BMC Medical Imaging最新文献

{"title":"Enhancing risk stratification in diabetic gastric cancer: muscle-fat ratio from photon-counting CT as a predictor of postoperative complications.","authors":"Shuangxiang Lin, Yuchen Jin, Mengxi Xu, Shuyue Wang, Weisheng Yao, Jiaxing Wu, Xinhong Wang, Jianzhong Sun","doi":"10.1186/s12880-025-01872-1","DOIUrl":"10.1186/s12880-025-01872-1","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"334"},"PeriodicalIF":3.2,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12363078/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881936","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 pectoralis muscle index predicts distant metastasis-free survival in non-small cell lung cancer patients: a retrospective study.","authors":"Zhihui Shi, Lin Wu, Dengke Jiang, Ruiling Yang, Rui Liao, Lizhu Liu, Ruimin You, Yanli Li, Xingxiang Dong, Dafu Zhang, Jing Wang, Xuewen Zhang, Xiaobo Chen, Zhenhui Li","doi":"10.1186/s12880-025-01873-0","DOIUrl":"10.1186/s12880-025-01873-0","url":null,"abstract":"<p><strong>Background: </strong>Thoracic muscles contribute to respiration, is a crucial indicator for assessing functional recovery following lung resection. However, there is a lack of research on the long-term prognostic value of pectoralis muscle.</p><p><strong>Methods: </strong>Consecutive patients who underwent curative-intent resection for stage I to IIIA NSCLC between 2013 and 2018 at a cancer center were retrospectively identified. The Cox proportional hazard model was employed to analyze the correlation between pectoralis muscle index (PMI) and survival, with subgroup analyses conducted to explore potential heterogeneity among different subgroups. Finally, the relative influence of each parameter was compared using a gradient boosting model (GBM).</p><p><strong>Results: </strong>A total of 2110 patients (median (IQR) age 59 (52, 66) years) were evaluated. Kaplan-Meier survival analysis showed that the recurrence-free survival (RFS) and distant metastasis-free survival (DMFS) rate of patients in the high PMI group were higher than those in the low PMI group, all with P < 0.001. In the multivariable analysis, low PMI is still associated with shorter RFS (HR = 1.34, 95% CI: (1.10, 1.62), P = 0.004), DMFS (HR = 1.35, 95% CI: (1.11, 1.65), P = 0.003), lung MFS (HR = 1.47, 95% CI: (1.19, 1.81), P < 0.001) and bone MFS (HR = 1.38, 95% CI: (1.11, 1.73), P = 0.004). These associations were consistent in subgroup analysis of different gender, age, tumor stage, histologic type, and surgical approach group.</p><p><strong>Conclusions: </strong>Low PMI is significantly associated with worse distant metastasis-free survival (DMFS) and recurrence-free survival (RFS) in non-small cell lung cancer (NSCLC) patients, supporting its utility in refining preoperative risk stratification. When CT imaging lacks L3-level coverage, PMI offers a viable alternative for assessing muscle quality.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"335"},"PeriodicalIF":3.2,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12362906/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881940","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":"Radiomics-based classification of pediatric dental trauma in periapical radiographs: a preliminary study.","authors":"Mengtian Peng, Bin Yu, Juan Hu, Xiaoxin Xie, Jihong He","doi":"10.1186/s12880-025-01877-w","DOIUrl":"10.1186/s12880-025-01877-w","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"336"},"PeriodicalIF":3.2,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12362901/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881941","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":"Computed tomography radiomics of intratumoral and peritumoral microenvironments for identifying the invasiveness of subcentimeter lung adenocarcinomas.","authors":"Yu-Qiang Zuo, Qing Liu, Tie-Zhi Li, Zhi-Hong Gao, Xu Yang, Yu-Ling Yin, Ping-Yong Feng, Zuo-Jun Geng","doi":"10.1186/s12880-025-01882-z","DOIUrl":"10.1186/s12880-025-01882-z","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"331"},"PeriodicalIF":3.2,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12359731/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144871351","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":"Subtraction fractional flow reserve with computed tomography and pericoronary fat attenuation index enhances the identification of revascularization needs in patients.","authors":"Tingting Zhu, Yanhui Li, Yujin Wang, Hanxiong Guan, Qian Li, Defu Li","doi":"10.1186/s12880-025-01874-z","DOIUrl":"10.1186/s12880-025-01874-z","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"332"},"PeriodicalIF":3.2,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12362918/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144871352","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 baseline ¹⁸F-FDG PET/CT imaging features in pediatric patients with congenital neuroblastoma.","authors":"Keyu Zhang, Guanyun Wang, Xiaoya Wang, Ying Kan, Wei Wang, Jigang Yang","doi":"10.1186/s12880-025-01863-2","DOIUrl":"10.1186/s12880-025-01863-2","url":null,"abstract":"<p><strong>Purpose: </strong>Congenital neuroblastoma represents a distinct subtype of neuroblastoma that originates during fetal and neonatal development. Limited research has been conducted on the prognostic significance of baseline Fluorine-18-Fluorodeoxyglucose positron emission tomography/computerized tomography (¹⁸F-FDG PET/CT) in pediatric patients with congenital neuroblastoma. This study aims to characterize the baseline ¹⁸F-FDG PET/CT imaging features in children with congenital neuroblastoma.