BMC Medical Imaging最新文献

{"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":"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":"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}

{"title":"MSA-Net: multiple self-attention mechanism for 3D lung nodule classification in CT images.","authors":"Jiating Pan, Lishi Liang, Peng Sun, Yongbo Liang, Jianming Zhu, Zhencheng Chen","doi":"10.1186/s12880-025-01725-x","DOIUrl":"10.1186/s12880-025-01725-x","url":null,"abstract":"<p><strong>Purpose: </strong>Lung cancer is a life-threatening disease that poses a significant risk to human health. Accurate differentiation between benign and malignant lung nodules, based on computed tomography (CT), is crucial to assess lung health. Developing an automated computer-aided diagnostic method for this differentiation is essential. We introduced a streamlined 3D model structure to solve the problems of 2D models cannot extract spatial information effectively and 3D models have high complexity and large occupation of computing resources.</p><p><strong>Methods: </strong>We proposed an MSA (multiple self-attention-based) model to address the limitations of 2D models in extracting spatial information effectively and the high complexity associated with 3D models. Our approach introduced the 3D RTConvBlock, which employed multiple self-attention mechanisms for the extraction of spatial features. This enabled the extraction of specific spatial feature information by combining local features, global information, and dependencies between features.</p><p><strong>Results: </strong>The MSA model demonstrates exceptional performance with an accuracy of 0.953, a sensitivity of 0.963, and an AUC (area under curve) of 0.993 in the LUNA16 dataset, which is higher than state-of-the-art methods. Compared with existing 2D models, we extract spatial information features better, resulting in higher accuracy.</p><p><strong>Conclusion: </strong>These results have significant implications for enhancing the accuracy and reliability of lung nodule classification, providing robust auxiliary support for physicians diagnosing lung diseases.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"193"},"PeriodicalIF":2.9,"publicationDate":"2025-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12117915/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144156824","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":"Magnetic resonance imaging features of intrahepatic bile duct adenoma: a 10-year retrospective study.","authors":"Ge Sun, Jiamei Yao, Huai Chen, Mengsu Zeng, Mingliang Wang","doi":"10.1186/s12880-025-01733-x","DOIUrl":"10.1186/s12880-025-01733-x","url":null,"abstract":"<p><strong>Background: </strong>Intrahepatic bile duct adenoma (BDA) is a rare tumor with limited understanding of its magnetic resonance imaging (MRI) features and clinical characteristics. This study aimed to analyze the MRI characteristics of BDA.</p><p><strong>Methods: </strong>This retrospective study analyzed MRI findings and clinical profiles of 33 patients diagnosed with bile duct adenomas (BDA) at Zhongshan Hospital Fudan University from January 2014 to January 2024. MRI features and clinical data were reviewed and analyzed.</p><p><strong>Results: </strong>A total of 36 lesions were identified among 33 patients, with 31 cases presenting as solitary lesions. The average diameter was 9.2 ± 3.1 mm, predominantly subcapsular, located near the liver capsule, with the majority exhibiting well-defined margins. On T1-weighted imaging (T1WI), lesions displayed hypointensity, while T2-weighted imaging (T2WI) was slightly hypointense in most cases, enhancing the visibility of the lesions. Apparent diffusion coefficient (ADC) values averaged (1.93 ± 0.51)×10⁻³ mm²/s, significantly higher than surrounding liver tissue (P < 0.001), suggesting unique tissue properties. Notably, BDA, as a hypervascular tumor, displayed rim and non-rim enhancement patterns, along with a tendency for persistent enhancement.</p><p><strong>Conclusion: </strong>The MRI features of BDA included small lesions near the liver capsule, characterized by distinct morphology and enhancement patterns, alongside elevated ADC values that distinguish them from malignant hepatic lesions. The findings emphasize the importance of MRI in the accurate diagnosis and management of BDA.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"188"},"PeriodicalIF":2.9,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12107894/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144149090","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":"Detecting microcephaly and macrocephaly from ultrasound images using artificial intelligence.","authors":"Abraham Keffale Mengistu, Bayou Tilahun Assaye, Addisu Baye Flatie, Zewdie Mossie","doi":"10.1186/s12880-025-01709-x","DOIUrl":"10.1186/s12880-025-01709-x","url":null,"abstract":"<p><strong>Background: </strong>Microcephaly and macrocephaly, which are abnormal congenital markers, are associated with developmental and neurologic deficits. Hence, there is a medically imperative need to conduct ultrasound imaging early on. However, resource-limited countries such as Ethiopia are confronted with inadequacies such that access to trained personnel and diagnostic machines inhibits the exact and continuous diagnosis from being met.</p><p><strong>Objective: </strong>This study aims to develop a fetal head abnormality detection model from ultrasound images via deep learning.</p><p><strong>Methods: </strong>Data were collected from three Ethiopian healthcare facilities to increase model generalizability. The recruitment period for this study started on November 9, 2024, and ended on November 30, 2024. Several preprocessing techniques have been performed, such as augmentation, noise reduction, and normalization. SegNet, UNet, FCN, MobileNetV2, and EfficientNet-B0 were applied to segment and measure fetal head structures using ultrasound images. The measurements were classified as microcephaly, macrocephaly, or normal using WHO guidelines for gestational age, and then the model performance was compared with that of existing industry experts. The metrics used for evaluation included accuracy, precision, recall, the F1 score, and the Dice coefficient.