BMC Medical Imaging最新文献

{"title":"Anatomical features of aortic root in patients with aortic stenosis treated by TAVR: an observational study.","authors":"Yang Chen, Baihua Sun, Zhongyu Wang, Moyang Wang, Hongliang Zhang, Guannan Niu, Zhenyan Zhao, Dejing Feng, Pinghai Zhang, Zhibo Jiang, Junhua Yuan, Junxian Song, Yongjian Wu","doi":"10.1186/s12880-025-01867-y","DOIUrl":"10.1186/s12880-025-01867-y","url":null,"abstract":"<p><strong>Objective: </strong>Transcatheter aortic valve replacement (TAVR) is a well-established technique for the treatment of aortic stenosis (AS). However, due to the complex anatomical features of the aortic root, the risk of vascular injury caused by operation under the condition of anatomical variations of the aortic root is high, and there is a lack of studies on the anatomical features of the aortic root on CT before TAVR. Therefore, this study will preliminarily summarize anatomical features of aortic root in patients with aortic stenosis treated by TAVR.</p><p><strong>Methods: </strong>A retrospective study was conducted at a single center, involving 60 patients with symptomatic severe AS treated TAVR between September 2022 and December 2022. Baseline patient information, CT measurements of aortic root anatomical characteristics, and associated risks were analyzed.</p><p><strong>Results: </strong>The mean age of the 60 patients was 77.72 ± 4.33 years, with 39 males (65.00%). The left ventricular ejection fraction was 65.46 ± 13.92%. Valve morphology included 38 cases (63.30%) of tricuspid valves and 22 cases (36.70%) of bicuspid valves. Common anatomical risks identified were acute aortic arch (18.33%), a short ascending aorta (10.00%, 8.33%, 16.67%, 15.00%), ascending aortic dilation (3.33%), a transverse heart (28.33%), cardiac anteversion (68.33%), a short left ventricle (5.00%), and a small left ventricle (5.00%).</p><p><strong>Conclusion: </strong>Preoperative cardiac CT scans detect aortic root morphological angle abnormalities in TAVR patients. Angular dimensions of the aortic root show considerable variability among patients, which may have procedural implications for TAVR.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"326"},"PeriodicalIF":3.2,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12341228/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144833884","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":"Correlation between carotid artery ultrasound parameters and lacunar infarction.","authors":"Peipei Yang, Ying Hui, Shuohua Chen, Xinyu Zhao, Wei Huang, Xiaoshuai Li, Shouling Wu, Yuntao Wu, Ling Yang, Jing Chen, Zhenchang Wang, Xian-Quan Shi","doi":"10.1186/s12880-025-01859-y","DOIUrl":"10.1186/s12880-025-01859-y","url":null,"abstract":"<p><strong>Objective: </strong>This study aims to investigate the correlation between the imaging characteristics of lacunar infarction (LI) and carotid artery ultrasound parameters within a community-based population.</p><p><strong>Methods: </strong>A total of 630 participants were included to undergo brain MRI and carotid ultrasound examinations, with their demographic and clinical characteristics systematically documented. Ultrasound imaging was used to quantify the structural, hemodynamic, and stiffness parameters of the common carotid artery (CCA) and internal carotid artery (ICA). Additionally, the associations between these parameters and the imaging features of LI were comprehensively analyzed.</p><p><strong>Result: </strong>The mean age of the participants was about 55.21 ± 10.98 years, and the prevalence of LI was 13.02% (82/630). As shown by correlation analysis, all carotid artery ultrasound parameters exhibited significant correlations with LI except for ICA-PSV. Internal diameter of CCA and ICA, plaque in CCA and ICA, resistance index (RI) of CCA and ICA, pulsatility indexes (PI) of CCA and ICA, systolic/diastolic(S/D) of CCA and ICA, and carotid-femoral pulse wave velocity (cf-PWV) were positively associated with LI; peak systolic velocities (PSV) of CCA, end-diastolic velocities (EDV) of CCA and ICA, average velocity (AVG) of CCA and ICA were negatively associated with LI. Multivariate regression analysis showed that CCA-internal diameter (95%CI, 1.04-1.93; p = 0.025), CCA-plaque (bilateral) (95%CI, 1.06-4.37; p = 0.034), and cf-PWV (95%CI, 1.01-1.15; p = 0.017) were independent factors of presence of LI.</p><p><strong>Conclusion: </strong>Arterial plaque burden and stiffness-related parameters assessed through carotid artery ultrasound, such as CCA-internal diameter, CCA-plaque, and cf-PWV, show predictive value for the risk of LI.