</p><p><strong>Methods: </strong>A retrospective collection was performed using imaging and clinical data from pediatric patients diagnosed with congenital neuroblastoma who underwent ¹⁸F-FDG PET/CT at the Beijing Friendship Hospital, Capital Medical University between June 2020 and June 2023. We collected clinical and ¹⁸F-FDG PET metabolic parameters, including maximum standardized uptake value, mean standardized uptake value (SUVmean), metabolic tumor volume (MTV), and total lesion glycolysis (TLG), total-body MTV and total-body TLG. Patients were categorized into the recurrence group and the non-recurrence group based on the follow-up outcomes.</p><p><strong>Results: </strong>A total of 28 pediatric patients with congenital neuroblastoma were included in the study. There are 26 patients exhibited elevated serum NSE levels, 25 patients exhibited elevated serum LDH levels. Only 3 patients had MYCN amplification. 5 patients had 11q23 aberration. Primary tumors were located in the abdomen or mediastinum in all but two patients, who had pelvic and cervical involvement. All primary tumor had high FDG uptake. 6 patients had liver metastases, and 1 patient showed normal FDG uptake. 4 patients had bone marrow metastases, all of them showed high FDG uptake. With a median follow-up of 711 days, 23 patients had progression free survival, and 5 cases of recurrence.</p><p><strong>Conclusion: </strong>Our study showed that the prognosis of congenital neuroblastoma was generally favorable and ¹⁸F-FDG PET/CT is valuable for the diagnosis and staging in congenital neuroblastoma.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"330"},"PeriodicalIF":3.2,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12355819/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144854337","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 in CTEPH: predicting the efficacy of BPA based on clinical and echocardiographic features.","authors":"Qiumeng Xi, Juanni Gong, Jianfeng Wang, Xiaojuan Guo, Yuanhua Yang, Xiuzhang Lv, Suqiao Yang, Yidan Li","doi":"10.1186/s12880-025-01870-3","DOIUrl":"10.1186/s12880-025-01870-3","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"328"},"PeriodicalIF":3.2,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12351865/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144854336","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":"AI post-intervention operational and functional outcomes prediction in ischemic stroke patients using MRIs.","authors":"Emily Wittrup, John Reavey-Cantwell, Aditya S Pandey, Dennis J Rivet Ii, Kayvan Najarian","doi":"10.1186/s12880-025-01864-1","DOIUrl":"10.1186/s12880-025-01864-1","url":null,"abstract":"<p><strong>Background: </strong>Despite the potential clinical utility for acute ischemic stroke patients, predicting short-term operational outcomes like length of stay (LOS) and long-term functional outcomes such as the 90-day Modified Rankin Scale (mRS) remain a challenge, with limited current clinical guidance on expected patient trajectories. Machine learning approaches have increasingly aimed to bridge this gap, often utilizing admission-based clinical features; yet, the integration of imaging biomarkers remains underexplored, especially regarding whole 2.5D image fusion using advanced deep learning techniques.</p><p><strong>Methods: </strong>This study introduces a novel method leveraging autoencoders to integrate 2.5D diffusion weighted imaging (DWI) with clinical features for refined outcome prediction.</p><p><strong>Results: </strong>Results on a comprehensive dataset of AIS patients demonstrate that our autoencoder-based method has comparable performance to traditional convolutional neural networks image fusion methods and clinical data alone (LOS > 8 days: AUC 0.817, AUPRC 0.573, F1-Score 0.552; 90-day mRS > 2: AUC 0.754, AUPRC 0.685, F1-Score 0.626).</p><p><strong>Conclusion: </strong>This novel integration of imaging and clinical data for post-intervention stroke prognosis has numerous computational and operational advantages over traditional image fusion methods. While further validation of the presented models is necessary before adoption, this approach aims to enhance personalized patient management and operational decision-making in healthcare settings.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"329"},"PeriodicalIF":3.2,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12355742/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144854335","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":"ES-UNet: efficient 3D medical image segmentation with enhanced skip connections in 3D UNet.","authors":"Minyoung Park, Seungtaek Oh, Junyoung Park, Taikyeong Jeong, Sungwook Yu","doi":"10.1186/s12880-025-01857-0","DOIUrl":"10.1186/s12880-025-01857-0","url":null,"abstract":"<p><strong>Background: </strong>Deep learning has significantly advanced medical image analysis, particularly in semantic segmentation, which is essential for clinical decisions. However, existing 3D segmentation models, like the traditional 3D UNet, face challenges in balancing computational efficiency and accuracy when processing volumetric medical data. This study aims to develop an improved architecture for 3D medical image segmentation with enhanced learning strategies to improve accuracy and address challenges related to limited training data.