BMC Medical Imaging最新文献

{"title":"Research on ischemic stroke risk assessment based on CTA radiomics and machine learning.","authors":"Zhi-Li Li, Hong-Yu Yang, Xiao-Xiao Lv, Ya-Kun Zhang, Xin-Yu Zhu, Yu-Rou Zhang, Li Guo","doi":"10.1186/s12880-025-01697-y","DOIUrl":"10.1186/s12880-025-01697-y","url":null,"abstract":"<p><strong>Background: </strong>The study explores the value of a model constructed by integrating CTA-based carotid plaque radiomic features, clinical risk factors, and plaque imaging characteristics for prognosticating the risk of ischemic stroke.</p><p><strong>Methods: </strong>Data from 123 patients with carotid atherosclerosis were analyzed and divided into stroke and asymptomatic groups based on DWI findings. Clinical information was collected, and plaque imaging characteristics were assessed to construct a traditional model. Radiomic features of carotid plaques were extracted using 3D-Slicer software to build a radiomics model. Logistic regression was applied in the training set to establish the traditional model, the radiomics model, and a combined model, which were then tested in the validation set. The prognostic ability of the three models for ischemic stroke was evaluated using ROC curves, while calibration curves, decision curve analysis, and clinical impact curves were used to assess the clinical utility of the models. Differences in AUC values between models were compared using the DeLong test.</p><p><strong>Results: </strong>Hypertension, diabetes, elevated homocysteine (Hcy) concentrations, and plaque burden are independent risk factors for ischemic stroke and were used to establish the traditional model. Through Lasso regression, nine optimal features were selected to construct the radiomics model. ROC curve analysis showed that the AUC values of the three Logistic regression models were 0.766, 0.766, and 0.878 in the training set, and 0.798, 0.801, and 0.847 in the validation set. Calibration curves and decision curve analysis showed that the radiomics model and the combined model had higher accuracy and better fit in prognosticating the risk of ischemic stroke.</p><p><strong>Conclusions: </strong>The radiomics model is slightly better than the traditional model in evaluating the risk of ischemic stroke, while the combined model has the best prognostic performance.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"206"},"PeriodicalIF":2.9,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12142908/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144233099","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-based radiomics model for predicting station 4 lymph node metastasis in non-small cell lung cancer.","authors":"Yanru Kang, Mei Li, Xizi Xing, Kaixuan Qian, Hongxia Liu, Yafei Qi, Yanguo Liu, Yi Cui, Hua Zhang","doi":"10.1186/s12880-025-01686-1","DOIUrl":"https://doi.org/10.1186/s12880-025-01686-1","url":null,"abstract":"<p><strong>Background: </strong>This study aimed to develop and validate machine learning models for preoperative identification of metastasis to station 4 mediastinal lymph nodes (MLNM) in non-small cell lung cancer (NSCLC) patients at pathological N0-N2 (pN0-pN2) stage, thereby enhancing the precision of clinical decision-making.</p><p><strong>Methods: </strong>We included a total of 356 NSCLC patients at pN0-pN2 stage, divided into training (n = 207), internal test (n = 90), and independent test (n = 59) sets. Station 4 mediastinal lymph nodes (LNs) regions of interest (ROIs) were semi-automatically segmented on venous-phase computed tomography (CT) images for radiomics feature extraction. Using least absolute shrinkage and selection operator (LASSO) regression to select features with non-zero coefficients. Four machine learning algorithms-decision tree (DT), logistic regression (LR), random forest (RF), and support vector machine (SVM)-were employed to construct radiomics models. Clinical predictors were identified through univariate and multivariate logistic regression, which were subsequently integrated with radiomics features to develop combined models. Models performance were evaluated using receiver operating characteristic (ROC) analysis, calibration curves, decision curve analysis (DCA), and DeLong's test.