BMC Medical Imaging最新文献

{"title":"CT texture analysis of pediatric teratomas-associations with identification and grading of immature teratoma.","authors":"Xinxin Qi, Xiaoyu Wang, Wen Zhao, Songyu Teng, Guanglun Zhou, Hongwu Zeng","doi":"10.1186/s12880-025-01764-4","DOIUrl":"https://doi.org/10.1186/s12880-025-01764-4","url":null,"abstract":"<p><strong>Background: </strong>Teratomas are categorized into mature teratomas (MT) and immature teratomas (IT) of grades I-III based on the content of immature tissues. The existing diagnostic methods are not comprehensive and objective enough. This study aims to utilize computed tomography texture analysis (CTTA) to exploring heterogeneity of tumor components and enhance the preoperative identification and grading of IT.</p><p><strong>Methods: </strong>Between 2019 and 2023, 52 patients with pathologically confirmed MT (n = 26) and IT (n = 26) underwent preoperative CT scans. Fat, calcification, and solid components of intratumoral components were extracted using 3D slicer. CT features including size and total volume, as well as 75 texture features were analyzed. Comparisons of these features were performed between the IT and MT groups and within the IT groups. Logistic regression models were constructed and the area under the curve (AUC) was used to evaluate the effectiveness of these models. Statistical significance was set at p < 0.05.</p><p><strong>Results: </strong>CT features showed that, IT group exhibited greater calcification size (p = 0.012), larger calcification volume (p = 0.003), and larger solid component volume (p < 0.001) than MT group. Texture features showed 22, 30, and 43 differential texture features for fat, calcification, and solid components between IT and MT group, respectively (p < 0.05). Among these, the neighborhood gray tone difference matrix busyness (NGTDM_busyness) feature for solid components was significantly higher in the IT group than in the MT group (p < 0.001) and higher in grade II than in grade I within the IT groups (p = 0.020). Logistic regression analysis indicated that IT identification efficacy of fat, calcifications, and solid components models were 0.778, 0.774, and 0.976, respectively.</p><p><strong>Conclusions: </strong>CTTA is an effective method for IT identification and grading, with NGTDM features holding unique value. Among tumor components, the solid components demonstrate excellent diagnostic value.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"256"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The value of diagnosing coronary slow flow based on epicardial adipose tissue radiomics in chest computed tomography.","authors":"Jing Tong, Libo Zhang, Guiguang Bei, Wenyuan Liu, Mingyu Zou, Yuze Li, Xiaogang Li, Yu Sun, Xinrui Wang, Jingya Zhu, Zhenguo Wang, Benqiang Yang","doi":"10.1186/s12880-025-01792-0","DOIUrl":"https://doi.org/10.1186/s12880-025-01792-0","url":null,"abstract":"<p><strong>Background: </strong>At present, the diagnosis of coronary slow flow (CSF) relies on coronary angiography, and non-invasive imaging examinations for the diagnosis of CSF have not been fully studied. This study aimed to explore the value of diagnosing CSF based on epicardial adipose tissue (EAT) radiomics in chest computed tomography (CT).</p><p><strong>Methods: </strong>This retrospective study included 211 patients who underwent coronary angiography showing coronary artery stenosis < 40% from January 2020 to December 2021 and underwent chest CT within 2 weeks before angiography. According to the thrombolysis in myocardial infarction flow grade, the patients were divided into CSF group (n = 103) and normal coronary flow group (n = 108). Establish an automatic method for segmenting EAT on chest CT images. Patients were randomly divided into a training set (n = 148) and a validation set (n = 63) at a ratio of 7:3, and then radiomics features were extracted. Features selected using the maximum relevance minimum redundancy and the least absolute shrinkage and selection operator were adopted to construct an EAT radiomics model. The diagnostic efficacy of the model for CSF was evaluated using the area under the receiver operating characteristic curve. The consistency between the model and the actual results was evaluated using calibration curves, and the clinical application value of the model was evaluated using decision curve analysis.</p><p><strong>Results: </strong>16 radiomics features were retained to establish an EAT radiomics model for diagnosing CSF. The model had an AUC of 0.81, sensitivity of 0.72, specificity of 0.79, and accuracy of 0.76 for diagnosing CSF in the training set, and an AUC of 0.77, sensitivity of 0.82, specificity of 0.71, and accuracy of 0.77 in the validation set. The calibration curves showed good consistency between the model and the actual results, while the decision analysis curves showed good overall net benefits of the model within most reasonable threshold probability ranges.