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"325"},"PeriodicalIF":3.2,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12341246/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144833885","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 preoperative lymph node metastasis in patients with high-grade serous ovarian cancer by using intratumoral and peritumoral radiomics: a retrospective cohort study.","authors":"Silin Nie, Yumin Jiang, Huixiang Ji, Xiaohui Liu, Lanxing Lyu, Chun Wang, Yuping Shan, Aiping Chen","doi":"10.1186/s12880-025-01868-x","DOIUrl":"10.1186/s12880-025-01868-x","url":null,"abstract":"<p><strong>Background: </strong>Ovarian cancer (OC) carries the worst prognosis among gynecologic cancers, with high-grade serous ovarian cancer (HGSOC) as its most common subtype. Cytoreductive surgery (tumor resection) is the cornerstone of OC treatment. However, controversy remains regarding whether lymphadenectomy should be performed during surgery; more than 30% of patients with OC undergo unnecessary lymphadenectomy, increasing surgical risks and prolonging postoperative recovery. By analyzing multidimensional imaging features, such as tumor morphology, texture, and density, radiomics can accurately quantify the biological characteristics of tumors. However, its application in OC needs to be explored further. This study aimed to explore radiomics' role in predicting lymph node metastasis risk in HGSOC.</p><p><strong>Methods: </strong>This retrospective cohort analysis involved 273 participants from Qingdao University Affiliated Hospital and Rizhao People's Hospital, and they were categorized into the training, testing, and external validation groups. Imaging characteristics were derived from the tumor region of interest and its surrounding areas (1-5 mm), and radiomics scores were calculated for each region. This approach was employed for assessing the diagnostic performance of different regions and identify the optimal one. We constructed a risk prediction model that integrated imaging features of the optimal region with independent clinical risk factors.</p><p><strong>Results: </strong>The radiomic features of the tumor and its surrounding 3-mm extension region yielded area under the curve (AUC) values of 0.957 and 0.793 in the training and testing sets, respectively. After integrating the radiomic features of the tumor and its surrounding 3-mm extension region with clinical features, the AUC values in the training set, testing set, and external validation set were 0.971, 0.811, and 0.869, respectively, demonstrating strong predictive ability.</p><p><strong>Conclusions: </strong>This study developed a model to assess lymph node metastasis likelihood in HGSOC patients. In the test and external validation cohorts, the model demonstrated excellent predictive performance. We believe the model can assist clinicians in identifying patients who are suitable for lymph node resection, thereby optimizing treatment decisions.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"323"},"PeriodicalIF":3.2,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12341290/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144833914","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":"Improvement in matching lesions in dual-view mammograms using a geometric model.","authors":"Sina Wang, Zeyuan Xu, Bowen Zheng, Hui Zeng, Derun Pan, Mengwei Ma, Weiguo Chen, Genggeng Qin","doi":"10.1186/s12880-025-01862-3","DOIUrl":"10.1186/s12880-025-01862-3","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate the effectiveness of a geometric model (GM) as an adjunctive tool for radiologists to match lesions between craniocaudal (CC) and mediolateral (MLO) views.</p><p><strong>Methods: </strong>A retrospective study was conducted on 711 patients who underwent mammography from January 2016 to August 2018. Two senior radiologists used bounding boxes to delineate lesions as the reference standard, calculated the absolute error (the shortest distance from the lesion center to the predicted curve) of GM, and compared it with the annular band (AB) and straight strip (SS) methods. Four radiologists of varying seniority levels were tasked with localizing the corresponding lesion in MLO view using a bounding box, based on the given lesion in CC views, and recording reading time per case with or without GM assistance. The Dice coefficient was used to evaluate the overlap between the bounding box and the reference standard.</p><p><strong>Results: </strong>Overall, 499 calcification and 212 mass pairs were evaluated. GM outperformed both AB and SS, yielding a median absolute error of 3.03 mm (IQR 1.45-5.55 mm) versus 5.78 mm (IQR 2.44-10.71 mm) for AB and 4.59 mm (IQR 1.91-8.19 mm) for SS (P < 0.001). With GM assistance, all four radiologists achieved improved Dice coefficients and reduced reading times (all P  < 0.001). Stratified analysis by lesion conspicuity demonstrated that GM assistance significantly enhanced Dice coefficients for all radiologists in the low-conspicuity group and improved matching consistency for junior radiologists.</p><p><strong>Conclusion: </strong>The geometric model holds substantial promise as a valuable tool to assist radiologists in more effectively localizing lesions in ipsilateral mammograms, thereby potentially enhancing diagnostic accuracy and efficiency.