</p><p><strong>Results: </strong>Out of 1721 radiomics features, eight radiomics features were selected using LASSO regression. The RF-based combined model exhibited the strongest discriminative power, with an area under the curve (AUC) of 0.934 for the training set and 0.889 for the internal test set. The calibration curve and DCA further indicated the superior performance of the combined model based on RF. The independent test set further verified the model's robustness.</p><p><strong>Conclusions: </strong>The combined model based on RF, integrating radiomics and clinical features, effectively and non-invasively identifies metastasis to the station 4 mediastinal LNs in NSCLC patients at pN0-pN2 stage. This model serves as an effective auxiliary tool for clinical decision-making and has the potential to optimize treatment strategies and improve prognostic assessment for pN0-pN2 patients.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"202"},"PeriodicalIF":2.9,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144224152","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":"Multimodality comparison of aorta morphology in patients with aortopathy: 4D flow CMR, CTA, mDIXON.","authors":"Bastiaan J C Te Kiefte, Faeze Gholamiankhah, Joe F Juffermans, Pieter Van Den Boogaard, Arthur J H A Scholte, Hildo J Lamb, Jos J M Westenberg","doi":"10.1186/s12880-025-01734-w","DOIUrl":"10.1186/s12880-025-01734-w","url":null,"abstract":"<p><strong>Background: </strong>Four-dimensional cardiovascular magnetic resonance flow imaging (4D flow CMR) enables analysing of aortic blood flow dynamics. In order to examine the relationship between morphology and hemodynamics, additional anatomical imaging is required. This study aims to assess if 4D flow CMR segmentations can be used to determine morphological parameters by comparing with segmentations from Computed Tomography Angiography (CTA) and mDIXON CMR.</p><p><strong>Methods: </strong>This study included 18 patients with various aortic pathologies who underwent CTA and CMR (including mDIXON and 4D flow CMR sequences) of the thoracic aorta. The aortic lumen was segmented from aortic valve to the descending aorta and divided into four anatomical segments: aortic root [AoR], ascending aorta [AAo], aortic arch [AA], and descending aorta [DA]. We compared morphological parameters (maximum diameter, volume, and centreline length) using these different scanning techniques. Segmentations were performed at different cardiac phases: peak systole for CTA and 4D flow CMR, and end-diastole for mDIXON.</p><p><strong>Results: </strong>Intraclass Correlation Coefficients (ICCs) and Bland-Altman plots were determined for all modalities and all segments. Agreement between 4D flow CMR and CTA was good to very good for maximum diameter (ICC 0.70-0.85) and centreline length (ICC 0.74-0.90), and very good to excellent for volume (ICC 0.89-0.97). Between mDIXON and CTA very good for maximum diameter (0.89-0.94), good to very good for centreline length (0.78-0.88), and very good to excellent for volume (0.87-0.96). Similar results were found when comparing 4D flow CMR with mDIXON with ICCs for maximum diameter (0.68-0.84), volume (0.91-0.97), and centreline length (0.78-0.90). Statistically significant differences were observed only for maximum diameter in AAo between CTA and mDIXON (p < 0.001), and for volume in AA between CTA and 4D flow CMR (p < 0.001). No significant differences were observed for other segments and parameters.</p><p><strong>Conclusions: </strong>Morphologic parameters derived from 4D flow CMR segmentations of the thoracic aorta demonstrate high levels of agreement when compared to segmentations based on CTA and mDIXON, in this relatively small cohort of patients with diverse aortic pathologies. This finding could be of interest for future 4D flow CMR research, as it possibly allows for the evaluation of both morphology and hemodynamics in a single imaging acquisition. Further research in larger cohorts is needed to robustly validate 4D flow CMR as a single-modality imaging technique.