</p><p><strong>Conclusions: </strong>The EAT radiomics model based on chest CT had good diagnostic efficacy for CSF and may become a potential non-invasive tool for diagnosing CSF.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"258"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ultrasound-based machine learning model to predict the risk of endometrial cancer among postmenopausal women.","authors":"Yi-Xin Li, Yu Lu, Zhe-Ming Song, Yu-Ting Shen, Wen Lu, Min Ren","doi":"10.1186/s12880-025-01705-1","DOIUrl":"https://doi.org/10.1186/s12880-025-01705-1","url":null,"abstract":"<p><strong>Background: </strong>Current ultrasound-based screening for endometrial cancer (EC) primarily relies on endometrial thickness (ET) and morphological evaluation, which suffer from low specificity and high interobserver variability. This study aimed to develop and validate an artificial intelligence (AI)-driven diagnostic model to improve diagnostic accuracy and reduce variability.</p><p><strong>Methods: </strong>A total of 1,861 consecutive postmenopausal women were enrolled from two centers between April 2021 and April 2024. Super-resolution (SR) technique was applied to enhance image quality before feature extraction. Radiomics features were extracted using Pyradiomics, and deep learning features were derived from convolutional neural network (CNN). Three models were developed: (1) R model: radiomics-based machine learning (ML) algorithms; (2) CNN model: image-based CNN algorithms; (3) DLR model: a hybrid model combining radiomics and deep learning features with ML algorithms.</p><p><strong>Results: </strong>Using endometrium-level regions of interest (ROI), the DLR model achieved the best diagnostic performance, with an area under the receiver operating characteristic curve (AUROC) of 0.893 (95% CI: 0.847-0.932), sensitivity of 0.847 (95% CI: 0.692-0.944), and specificity of 0.810 (95% CI: 0.717-0.910) in the internal testing dataset. Consistent performance was observed in the external testing dataset (AUROC 0.871, sensitivity 0.792, specificity 0.829). The DLR model consistently outperformed both the R and CNN models. Moreover, endometrium-level ROIs yielded better results than uterine-corpus-level ROIs.</p><p><strong>Conclusions: </strong>This study demonstrates the feasibility and clinical value of AI-enhanced ultrasound analysis for EC detection. By integrating radiomics and deep learning features with SR-based image preprocessing, our model improves diagnostic specificity, reduces false positives, and mitigates operator-dependent variability. This non-invasive approach offers a more accurate and reliable tool for EC screening in postmenopausal women.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"244"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated pancreatic extracellular volume fraction as a biomarker for microangiopathy in type 2 diabetes mellitus.","authors":"Jiayu Wan, Dan Zhao, Xue Lin, Peng Sun, Shen Gui, Weiwei Liu, Lian Yang, Feng Pan","doi":"10.1186/s12880-025-01731-z","DOIUrl":"https://doi.org/10.1186/s12880-025-01731-z","url":null,"abstract":"<p><strong>Objective: </strong>To develop noninvasive, opportunistic screening methods using routine abdominal enhanced CT imaging to derive an automated pancreatic extracellular volume fraction (AP-ECV) as a novel biomarker for evaluating microangiopathy in type 2 diabetes mellitus (T2DM).</p><p><strong>Methods: </strong>A retrospective study was conducted on 320 patients with T2DM who underwent routine enhanced abdominal CT examinations. Microangiopathy refers to retinopathy, nephropathy or peripheral neuropathy in patients with diabetes. An automated method was developed to calculate AP-ECV values from enhanced abdominal CT images. The association between AP-ECV and T2DM microangiopathy was evaluated using univariate and multivariate logistic regression analyses. Then, assess the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) for AP-ECV's diagnostic ability in T2DM microangiopathy. Ordinal logistic regression estimated risk factors associated with the severities of microangiopathy, categorized into three levels.</p><p><strong>Results: </strong>AP-ECV and T2DM duration significantly increased in T2DM patients with microangiopathy (p < 0.01). The AUC for AP-ECV and T2DM duration were 0.767 and 0.761, respectively, with a combined AUC of 0.881. As AP-ECV increased (OR 1.406) and T2DM duration lengthened (OR 1.163), microangiopathy severity significantly escalated.</p><p><strong>Conclusion: </strong>AP-ECV is a potential imaging biomarker for T2DM microangiopathy, offering a valuable noninvasive diagnostic tool benefitting early management in T2DM patients.