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"322"},"PeriodicalIF":3.2,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12337522/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144820501","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 radiomics in glioma: predicting recurrence in the peritumoural brain zone using integrated MRI.","authors":"Qian Li, Chaodong Xiang, Xianchun Zeng, Ang Liao, Kang Chen, Jing Yang, Yong Li, Min Jia, Lingheng Song, Xiaofei Hu","doi":"10.1186/s12880-025-01853-4","DOIUrl":"10.1186/s12880-025-01853-4","url":null,"abstract":"<p><strong>Background: </strong>Gliomas exhibit a high recurrence rate, particularly in the peritumoural brain zone after surgery. This study aims to develop and validate a radiomics-based model using preoperative fluid-attenuated inversion recovery (FLAIR) and T1-weighted contrast-enhanced (T1-CE) magnetic resonance imaging (MRI) sequences to predict glioma recurrence within specific quadrants of the surgical margin.</p><p><strong>Methods: </strong>In this retrospective study, 149 patients with confirmed glioma recurrence were included. 23 cases of data from Guizhou Medical University were used as a test set, and the remaining data were randomly used as a training set (70%) and a validation set (30%). Two radiologists from the research group established a Cartesian coordinate system centred on the tumour, based on FLAIR and T1-CE MRI sequences, dividing the tumour into four quadrants. Recurrence in each quadrant after surgery was assessed, categorising preoperative tumour quadrants as recurrent and non-recurrent. Following the division of tumours into quadrants and the removal of outliers, These quadrants were assigned to a training set (105 non-recurrence quadrants and 226 recurrence quadrants), a verification set (45 non-recurrence quadrants and 97 recurrence quadrants) and a test set (16 non-recurrence quadrants and 68 recurrence quadrants). Imaging features were extracted from preoperative sequences, and feature selection was performed using least absolute shrinkage and selection operator. Machine learning models included support vector machine, random forest, extra trees, and XGBoost. Clinical efficacy was evaluated through model calibration and decision curve analysis.</p><p><strong>Results: </strong>The fusion model, which combines features from FLAIR and T1-CE sequences, exhibited higher predictive accuracy than single-modality models. Among the models, the LightGBM model demonstrated the highest predictive accuracy, with an area under the curve of 0.906 in the training set, 0.832 in the validation set and 0.805 in the test set.</p><p><strong>Conclusion: </strong>The study highlights the potential of a multimodal radiomics approach for predicting glioma recurrence, with the fusion model serving as a robust tool for clinical decision-making.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"321"},"PeriodicalIF":3.2,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12337491/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144820502","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":"CT-based radiomics model for noninvasive prediction of progression-free survival in high-grade serous ovarian carcinoma: a multicenter study incorporating preoperative and postoperative clinical factors.","authors":"Xinping Yu, Zidong Zhang, Yuwei Zou, Chang Wang, Jinwen Jiao, Chengjian Wang, Haiyang Yu, Shuai Zhang","doi":"10.1186/s12880-025-01865-0","DOIUrl":"10.1186/s12880-025-01865-0","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;To investigate the potential of combining radiomics with clinicoradiological features in predicting progression-free survival (PFS) after the surgery of high-grade serous ovarian carcinoma (HGSOC).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;In this retrospective multicenter study, a total of 195 patients with pathologically confirmed HGSOC who underwent cytoreductive surgery followed by platinum-based chemotherapy were included from two institutions (train cohort, n = 134; test cohort, n = 61). From the train cohort, univariate and multivariate Cox proportional hazards regression analyses systematically evaluated associations between clinicoradiological features and PFS, culminating in a clinical prediction model for stratifying progression risk. Radiomics features were extracted and utilized to build the radiomics model through univariate Cox regression and least absolute shrinkage and selection operator Cox regression. A combined model integrating both clinicoradiological and radiomics features was subsequently developed. The concordance index (C-index) was used to assess the predictive performance of different models in 1-, 3-, and 5-year PFS evens among HGSOC patients. Model performance was assessed using time-dependent receiver operating characteristic curves, with area under the curve (AUC) values calculated at various time points. as well as calibration curves and Brier scores to evaluate prediction accuracy and model reliability. Kaplan-Meier analysis was employed to evaluate the clinical utility of each model in predicting PFS.