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"201"},"PeriodicalIF":2.9,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12135574/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144214833","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":"Deep learning reconstruction improves computer-aided pulmonary nodule detection and measurement accuracy for ultra-low-dose chest CT.","authors":"Jinhua Wang, Zhenchen Zhu, Zhengsong Pan, Weixiong Tan, Wei Han, Zhen Zhou, Ge Hu, Zhuangfei Ma, Yinghao Xu, Zhoumeng Ying, Xin Sui, Zhengyu Jin, Lan Song, Wei Song","doi":"10.1186/s12880-025-01746-6","DOIUrl":"10.1186/s12880-025-01746-6","url":null,"abstract":"<p><strong>Purpose: </strong>To compare the image quality and pulmonary nodule detectability and measurement accuracy between deep learning reconstruction (DLR) and hybrid iterative reconstruction (HIR) of chest ultra-low-dose CT (ULDCT).</p><p><strong>Materials and methods: </strong>Participants who underwent chest standard-dose CT (SDCT) followed by ULDCT from October 2020 to January 2022 were prospectively included. ULDCT images reconstructed with HIR and DLR were compared with SDCT images to evaluate image quality, nodule detection rate, and measurement accuracy using a commercially available deep learning-based nodule evaluation system. Wilcoxon signed-rank test was used to evaluate the percentage errors of nodule size and nodule volume between HIR and DLR images.</p><p><strong>Results: </strong>Eighty-four participants (54 ± 13 years; 26 men) were finally enrolled. The effective radiation doses of ULDCT and SDCT were 0.16 ± 0.02 mSv and 1.77 ± 0.67 mSv, respectively (P < 0.001). The mean ± standard deviation of the lung tissue noises was 61.4 ± 3.0 HU for SDCT, 61.5 ± 2.8 HU and 55.1 ± 3.4 HU for ULDCT reconstructed with HIR-Strong setting (HIR-Str) and DLR-Strong setting (DLR-Str), respectively (P < 0.001). A total of 535 nodules were detected. The nodule detection rates of ULDCT HIR-Str and ULDCT DLR-Str were 74.0% and 83.4%, respectively (P < 0.001). The absolute percentage error in nodule volume from that of SDCT was 19.5% in ULDCT HIR-Str versus 17.9% in ULDCT DLR-Str (P < 0.001).</p><p><strong>Conclusion: </strong>Compared with HIR, DLR reduced image noise, increased nodule detection rate, and improved measurement accuracy of nodule volume at chest ULDCT.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"200"},"PeriodicalIF":2.9,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12125719/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144186451","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 differentiation of upper urinary tract urothelial and renal cell carcinoma in preoperative computed tomography datasets.","authors":"Julian Marcon, Philipp Weinhold, Mona Rzany, Matthias P Fabritius, Michael Winkelmann, Alexander Buchner, Lennert Eismann, Jan-Friedrich Jokisch, Jozefina Casuscelli, Gerald B Schulz, Thomas Knösel, Michael Ingrisch, Jens Ricke, Christian G Stief, Severin Rodler, Philipp M Kazmierczak","doi":"10.1186/s12880-025-01727-9","DOIUrl":"10.1186/s12880-025-01727-9","url":null,"abstract":"<p><strong>Background: </strong>To investigate a non-invasive radiomics-based machine learning algorithm to differentiate upper urinary tract urothelial carcinoma (UTUC) from renal cell carcinoma (RCC) prior to surgical intervention.</p><p><strong>Methods: </strong>Preoperative computed tomography venous-phase datasets from patients that underwent procedures for histopathologically confirmed UTUC or RCC were retrospectively analyzed. Tumor segmentation was performed manually, and radiomic features were extracted according to the International Image Biomarker Standardization Initiative. Features were normalized using z-scores, and a predictive model was developed using the least absolute shrinkage and selection operator (LASSO). The dataset was split into a training cohort (70%) and a test cohort (30%).</p><p><strong>Results: </strong>A total of 236 patients [30.5% female, median age 70.5 years (IQR: 59.5-77), median tumor size 5.8 cm (range: 4.1-8.2 cm)] were included. For differentiating UTUC from RCC, the model achieved a sensitivity of 88.4% and specificity of 81% (AUC: 0.93, radiomics score cutoff: 0.467) in the training cohort. In the validation cohort, the sensitivity was 80.6% and specificity 80% (AUC: 0.87, radiomics score cutoff: 0.601). Subgroup analysis of the validation cohort demonstrated robust performance, particularly in distinguishing clear cell RCC from high-grade UTUC (sensitivity: 84%, specificity: 73.1%, AUC: 0.84) and high-grade from low-grade UTUC (sensitivity: 57.7%, specificity: 88.9%, AUC: 0.68). Limitations include the need for independent validation in future randomized controlled trials (RCTs).