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"226"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Glymphatic and neurofluidic dysfunction in classical trigeminal neuralgia: a multimodal MRI study of brain-CSF functional and structural dynamics.","authors":"Fenyang Chen, Zhiliang Zhang, Jianliang Miao, Yvting Zhang, Ding Wang, Juncheng Yan, Lei Pan, Haiqi Ye, Zhongxiang Ding, Xiuhong Ge","doi":"10.1186/s12880-025-01801-2","DOIUrl":"https://doi.org/10.1186/s12880-025-01801-2","url":null,"abstract":"<p><strong>Objective: </strong>To investigate whether dysfunction of the glymphatic system and altered neurofluidic dynamics contribute to the pathophysiology of classical trigeminal neuralgia (CTN), and to explore the potential interplay between brain-CSF coupling and structural brain changes.</p><p><strong>Methods: </strong>A total of 131 patients with CTN and 106 age- and sex-matched healthy controls were recruited. All participants underwent multimodal MRI, including high-resolution structural imaging, resting-state functional MRI, and diffusion tensor imaging. Key indices included choroid plexus (CP) volume as a proxy for CSF production, global BOLD-CSF coupling as a measure of functional neurofluidic interaction, and the DTI-based ALPS index reflecting glymphatic clearance. Additional markers included peak width of skeletonized mean diffusivity (PSMD) and global gray/white matter and CSF volume. Partial correlation analyses were performed between imaging metrics and clinical assessments.</p><p><strong>Results: </strong>CTN patients showed significantly increased CP volume (P = 0.022) and gBOLD-CSF coupling (P < 0.001), along with reduced bilateral ALPS indices (P = 0.002, P = 0.004). PSMD and CSF volume were elevated (P < 0.001, P < 0.001), while gray and white matter volumes were reduced (P = 0.028, P = 0.009). gBOLD-CSF coupling correlated positively with depression, anxiety, and pain-related disability scores (P < 0.001), and negatively with MMSE (P = 0.022).</p><p><strong>Conclusion: </strong>This study provides multimodal MRI evidence of glymphatic dysfunction and neurofluidic alterations in CTN, supporting a conceptual framework in which disrupted brain-CSF interaction may influence peripheral sensory modulation through a putative brain-CSF-ganglion pathway. These results may inform mechanistic hypotheses and guide future research on the neurofluidic underpinnings of neuropathic pain, potentially providing new insights into the pathogenesis of CTN.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"222"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development and validation of CT-based fusion model for preoperative prediction of invasion and lymph node metastasis in adenocarcinoma of esophagogastric junction.","authors":"Mengxuan Cao, Ruixin Xu, Yi You, Chencui Huang, Yahan Tong, Ruolan Zhang, Yanqiang Zhang, Pengcheng Yu, Yi Wang, Wujie Chen, Xiangdong Cheng, Lei Zhang","doi":"10.1186/s12880-025-01777-z","DOIUrl":"https://doi.org/10.1186/s12880-025-01777-z","url":null,"abstract":"<p><strong>Purpose: </strong>In the context of precision medicine, radiomics has become a key technology in solving medical problems. For adenocarcinoma of esophagogastric junction (AEG), developing a preoperative CT-based prediction model for AEG invasion and lymph node metastasis is crucial.</p><p><strong>Methods: </strong>We retrospectively collected 256 patients with AEG from two centres. The radiomics features were extracted from the preoperative diagnostic CT images, and the feature selection method and machine learning method were applied to reduce the feature size and establish the predictive imaging features. By comparing the three machine learning methods, the best radiomics nomogram was selected, and the average AUC was obtained by 20 repeats of fivefold cross-validation for comparison. The fusion model was constructed by logistic regression combined with clinical factors. On this basis, ROC curve, calibration curve and decision curve of the fusion model are constructed.</p><p><strong>Results: </strong>The predictive efficacy of fusion model for tumour invasion depth was higher than that of radiomics nomogram, with an AUC of 0.764 vs. 0.706 in the test set, P < 0.001, internal validation set 0.752 vs. 0.697, P < 0.001, and external validation set 0.756 vs. 0.687, P < 0.001, respectively. The predictive efficacy of the lymph node metastasis fusion model was higher than that of the radiomics nomogram, with an AUC of 0.809 vs. 0.732 in the test set, P < 0.001, internal validation set 0.841 vs. 0.718, P < 0.001, and external validation set 0.801 vs. 0.680, P < 0.001, respectively.</p><p><strong>Conclusion: </strong>We have developed a fusion model combining radiomics and clinical risk factors, which is crucial for the accurate preoperative diagnosis and treatment of AEG, advancing precision medicine. It may also spark discussions on the imaging feature differences between AEG and GC (Gastric cancer).