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Five clinicoradiologicall features, including supradiaphragmatic lymphadenopathy, CA125 level, HE4 level, residual tumor status, and FIGO stage, were included in the clinical model.The combined model achieved strong predictive performance with a C-index of 0.758 (95% CI: 0.685-0.830) in the train cohort and 0.707 (95% CI: 0.593-0.821) in the test cohort, outperforming both the clinical and radiomics models independently. The combined model demonstrated superior performance for 1-year prediction, with the highest accuracy (0.822), AUC (0.864), and lowest Brier score (0.132) in the train cohort, and the highest balanced accuracy (0.806), AUC (0.787), and lowest Brier score (0.159) in the test cohort. For 3-year survival, the radiomics model showed the best performance, with a balanced accuracy of 0.760, AUC of 0.838, and Brier score of 0.168 in train cohort, and a balanced accuracy of 0.813, AUC of 0.785, and Brier score of 0.198 in test cohort. Similarly, the radiomics model overall outperformed the other models for 5-year survival, with a balanced accuracy of 0.813, AUC of 0.887, and Brier score of 0.164 in train cohort, and a balanced accuracy of 0.813, AUC of 0.767, and Brier score of 0.207 in test cohort.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusion: &lt;/strong&gt;The combined model excels in 1-year PFS prediction and overall risk stratification, while the radiomics model performs bet","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"320"},"PeriodicalIF":3.2,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12335143/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144803373","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":"Intravoxel incoherent motion and diffusion kurtosis imaging for subtype differentiation in salivary gland tumors: a diagnostic performance study.","authors":"Jinru Yu, Huimin Huang, Jiawen Gao, Han Zhang, Shuo Shao, Ning Zheng","doi":"10.1186/s12880-025-01815-w","DOIUrl":"10.1186/s12880-025-01815-w","url":null,"abstract":"","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"319"},"PeriodicalIF":3.2,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12330006/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144798107","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 MRI and CA19-9 for predicting occult lymph node metastasis in small pancreatic ductal adenocarcinoma (≤ 2 cm).","authors":"Qiying Tang, Lei Li, Zhiwei Pan, Jianbo Li, Xiaolan Huang, Mengsu Zeng, Haitao Sun, Jianjun Zhou","doi":"10.1186/s12880-025-01854-3","DOIUrl":"10.1186/s12880-025-01854-3","url":null,"abstract":"<p><strong>Aim: </strong>Accurate prediction of occult lymph node metastasis (OLNM) in small pancreatic ductal adenocarcinoma (sPDAC) (≤ 2 cm) is crucial for curative management. This study aims to explore clinical and MRI features associated with OLNM in sPDAC and their pathological and prognostic implications.</p><p><strong>Materials and methods: </strong>This retrospective study included 135 patients with pathologically confirmed sPDAC who underwent surgery between September 2014 and September 2023. Preoperative multi-sequence MRI, clinical data, and pathological features were analyzed. Univariate and multivariate logistic regression models were used to identify risk predictors of OLNM in sPDAC. Receiver operating characteristic (ROC) analysis was performed to assess diagnostic performance and Kaplan-Meier survival analysis was used to evaluate prognostic outcomes.</p><p><strong>Results: </strong>OLNM was present in 43 (31.9%) sPDAC patients. Univariate and multivariate analysis identified elevated CA19-9 (> 100 U/mL) (OR = 2.404, P = 0.040) and low apparent diffusion coefficient (ADC) values (OR = 0.243, P = 0.031) as independent predictors of OLNM. The combined clinical-radiological model demonstrated an AUC of 0.740, significantly higher than CA19-9 (AUC = 0.653, P = 0.021) or ADC alone (AUC = 0.635, P = 0.035). sPDAC patients with OLNM exhibited higher rates of lymphovascular invasion (44.2%, P = 0.013) and pathological fat invasion (86.0%, P = 0.030). OLNM was associated with significantly worse OS and DFS (P = 0.034 and 0.043).</p><p><strong>Conclusions: </strong>OLNM is associated with adverse pathological features and poorer prognosis. The combination of preoperative MRI assessment of ADC and CA19-9 may aid in identifying sPDAC patients at high risk for OLNM.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"318"},"PeriodicalIF":3.2,"publicationDate":"2025-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12326715/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144788211","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":"Enhancing pediatric distal radius fracture detection: optimizing YOLOv8 with advanced AI and machine learning techniques.","authors":"Farid Amirouche, Aashik Mathew Prosper, Majd Mzeihem","doi":"10.1186/s12880-025-01669-2","DOIUrl":"10.1186/s12880-025-01669-2","url":null,"abstract":"<p><strong>Background: </strong>In emergency departments, residents and physicians interpret X-rays to identify fractures, with distal radius fractures being the most common in children. Skilled radiologists typically ensure accurate readings in well-resourced hospitals, but rural areas often lack this expertise, leading to lower diagnostic accuracy and potential delays in treatment. Machine learning systems offer promising solutions by detecting subtle features that non-experts might miss. Recent advancements, including YOLOv8 and its attention-mechanism models, YOLOv8-AM, have shown potential in automated fracture detection. This study aims to refine the YOLOv8-AM model to improve the detection of distal radius fractures in pediatric patients by integrating targeted improvements and new attention mechanisms.