</p><p><strong>Conclusions: </strong>Machine learning-based radiomics models can reliably differentiate between RCC and UTUC in preoperative CT imaging. With a suggested performance benefit compared to conventional imaging, this technology might be added to the current preoperative diagnostic workflow.</p><p><strong>Clinical trial number: </strong>Local ethics committee no. 20-179.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"196"},"PeriodicalIF":2.9,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12123764/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144186455","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":"Multi-spatial-attention U-Net: a novel framework for automated gallbladder segmentation on CT images.","authors":"Henan Lou, Xiaobo Wen, Fanxia Lin, Zhan Peng, Qiuxiao Wang, Ruimei Ren, Junlin Xu, Jinfei Fan, Hao Song, Xiaomeng Ji, Huiyu Wang, Xiangyin Sun, Yinying Dong","doi":"10.1186/s12880-025-01737-7","DOIUrl":"10.1186/s12880-025-01737-7","url":null,"abstract":"<p><strong>Objective: </strong>This study aimed to construct a novel model, Multi-Spatial Attention U-Net (MSAU-Net) by incorporating our proposed Multi-Spatial Attention (MSA) block into the U-Net for the automated segmentation of the gallbladder on CT images.</p><p><strong>Methods: </strong>The gallbladder dataset consists of CT images of retrospectively-collected 152 liver cancer patients and corresponding ground truth delineated by experienced physicians. Our proposed MSAU-Net model was transformed into two versions V1(with one Multi-Scale Feature Extraction and Fusion (MSFEF) module in each MSA block) and V2 (with two parallel MSEFE modules in each MSA blcok). The performances of V1 and V2 were evaluated and compared with four other derivatives of U-Net or state-of-the-art models quantitatively using seven commonly-used metrics, and qualitatively by comparison against experienced physicians' assessment.</p><p><strong>Results: </strong>MSAU-Net V1 and V2 models both outperformed the comparative models across most quantitative metrics with better segmentation accuracy and boundary delineation. The optimal number of MSA was three for V1 and two for V2. Qualitative evaluations confirmed that they produced results closer to physicians' annotations. External validation revealed that MSAU-Net V2 exhibited better generalization capability.</p><p><strong>Conclusion: </strong>The MSAU-Net V1 and V2 both exhibited outstanding performance in gallbladder segmentation, demonstrating strong potential for clinical application. The MSA block enhances spatial information capture, improving the model's ability to segment small and complex structures with greater precision. These advantages position the MSAU-Net V1 and V2 as valuable tools for broader clinical adoption.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"197"},"PeriodicalIF":2.9,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12125801/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144186454","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":"Impact of arm position on low dose dual-source CT one-step aortic and cerebral-carotid artery angiography image quality and radiation dose.","authors":"Meng Wang, Chao Zheng, Lin Yang, Juan Su, Jiexin Sheng, Xiaolong He, Bo Wang, GuangHang Wu","doi":"10.1186/s12880-025-01742-w","DOIUrl":"10.1186/s12880-025-01742-w","url":null,"abstract":"<p><strong>Background: </strong>Although one-stop cerebral carotid aortic CTA is useful for diagnosing and treating type A aortic dissection, the radiation dose is increased due to the wider scanning range. The impact of varying arm positions on radiation dose and image quality is unknown when optimizing the scan protocol. This study aims to determine the best scanning protocol to minimize radiation dose while maintaining image quality, as well as how arm position impacts radiation dose and image quality of low dose one-stop cerebral carotid aortic CTA.