</p><p><strong>Results: </strong>This study was able to demonstrate the feasibility of using SegNet for automatic segmentation, measurement of abnormalities of the fetal head, and classification of macrocephaly and microcephaly, with an accuracy of 98% and a Dice coefficient of 0.97. Compared with industry experts, the model achieved accuracies of 92.5% and 91.2% for the BPD and HC measurements, respectively.</p><p><strong>Conclusion: </strong>Deep learning models can enhance prenatal diagnosis workflows, especially in resource-constrained settings. Future work needs to be done on optimizing model performance, trying complex models, and expanding datasets to improve generalizability. If these technologies are adopted, they can be used in prenatal care delivery.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"183"},"PeriodicalIF":2.9,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12105205/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144149088","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":"Age-and gender-related variations of liver diffusion metrics apparent diffusion coefficient (ADC) and diffusion derived vessel density (DDVD), and explanations with the known physiological T2 relaxation time variations among different volunteers' groups.","authors":"Ying-Ying Deng, Ming-Hua Sun, Hua Huang, Yì Xiáng J Wáng","doi":"10.1186/s12880-025-01730-0","DOIUrl":"10.1186/s12880-025-01730-0","url":null,"abstract":"<p><strong>Background: </strong>Age-related liver diffusion metrics changes have been described. We aim to further clarify these questions: 1) whether an age-related reduction of liver perfusion can be observed by DDVD (diffusion derived vessel density) in older males; 2) whether there is a male female difference in liver perfusion; 3) whether liver ADC values and spleen ADC values are correlated. It is known that, physiologically, males' liver has a higher iron level (thus a shorter T2) than females' liver; pre-menopausal females have a lower liver iron level (thus a longer T2) than post-menopausal females. The observations of this study will be interpreted with the recently gained knowledge of the T2 contribution to diffusion metrics.</p><p><strong>Methods: </strong>Included in this healthy volunteer's study were 68 males (mean age:50.22 years, range: 25-70 years) and 43 females (mean age 45.56 years, range:20-71 years). DWI images with b-values of 0, 2, 10, 20, 60, and 600 s/mm² were acquired at 1.5T. DDVD were calculated with b = 0, b = 2, b = 10, and b = 20 s/mm² images. ADC were calculated with b = 0, b = 2, b = 60 and b = 600 s/mm² images.</p><p><strong>Results: </strong>There was a statistically significant age-related decline of liver DDVD values for females (p = 0.024). A similar trend was observed for males, though statistical significance was not achieved (p = 0.113). Liver DDVD values were all higher in females than in males (p < 0.001). There was a statistically significant age-related decline of liver ADC values both for males (ADC_(b0b600), p = 0.009) and for females (ADC_(b0b600), p = 0.016). Liver ADC values and spleen ADC values were positively correlated (ADC_(b0b600), r = 0.33 for males and 0.31 for females, p < 0.05). When the spleen ADC was used to normalize the liver ADC, then the age-related trend was largely removed, both for males and for females (p > 0.05).</p><p><strong>Conclusion: </strong>Females have a larger liver perfusion volume than males. There is an age-related decrease of DDVD and ADC, both for males and females. Liver ADC values and spleen ADC values are positively correlated. These gender and age-related changes are unlikely mainly caused by the liver T2 relaxation time variations.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"185"},"PeriodicalIF":2.9,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12105168/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144149141","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":"Auto-segmentation of cerebral cavernous malformations using a convolutional neural network.","authors":"Chi-Jen Chou, Huai-Che Yang, Cheng-Chia Lee, Zhi-Huan Jiang, Ching-Jen Chen, Hsiu-Mei Wu, Chun-Fu Lin, I-Chun Lai, Syu-Jyun Peng","doi":"10.1186/s12880-025-01738-6","DOIUrl":"10.1186/s12880-025-01738-6","url":null,"abstract":"<p><strong>Background: </strong>This paper presents a deep learning model for the automated segmentation of cerebral cavernous malformations (CCMs).</p><p><strong>Methods: </strong>The model was trained using treatment planning data from 199 Gamma Knife (GK) exams, comprising 171 cases with a single CCM and 28 cases with multiple CCMs. The training data included initial MRI images with target CCM regions manually annotated by neurosurgeons. For the extraction of data related to the brain parenchyma, we employed a mask region-based convolutional neural network (Mask R-CNN). Subsequently, this data was processed using a 3D convolutional neural network known as DeepMedic.</p><p><strong>Results: </strong>The efficacy of the brain parenchyma extraction model was demonstrated via five-fold cross-validation, resulting in an average Dice similarity coefficient of 0.956 ± 0.002. The segmentation models used for CCMs achieved average Dice similarity coefficients of 0.741 ± 0.028 based solely on T2W images. The Dice similarity coefficients for the segmentation of CCMs types were as follows: Zabramski Classification type I (0.743), type II (0.742), and type III (0.740). We also developed a user-friendly graphical user interface to facilitate the use of these models in clinical analysis.</p><p><strong>Conclusions: </strong>This paper presents a deep learning model for the automated segmentation of CCMs, demonstrating sufficient performance across various Zabramski classifications.</p><p><strong>Trial registration: </strong>not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"190"},"PeriodicalIF":2.9,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12107882/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144149145","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}