</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"242"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced pulmonary nodule detection with U-Net, YOLOv8, and swin transformer.","authors":"Xing Wang, Houde Wu, Longshuang Wang, Jingxu Chen, Yi Li, Xinliu He, Ting Chen, Minghui Wang, Li Guo","doi":"10.1186/s12880-025-01784-0","DOIUrl":"https://doi.org/10.1186/s12880-025-01784-0","url":null,"abstract":"<p><strong>Rationale and objectives: </strong>Lung cancer remains the leading cause of cancer-related mortality worldwide, emphasizing the critical need for early pulmonary nodule detection to improve patient outcomes. Current methods encounter challenges in detecting small nodules and exhibit high false positive rates, placing an additional diagnostic burden on radiologists. This study aimed to develop a two-stage deep learning model integrating U-Net, Yolov8s, and the Swin transformer to enhance pulmonary nodule detection in computer tomography (CT) images, particularly for small nodules, with the goal of improving detection accuracy and reducing false positives.</p><p><strong>Materials and methods: </strong>We utilized the LUNA16 dataset (888 CT scans) and an additional 308 CT scans from Tianjin Chest Hospital. Images were preprocessed for consistency. The proposed model first employs U-Net for precise lung segmentation, followed by Yolov8s augmented with the Swin transformer for nodule detection. The Shape-aware IoU (SIoU) loss function was implemented to improve bounding box predictions.</p><p><strong>Results: </strong>For the LUNA16 dataset, the model achieved a precision of 0.898, a recall of 0.851, and a mean average precision at 50% IoU (mAP50) of 0.879, outperforming state-of-the-art models. The Tianjin Chest Hospital dataset has a precision of 0.855, a recall of 0.872, and an mAP50 of 0.862.</p><p><strong>Conclusion: </strong>This study presents a two-stage deep learning model that leverages U-Net, Yolov8s, and the Swin transformer for enhanced pulmonary nodule detection in CT images. The model demonstrates high accuracy and a reduced false positive rate, suggesting its potential as a useful tool for early lung cancer diagnosis and treatment.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"247"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Usefulness of the internal-to-external circle area ratio in contrast-enhanced CT to differentiate small (< 3 cm) fat-poor angiomyolipoma from renal cell carcinoma.","authors":"Xinhong Song, Wenjie Zhang, Xinyan Li, Dandan Sun, Qianqian Zhang, Heng Ma, Jianyi Qu, Xiaofei Wang","doi":"10.1186/s12880-025-01758-2","DOIUrl":"https://doi.org/10.1186/s12880-025-01758-2","url":null,"abstract":"<p><strong>Background: </strong>This study aimed to assess the use of morphological parameters, including the internal-to-external circle area ratio (IECR), in contrast-enhanced CT to distinguish small (< 3 cm) fat-poor angiomyolipoma (AML) from renal cell carcinoma (RCC).</p><p><strong>Methods: </strong>A total of 212 tumors (35 fat-poor AMLs and 177 RCCs) in the initial cohort were retrospectively evaluated using contrast-enhanced CT. Morphological characteristics (angular interface sign [AIS] score, overflowing beer sign [OBS] score, tumor diameter, circularity index, and IECR) were compared between RCC and fat-poor AML. The diagnostic performance of the significant parameters was evaluated via the area under the receiver operating characteristic curve (AUC) and compared via the DeLong test. Logistic regression was used to determine the main factors for distinguishing fat-poor AML from RCC. Three prediction models were constructed and evaluated: one omitting circularity index and IECR, one incorporating circularity index, and one incorporating IECR. The effectiveness of the prediction models was then confirmed through a validation cohort (19 fat-poor AMLs and 99 RCCs).</p><p><strong>Results: </strong>There were significant differences between RCC and fat-poor AML in both sex (P < 0.001) and all morphological parameters, including AIS score (P = 0.003), OBS score (P < 0.001), any sign for AML (P < 0.001), tumor diameter (P = 0.008), circularity index (P < 0.001), and IECR (P < 0.001), with AUC values ranging from 0.619 to 0.899. The diagnostic performance of IECR (AUC, 0.899) was significantly better than that of other parameters (Z range, 2.128-8.582; all P < 0.05). To distinguish fat-poor AML from RCC, the AUC values of the prediction model omitting circularity index and IECR, prediction model incorporating circularity index, and prediction model incorporating IECR were 0.873, 0.921, and 0.951 in the initial cohort, as well as 0.867, 0.891, and 0.933 in the validation cohort, respectively. The prediction model that used the IECR outperformed the models without the IECR.</p><p><strong>Conclusions: </strong>The IECR can be used as a simple and practical quantitative morphological factor to distinguish fat-poor AML from RCC. Adding IECR can increase the diagnostic performance of prediction models on the basis of morphological characteristics in the differential diagnosis of fat-poor AML and RCC.