</p><p><strong>Methods: </strong>Between January 2022 and August 2023,a total of 185 patients were enrolled in the study and underwent low-dose one-stop cerebral carotid aortic CTA. Two groups were randomly assigned to the patients: Rising arm group (group A) and drooping arm group (group B). Two radiologists assessed the subjective image quality using a 5-point scale, and kappa test was performed to evaluate the consistency between observers. Regions of interest (ROI) were set up in target vessels, and the objective image quality was evaluated by attenuation, noise, signal to noise ratio (SNR) and contrast to noise ratio (CNR). Tube current, volumetric CT dose index (CTDIvol) and dose length product (DLP) and the effective radiation dose (E) were compared between the two groups. The comparison was performed using t test.</p><p><strong>Results: </strong>Subjective image quality of group B was significantly higher than group A (p < 0.05), and the patient characteristics of the two groups did not differ significantly (P > 0.05). The consistency between observers (κ = 0.84 for group A and κ = 0.89 for group B) were excellent. Group B showed lower overall noise level, higher SNR, CNR, and higher vascular attenuation level than group A. Furthermore, group B showed reduced DLP, E, tube current, and CTDIvol, and higher aortic noise and decreased cerebral and carotid vascular noise (all p < 0.05).</p><p><strong>Conclusion: </strong>Low-dose dual-source one-stop cerebral carotid aortic CTA radiation dose can be minimized and image quality can be improved by positioning both arms on the body side.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"198"},"PeriodicalIF":2.9,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12125744/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144186453","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":"Imaging-based machine learning to evaluate the severity of ischemic stroke in the middle cerebral artery territory.","authors":"Gang Xie, Jin Gao, Jian Liu, Xuwei Zhou, Zhengkai Zhao, Wuli Tang, Yue Zhang, Lingfeng Zhang, Kang Li","doi":"10.1186/s12880-025-01745-7","DOIUrl":"10.1186/s12880-025-01745-7","url":null,"abstract":"<p><strong>Objectives: </strong>This study aims to develop an imaging-based machine learning model for evaluating the severity of ischemic stroke in the middle cerebral artery (MCA) territory.</p><p><strong>Methods: </strong>This retrospective study included 173 patients diagnosed with acute ischemic stroke (AIS) in the MCA territory from two centers, with 114 in the training set and 59 in the test set. In the training set, spearman correlation coefficient and multiple linear regression were utilized to analyze the correlation between the CT imaging features of patients prior to treatment and the national institutes of health stroke scale (NIHSS) score. Subsequently, an optimal machine learning algorithm was determined by comparing seven different algorithms. This algorithm was then used to construct a imaging-based prediction model for stroke severity (severe and non-severe). Finally, the model was validated in the test set.</p><p><strong>Results: </strong>After conducting correlation analysis, CT imaging features such as infarction side, basal ganglia area involvement, dense MCA sign, and infarction volume were found to be independently associated with NIHSS score (P < 0.05). The Logistic Regression algorithm was determined to be the optimal method for constructing the prediction model for stroke severity. The area under the receiver operating characteristic curve of the model in both the training set and test set were 0.815 (95% CI: 0.736-0.893) and 0.780 (95% CI: 0.646-0.914), respectively, with accuracies of 0.772 and 0.814.</p><p><strong>Conclusion: </strong>Imaging-based machine learning model can effectively evaluate the severity (severe or non-severe) of ischemic stroke in the MCA territory.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"199"},"PeriodicalIF":2.9,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12125870/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144186452","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":"Assessment of the association between C2 vertebral morphology and facial asymmetry using CBCT and panoramic radiography.","authors":"Çağan Erkman Şaylan, Mehmet Birol Özel, Alican Kuran, Enver Alper Sinanoğlu","doi":"10.1186/s12880-025-01744-8","DOIUrl":"10.1186/s12880-025-01744-8","url":null,"abstract":"<p><strong>Purpose: </strong>To investigate the relationship between the morphology of the Axis (C2 vertebra) and facial asymmetry using cone-beam computed tomography (CBCT) and panoramic radiographs.