</p><p><strong>Methods: </strong>We propose ES-UNet, a 3D segmentation architecture that achieves superior segmentation performance while offering competitive efficiency across multiple computational metrics, including memory usage, inference time, and parameter count. The model builds upon the full-scale skip connection design of UNet3+ by integrating channel attention modules into each encoder-to-decoder path and incorporating full-scale deep supervision to enhance multi-resolution feature learning. We further introduce Region Specific Scaling (RSS), a data augmentation method that adaptively applies geometric transformations to annotated regions, and a Dynamically Weighted Dice (DWD) loss to improve the balance between precision and recall. The model was evaluated on the MICCAI HECKTOR dataset, and additional validation was conducted on selected tasks from the Medical Segmentation Decathlon (MSD).</p><p><strong>Results: </strong>On the HECKTOR dataset, ES-UNet achieved a Dice Similarity Coefficient (DSC) of 76.87%, outperforming baseline models including 3D UNet, 3D UNet 3+, nnUNet, and Swin UNETR. Ablation studies showed that RSS and DWD contributed up to 1.22% and 1.06% improvement in DSC, respectively. A sensitivity analysis demonstrated that the chosen scaling range in RSS offered a favorable trade-off between deformation and anatomical plausibility. Cross-dataset evaluation on MSD Heart and Spleen tasks also indicated strong generalization. Computational analysis revealed that ES-UNet achieves superior segmentation performance with moderate computational demands. Specifically, the enhanced skip connection design with lightweight channel attention modules integrated throughout the network architecture enables this favorable balance between high segmentation accuracy and computational efficiency.</p><p><strong>Conclusion: </strong>ES-UNet integrates architectural and algorithmic improvements to achieve robust 3D medical image segmentation. While the framework incorporates established components, its core contributions lie in the optimized skip connection strategy and supporting techniques like RSS and DWD. Future work will explore adaptive scaling strategies and broader validation across diverse imaging modalities.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"327"},"PeriodicalIF":3.2,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12351991/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144844297","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":"Multimodal fusion radiomic-immunologic scoring model: accurate identification of prostate cancer progression.","authors":"Zhonglin Zhang, Huan Liu, Xiling Gu, Yang Qiu, Jiangqing Ma, Guangyong Ai, Xiaojing He","doi":"10.1186/s12880-025-01869-w","DOIUrl":"10.1186/s12880-025-01869-w","url":null,"abstract":"<p><strong>Objectives: </strong>This study aims to conceptualize, develop, and rigorously validate an innovative Radiomic-Immunologic Score (RDIS) model for accurately distinguishing prostate cancer (PCa) progression.</p><p><strong>Methods: </strong>This single-center, retrospective cohort study analyzed PCa patients diagnosed between 2019 and 2022. This study employed a comprehensive interdisciplinary approach, integrating CD3+/CD8 + T cell immunoanalysis with Multiparametric Magnetic Resonance Imaging (mpMRI) analysis, while adhering to a robust multi-phase feature selection process. This included the Akaike Information Criterion (AIC), Maximum Relevance Minimum Redundancy (mRMR), and Least Absolute Shrinkage and Selection Operator (LASSO) algorithms, validated through 10-fold cross-validation. Logistic regression models were constructed for radiomic, immunologic, and combined RDIS models, with predictive performance rigorously evaluated using Receiver Operating Characteristic (ROC) curve analysis, calibration curve assessments, and Decision Curve Analysis (DCA).</p><p><strong>Results: </strong>The RDIS model achieved an Area Under the Curve (AUC) of 0.874 in the validation cohort, outperforming traditional single-omics models, including the radiomic model (AUC: 0.844) and the immunologic model (AUC: 0.767), supporting potential use in early intervention decision-making. The correlation heatmap reveals weak to moderate correlations among 7 pairs of radiomic and immunologic features associated with PCa progression. The RDIS model demonstrates good specificity in further predicting bone metastases and castration-resistant prostate cancer (CRPC).</p><p><strong>Conclusions: </strong>The RDIS model effectively distinguished the progression status of PCa, with its multi-omics integrative attributes likely providing comprehensive insights into the factors influencing disease progression.</p><p><strong>Advances in knowledge: </strong>The immunologic and radiologic characteristics are associated with prostate cancer progression. The RDIS multi-omics integrative scoring system shows great potential in distinguishing whether prostate cancer has progressed.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"324"},"PeriodicalIF":3.2,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12341337/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144833886","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}