, the CE-CBBCT combined model exhibited higher specificity than MRI (0.857 vs. 0.714, p = 0.011) for identifying pCR.</p><p><strong>Conclusion: </strong>The combination of calcification morphology and ΔHU on CE-CBBCT improved accuracy in discriminating pCR from MRD, achieving performance comparable to MRI. Notably, the CE-CBBCT combined model showed superior specificity to MRI within the HER2-enriched subgroup, suggesting its potential utility in reducing overtreatment in this patient population.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"390"},"PeriodicalIF":3.2,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12482609/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145190828","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":"Predicting biliary stricture after liver transplantation based on CT imaging features combined with clinicopathological factors.","authors":"Caiqiong Wang, Lingqing Tang, Fan Zhang, Yubo Wang, Hao Hu, Bosen Xie, Yonghua Liu, Wei Li, Yurong Qi, Weilian Guo, Yan Li, Yuchao Bao, Bin Yang","doi":"10.1186/s12880-025-01866-z","DOIUrl":"10.1186/s12880-025-01866-z","url":null,"abstract":"<p><strong>Objective: </strong>To investigate the value of computed tomography imaging features combined with clinicopathological factors in predicting patients' biliary stricture (BS) after liver transplantation and to identify patients at a high risk for BS.</p><p><strong>Methods: </strong>The imaging data and clinicopathological factors of 178 recipients who underwent liver transplantation at the First People's Hospital of Kunming, were collected. The patients were randomly divided into training and validation set, patients were divided into BS (n = 46) and non-BS groups (n = 132). Independent risk factors to establish models were screened using logistic regression analysis. Predictive efficacy of the models was evaluated using the area under the receiver operating characteristic curve (AUC).</p><p><strong>Results: </strong>BS occurred in 46 of 178 liver transplant recipients. Univariate analysis revealed that postoperative cholangitis, postoperative biliary calculi, and abdominal aorta and branch plaques were significant risk factors for biliary stricture after liver transplantation (p < 0.05). Further multivariate analysis showed that postoperative cholangitis (OR = 19.450, 95% CI: 2.150-176.010), postoperative biliary calculi (OR = 15.340, 95% CI: 1.530-154.060), and abdominal aorta and branch plaques (OR = 4.360, 95% CI: 1.760-10.810) were independent risk factors for biliary stricture after liver transplantation (p < 0.05). The prediction model constructed based on these risk factors revealed AUC values of 0.745 and 0.738 for the training and validation sets, respectively. The calibration curve demonstrated consistency between the predicted and actual values, and the decision curve highlighted the clinical benefit.</p><p><strong>Conclusion: </strong>The nomogram based on independent risk factors effectively identified patients at high risk of BS post-liver transplantation.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"389"},"PeriodicalIF":3.2,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12482254/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145190957","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 of a machine learning model using radiomics features from breast synthetic MRI.","authors":"Takuya Matsuda, Megumi Matsuda, Hasnine Haque, Shotaro Fuchibe, Masaki Matsumoto, Yasuhiro Shiraishi, Yuki Nobe, Kango Kuwabara, Wataru Toshimori, Kanako Okada, Naoto Kawaguchi, Mie Kurata, Yoshiaki Kamei, Riko Kitazawa, Teruhito Kido","doi":"10.1186/s12880-025-01930-8","DOIUrl":"10.1186/s12880-025-01930-8","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"399"},"PeriodicalIF":3.2,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12482869/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145190876","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":"Application of snake model imaging selection and analysis to the ultrasound diagnosis of white matter damage in preterm infants.","authors":"Xuehua He, Hongying Wang, Liling Zhu, Na Wang","doi":"10.1186/s12880-025-01943-3","DOIUrl":"10.1186/s12880-025-01943-3","url":null,"abstract":"<p><strong>Background: </strong>Approximately 20% to 30% of preterm infants may develop white matter injury. Early detection of brain injury is of great significance for clinical practice. The snake model is a boundary detection technology used in image processing and computer vision. It automatically locates the closed boundaries of objects in the image by simulating the behavior of elastic snakes. The quantitative ultrasound segmentation technique using the snake model can improve the accuracy of the diagnosis of early white matter injury.</p><p><strong>Methods: </strong>In this retrospective single-center study, cranial ultrasound scans from 60 preterm infants with clinically confirmed WMD and 40 healthy controls were analyzed. Five regions of interest (ROIs) around key brain structures were automatically delineated by the snake model, and mean grayscale values were measured. Reproducibility was assessed via inter- and intra-observer analyses, and receiver operating characteristic (ROC) curves determined optimal thresholds for WMD prediction.