</p><p><strong>Materials and methods: </strong>A retrospective evaluation was performed on CBCT and panoramic radiographs of 50 patients (aged 18-45 years) selected from university archives. Axis vertebral morphology was assessed on CBCT using angular and perpendicular measurements of the dens and transverse processes. Facial asymmetry was evaluated on panoramic radiographs by measuring bilateral distances and angles from the condylion to the midsagittal plane. Pearson's correlation and Chi-square tests were used to analyze associations. Sample size was calculated based on a priori power analysis.</p><p><strong>Results: </strong>Moderate but statistically significant correlations were identified between specific vertebral and facial asymmetry parameters. A negative correlation was observed between the right Axis angle and the right Co-ANSMe perpendicular distance (r = - 0.31, p = 0.026), while the left Axis perpendicular distance showed a positive correlation with both right (r = 0.36, p = 0.009) and left (r = 0.33, p = 0.018) Co-ANSMe perpendicular distances. Additionally, combined measurements of Axis and Co-ANSMe distances demonstrated a moderate positive correlation (r = 0.31, p = 0.028). No other statistically significant correlations were found.</p><p><strong>Conclusions: </strong>Morphological differences in the Axis vertebra appear moderately associated with transverse facial asymmetry. These findings may offer additional reference points for radiographic assessment. Further studies with larger samples are recommended to confirm these observations.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"195"},"PeriodicalIF":2.9,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12123825/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144179620","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 decision support model construction for craniotomy approach of pineal region tumors based on MRI images.","authors":"Ziyan Chen, Yinhua Chen, Yandong Su, Nian Jiang, Siyi Wanggou, Xuejun Li","doi":"10.1186/s12880-025-01712-2","DOIUrl":"10.1186/s12880-025-01712-2","url":null,"abstract":"<p><strong>Background: </strong>Pineal region tumors (PRTs) are rare but deep-seated brain tumors, and complete surgical resection is crucial for effective tumor treatment. The choice of surgical approach is often challenging due to the low incidence and deep location. This study aims to combine machine learning and deep learning algorithms with pre-operative MRI images to build a model for PRTs surgical approaches recommendation, striving to model clinical experience for practical reference and education.</p><p><strong>Methods: </strong>This study was a retrospective study which enrolled a total of 173 patients diagnosed with PRTs radiologically from our hospital. Three traditional surgical approaches of were recorded for prediction label. Clinical and VASARI related radiological information were selected for machine learning prediction model construction. And MRI images from axial, sagittal and coronal views of orientation were also used for deep learning craniotomy approach prediction model establishment and evaluation.</p><p><strong>Results: </strong>5 machine learning methods were applied to construct the predictive classifiers with the clinical and VASARI features and all methods could achieve area under the ROC (Receiver operating characteristic) curve (AUC) values over than 0.7. And also, 3 deep learning algorithms (ResNet-50, EfficientNetV2-m and ViT) were applied based on MRI images from different orientations. EfficientNetV2-m achieved the highest AUC value of 0.89, demonstrating a significant high performance of prediction. And class activation mapping was used to reveal that the tumor itself and its surrounding relations are crucial areas for model decision-making.</p><p><strong>Conclusion: </strong>In our study, we used machine learning and deep learning to construct surgical approach recommendation models. Deep learning could achieve high performance of prediction and provide efficient and personalized decision support tools for PRTs surgical approach.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"194"},"PeriodicalIF":2.9,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12117726/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144156822","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}