</p><p><strong>Methods: </strong>We enhanced the YOLOv8-AM model to improve pediatric wrist fracture detection, maintaining the YOLOv8 backbone while integrating attention mechanisms such as the Convolutional Block Attention Module (CBAM) and the Global Context (GC) block. We optimized the model through hyperparameter tuning, implementing data cleaning, augmentation, and normalization techniques using the GRAZPEDWRI-DX dataset. This process addressed class imbalances and significantly improved model performance, with mean Average Precision (mAP) increasing from 63.6 to 66.32%.</p><p><strong>Results and discussion: </strong>The iYOLOv8 models demonstrated substantial improvements in performance metrics. The iYOLOv8 + GC model achieved the highest precision at 97.2%, with an F1-score of 67% and an mAP50 of 69.5%, requiring only 3.62 h of training time. In comparison, the iYOLOv8 + ECA model reached 96.7% precision, significantly reducing training time from 8.54 to 2.16 h. The various iYOLOv8-AM models achieved an average accuracy of 96.42% in fracture detection, although performance for detecting bone anomalies and soft tissues was lower due to dataset constraints. The improvements highlight the model's effectiveness in pathological detection of the pediatric distal radius, suggesting that integrating these AI models into clinical practice could significantly enhance diagnostic efficiency.</p><p><strong>Conclusion: </strong>Our improved YOLOv8-AM model, incorporating the GC attention mechanism, demonstrated superior speed and accuracy in pediatric distal radius fracture detection while reducing training time. Future research should explore additional features to further enhance detection capabilities in other musculoskeletal areas, as this model has the potential to adapt to various fracture types with appropriate training.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"316"},"PeriodicalIF":3.2,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12326825/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144788196","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":"Determination of redundant scan coverages along the Z-axis and dose implications for common paediatric computed tomography imaging examinations in a limited resource setting.","authors":"Rosemary Yeboah Ampofo, Kofi Adesi Kyei, Joseph Daniels, Andrew Yaw Nyantakyi","doi":"10.1186/s12880-025-01860-5","DOIUrl":"10.1186/s12880-025-01860-5","url":null,"abstract":"<p><strong>Introduction: </strong>Optimizing scan parameters, particularly along the Z-axis, is crucial for minimizing unnecessary medical radiation exposure. Understanding and mitigating redundant scan coverages is essential for enhancing the safety and efficacy of paediatric CT imaging. This study quantified redundant Z-axis scan coverage and evaluated its associated dose implications in paediatric CT examinations in a limited-resource healthcare setting.</p><p><strong>Methods: </strong>A retrospective review was conducted on 279 paediatric CT scan records from two large tertiary hospitals in Ghana. Distances above the upper target and below the lower target of selected anatomical regions were measured using calibrated callipers on the CT console. The National Cancer Institute Dosimetry System for Computed Tomography (Monte Carlo-based software) was used to simulate the scanning situations and organ-dose implications.</p><p><strong>Results: </strong>In all, 87.3% of the CT scans had redundancies ranging from 0.77 ± 0.42 to 2.34 ± 1.22 cm for head, 1.43 ± 2.36 to 5.64 ± 3.00 cm for chest and 4.86 ± 3.01 to 6.75 ± 4.28 cm for abdominopelvic CT scans. Optimizing the scan length to the appropriate anatomical boundaries reduced the total dose-length product of neonates and middle-aged children by 27.9% and 26.1% respectively for chest CT scans, and 26.2% for infants during abdominopelvic CT scans. Optimal scan length selection for chest CT examinations resulted in organ-dose reductions of 57.5%, 56.1%, 63.6% and 73.8% for the thyroid glands, heart wall, lungs and breasts respectively.</p><p><strong>Conclusion: </strong>The study demonstrates a high prevalence (87.3%) of redundant scan coverage in paediatric CT examinations, with significant variances across different body sites. Implementing optimized scan lengths could substantially reduce radiation exposure and significantly lower organ doses.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"317"},"PeriodicalIF":3.2,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12326660/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144788195","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}