</p><p><strong>Results: </strong>The snake model achieved a mean area under the ROC curve (AUC) of 0.87 for ROI₁, 0.85 for ROI₂, and 0.82 for ROI₃, with corresponding sensitivities of 0.82, 0.70, and 0.63 and specificities of 0.88, 0.85, and 0.88. The average Dice coefficient across ROIs was 0.75, and The total coefficient of variation was 6.7%, which was less than 10%, indicating high reproducibility.</p><p><strong>Conclusions: </strong>Quantitative analysis of ultrasound images with the snake model demonstrates promising accuracy and reproducibility for early WMD detection in preterm infants. Future multicenter studies with larger cohorts are warranted to validate these findings.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"396"},"PeriodicalIF":3.2,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12482655/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145190809","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":"Sound touch viscosity in the evaluation of median nerve in healthy volunteers-a preliminary study.","authors":"Jun Huang, Hongpeng Duan, Minwei Zhang, Jian Lu, Feng Mao, Ling Zhou, Shengmin Zhang","doi":"10.1186/s12880-025-01939-z","DOIUrl":"10.1186/s12880-025-01939-z","url":null,"abstract":"<p><strong>Background: </strong>Quantitative assessment of peripheral nerve viscoelasticity is important for understanding nerve physiology and detecting early neuropathic changes. However, reference values for the viscosity and stiffness of the median nerve in healthy adults are lacking.</p><p><strong>Materials and methods: </strong>A total of 98 healthy volunteers (58 females, 40 males; mean age: 35 ± 12 years) were assessed using the Sound Touch Viscosity and shear wave elastography modules integrated into the Resona A20S ultrasound system. Viscosity and stiffness were measured at three anatomical locations: the carpal tunnel (MN1), mid-forearm (MN2), and 5 cm proximal to the elbow joint (MN3). Paired bilateral measurements were obtained, and demographic factors were analyzed for their influence.</p><p><strong>Results: </strong>No significant differences were found between the left and right median nerves (p > 0.05). MN1 showed the highest viscosity 1.83 Pa·s (1.48-2.13) and stiffness of 30.24 kPa (28.46-33.65) significantly greater than MN2 and MN3 (p < 0.001). Viscosity and stiffness were moderately correlated at all sites ((r = 0.39, 0.56, and 0.36; all p < 0.001). Males showed higher stiffness at all locations (p < 0.001) and higher viscosity at MN1 and MN2 (p = 0.039 and 0.011). While age and body mass index (BMI) showed no significant effects.</p><p><strong>Conclusion: </strong>STVi is a feasible and reproducible modality for quantifying median nerve viscoelasticity. Viscoelastic parameters vary significantly by anatomical location and sex, with no influence from age and BMI. These findings establish normative values and support the clinical applicability of Sound Touch Viscosity in peripheral nerve assessment.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"394"},"PeriodicalIF":3.2,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12482535/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145190995","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":"DCM-Net: dual-encoder CNN-Mamba network with cross-branch fusion for robust medical image segmentation.","authors":"Chukwuemeka Clinton Atabansi, Sheng Wang, Hui Li, Jing Nie, Lei Xiang, Cheng Zhang, Haijun Liu, Xichuan Zhou, Dewei Li","doi":"10.1186/s12880-025-01942-4","DOIUrl":"10.1186/s12880-025-01942-4","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"395"},"PeriodicalIF":3.2,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12482534/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145190843","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":"Investigation of MRI features in subtypes of primary central nervous system diffuse large B-cell lymphoma.","authors":"Yanwei Zeng, Xin Cao, Kun Lv, Mengxue Zhang, Daoying Geng","doi":"10.1186/s12880-025-01933-5","DOIUrl":"10.1186/s12880-025-01933-5","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"400"},"PeriodicalIF":3.2,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12482133/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145190863","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":"Gd-EOB-DTPA-enhanced hepatobiliary phase MRI characteristics of inflammatory hepatic adenoma.","authors":"Yiheng Zheng, Ermin Cai, Mengsu Zeng, Mingliang Wang","doi":"10.1186/s12880-025-01938-0","DOIUrl":"10.1186/s12880-025-01938-0","url":null,"abstract":"<p><strong>Purpose: </strong>To investigate the imaging characteristics of the hepatocyte-specific contrast agent gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid (Gd-EOB-DTPA) in inflammatory hepatocellular adenoma.</p><p><strong>Methods: </strong>The clinical data and magnetic resonance imaging (MRI) manifestations of 13 patients with pathologically confirmed I-HCA were retrospectively analyzed. There were 10 males and 3 females with an average age of 33.1 ± 10.7years. All patients underwent enhanced MR examination with Gd-EOB-DTPA (a hepatocyte-specific contrast agent). Image analysis included the number, location, size, morphology, plain scan signal, enhancement characteristics, and hepatobiliary-specific phase (HBP). The apparent diffusion coefficient (ADC) values of the lesions and surrounding normal liver parenchyma were measured on the ADC map, and the difference was compared by paired sample t-test.