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"236"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A nomogram based on multiparametric magnetic resonance imaging radiomics for prediction of acute pancreatitis activity.","authors":"Ting-Ting Liu, You-Qiang Hu, Ning-Jun Yu, Xue-Ying Zhang, Dong-Lin Jiang, Jiang Luo, Yong Chen, Di Tao, Xing-Hui Li, Xiao-Ming Zhang","doi":"10.1186/s12880-025-01778-y","DOIUrl":"https://doi.org/10.1186/s12880-025-01778-y","url":null,"abstract":"<p><strong>Purpose: </strong>In acute pancreatitis (AP), disease activity is defined as the reversible manifestation of the disease. The aim of this study was to develop a nomogram for predicting disease activity in AP based on multiparametric magnetic resonance imaging (MRI) radiomics.</p><p><strong>Methods: </strong>This retrospective study included 310 patients with first-episode AP from two medical centers in China. Patients from the first medical center were randomly divided into a training cohort (n = 122) and an internal validation cohort (n = 123) in a 5:5 ratio. Patients from the second medical center were used as the external independent validation cohort (n = 65). Radiomics features were extracted from multiparametric MRI images based on pancreatic parenchymal regions. The least absolute shrinkage and selection operator (LASSO) was used for feature screening, logistic regression was used to establish radiomic feature, and statistically significant laboratory parameters were incorporated to construct the nomogram. The area under the receiver operator characteristic curve assessed the predictive performance of the nomogram. Furthermore, decision curve analysis (DCA) was used to assess the clinical utility of the nomogram, and the disease activity was validated against follow-up clinical outcomes (e.g., organ failure progression, ICU admission) and imaging-confirmed changes within one-week after MRI.</p><p><strong>Results: </strong>The AUCs of the radiomic signature were 0.808 (training cohort), 0.789 (internal validation cohort), and 0.783 (external validation cohort). Radiomic signature, extrapancreatic inflammation on MRI (EPIM) scores, and WBC count were identified as independent risk factors for the activity of AP and were therefore included in the nomogram. The AUC of the nomogram were 0.881 (training cohort), 0.922 (internal validation cohort) and 0.912 (external validation cohort). Additionally, the nomogram model obtained the greatest net benefit, according to the results of decision curves Based on the follow-up results, we also found that AP patients with higher disease activity were more likely to experience exacerbations.</p><p><strong>Conclusions: </strong>This nomogram can accurately predict the activity of AP patients, thus providing objective monitoring of the patient's course and potentially improving patient prognosis.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"241"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated 3D segmentation of the hyoid bone in CBCT using nnU-Net v2: a retrospective study on model performance and potential clinical utility.","authors":"Ismail Gümüssoy, Emre Haylaz, Suayip Burak Duman, Fahrettin Kalabalik, Seyda Say, Ozer Celik, Ibrahim Sevki Bayrakdar","doi":"10.1186/s12880-025-01797-9","DOIUrl":"https://doi.org/10.1186/s12880-025-01797-9","url":null,"abstract":"<p><strong>Objective: </strong>This study aimed to identify the hyoid bone (HB) using the nnU-Net based artificial intelligence (AI) model in cone beam computed tomography (CBCT) images and assess the model's success in automatic segmentation.</p><p><strong>Methods: </strong>CBCT images of 190 patients were randomly selected. The raw data was converted to DICOM format and transferred to the 3D Slicer Imaging Software (Version 4.10.2; MIT, Cambridge, MA, USA). HB was labeled manually using the 3D Slicer. The dataset was divided into training, validation, and test sets in a ratio of 8:1:1. The nnU-Net v2 architecture was utilized to process the training and test datasets, generating the algorithm weight factors. To assess the model's accuracy and performance, a confusion matrix was employed. F1-score, Dice coefficient (DC), 95% Hausdorff distance (95% HD), and Intersection over Union (IoU) metrics were calculated to evaluate the results.</p><p><strong>Results: </strong>The model's performance metrics were as follows: DC = 0.9434, IoU = 0.8941, F1-score = 0.9446, and 95% HD = 1.9998. The receiver operating characteristic (ROC) curve was generated, yielding an AUC value of 0.98.</p><p><strong>Conclusion: </strong>The results indicated that the nnU-Net v2 model achieved high precision and accuracy in HB segmentation on CBCT images. Automatic segmentation of HB can enhance clinicians' decision-making speed and accuracy in diagnosing and treating various clinical conditions.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"217"},"PeriodicalIF":2.9,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144538220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}