</p><p><strong>Results: </strong>In this study, CRP showed a high rate of positive results; there was positive reactivity for CD34 in all patients. Among the 13 cases, 8 cases were single and 5 were multiple, for a total of 26 lesions. The margins of the lesions were all clear, and mostly round or oval; T1WI showed equal or high signal, T2WI showed high signal, DWI showed high signal, the arterial phase was highly enhanced, and the portal phase was not clear. 21 lesions in the hepatobiliary-specific phase had no uptake. The atoll sign was present in only 12% of cases. There was no significant difference between the average ADC value of the lesion and the average ADC value of the adjacent normal liver parenchyma (P = 0.620). The study revealed positive reactivity for C-reactive protein (CRP) and CD34.</p><p><strong>Conclusion: </strong>The Gd-EOB-DTPA-enhanced hepatobiliary phase MRI of I-HCA exhibits certain characteristic features, which serve as an aid in the diagnosis of the disease.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"388"},"PeriodicalIF":3.2,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12481813/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145190879","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":"Heterogeneity phenotypes in recurrent glioblastoma: a multimodal MRI-based spatial mapping framework for precision treatment.","authors":"Yan Zhu, Dian Huang, Yang Ji, Ranchao Wang, Yang Li, Yuhao Xu, Yan Zhuang, Zhe Liu, Yuefeng Li, Wei Wang","doi":"10.1186/s12880-025-01929-1","DOIUrl":"10.1186/s12880-025-01929-1","url":null,"abstract":"<p><strong>Background: </strong>To develop a multimodal magnetic resonance imaging (MRI)-based spatial mapping framework for quantitatively characterizing intratumoral heterogeneity in recurrent glioblastoma (rGBM), identifying distinct imaging subregions, and classifying heterogeneity phenotypes predictive of treatment response and survival outcomes.</p><p><strong>Methods: </strong>A total of 140 rGBM patients were recruited and underwent standardized diffusion-weighted imaging (DWI) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Pixel-wise colocalization of apparent diffusion coefficient (ADC) and DCE-MRI features identified four Multimodal Imaging Subregions (MIS). Entropy and Moran's I quantified heterogeneity, and hierarchical clustering defined imaging phenotypes. Treatment response to 1-(2-chloroethyl)-3-cyclohexyl-1-nitrosourea (CCNU), bevacizumab (Bev) + stereotactic radiotherapy (SRT), and Bev + CCNU was assessed by volumetric and component-level changes. Survival analyses were performed using Kaplan-Meier and multivariate Cox models.</p><p><strong>Results: </strong>MIS4, defined by low ADC and slow-rising enhancement, was consistently treatment-resistant. Three imaging phenotypes with distinct heterogeneity patterns demonstrated significant prognostic stratification across regimens. Phenotype A showed the best outcomes under Bev-based regimens, while Phenotype B responded better to CCNU. Imaging phenotypes independently predicted progression-free survival (PFS) and overall survival (OS).</p><p><strong>Conclusion: </strong>This framework enables spatially resolved, phenotype-based analysis of rGBM heterogeneity using routine MRI. Imaging phenotypes serve as non-invasive biomarkers to guide personalized treatment planning and outcome prediction in recurrent glioblastoma.</p><p><strong>Clinical trial registration number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"386"},"PeriodicalIF":3.2,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12465940/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173500","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":"Enhanced CoAtNet based hybrid deep learning architecture for automated tuberculosis detection in human chest X-rays.","authors":"Gunjan Siddharth, Ananya Ambekar, Naveenkumar Jayakumar","doi":"10.1186/s12880-025-01901-z","DOIUrl":"10.1186/s12880-025-01901-z","url":null,"abstract":"<p><p>Tuberculosis (TB) is a serious infectious disease that remains a global health challenge. While chest X-rays (CXRs) are widely used for TB detection, manual interpretation can be subjective and time-consuming. Automated classification of CXRs into TB and non-TB cases can significantly support healthcare professionals in timely and accurate diagnosis. This paper introduces a hybrid deep learning approach for classifying CXR images. The solution is based on the CoAtNet framework, which combines the strengths of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). The model is pre-trained on the large-scale ImageNet dataset to ensure robust generalization across diverse images. The evaluation is conducted on the IN-CXR tuberculosis dataset from ICMR-NIRT, which contains a comprehensive collection of CXR images of both normal and abnormal categories. The hybrid model achieves a binary classification accuracy of 86.39% and an ROC-AUC score of 93.79%, outperforming tested baseline models that rely exclusively on either CNNs or ViTs when trained on this dataset. Furthermore, the integration of Local Interpretable Model-agnostic Explanations (LIME) enhances the interpretability of the model's predictions. This combination of reliable performance and transparent, interpretable results strengthens the model's role in AI-driven medical imaging research. Code will be made available upon request.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"379"},"PeriodicalIF":3.2,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12465491/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145173562","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}