BMC Medical Imaging最新文献

{"title":"Multimodal diagnostic tools and advanced data models for detection of prodromal Parkinson's disease: a scoping review.","authors":"Ibrahim Serag, Ahmed Y Azzam, Amr K Hassan, Rehab Adel Diab, Mohamed Diab, Mahmoud Tarek Hefnawy, Mohamed Ahmed Ali, Ahmed Negida","doi":"10.1186/s12880-025-01620-5","DOIUrl":"https://doi.org/10.1186/s12880-025-01620-5","url":null,"abstract":"<p><strong>Background: </strong>Parkinson's Disease (PD) is a progressive neurodegenerative disorder characterized by the loss of dopaminergic neurons in the substantia nigra pars compacta. PD is diagnosed by a combination of motor symptoms including bradykinesia, resting tremors, rigidity and postural instability. Prodromal PD is the stage preceding the onset of classic motor symptoms of PD. The diagnosis of prodromal PD remains challenging despite many available diagnostic modalities.</p><p><strong>Aim: </strong>This scoping review aims to investigate and explore the current diagnostic modalities used to detect prodromal PD, focusing particularly on multimodal imaging analysis and AI-based approaches.</p><p><strong>Methods: </strong>We adhered to the PRISMA-SR guidelines for scoping reviews. We conducted a comprehensive literature search at multiple databases such as PubMed, Scopus, Web of Science, and the Cochrane Library from inception to July 2024, using keywords related to prodromal PD and diagnostic modalities. We included studies based on predefined inclusion and exclusion criteria and performed data extraction using a standardized form.</p><p><strong>Results: </strong>The search included 9 studies involving 567 patients with prodromal PD and 35,643 control. Studies utilized various diagnostic approaches including neuroimaging techniques and AI-driven models. sensitivity ranging from 43 to 84% and specificity up to 96%. Neuroimaging and AI technologies showed promising results in identifying early pathological changes and predicting PD onset. The highest specificity was achieved by neuromelanin-sensitive imaging model, while highest sensitivity was achieved by standard 10-s electrocardiogram (ECG) + Machine learning model.</p><p><strong>Conclusion: </strong>Advanced diagnostic modalities such as AI-driven models and multimodal neuroimaging revealed promising results in early detection of prodromal PD. However, their clinical application as screening tool for prodromal PD is limited because of the lack of validation. Future research should be directed towards using Multimodal imaging in diagnosing and screening for prodromal PD.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"103"},"PeriodicalIF":2.9,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11951780/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143742221","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":"Hepatobiliary phase manifestations of breast cancer liver metastasis: differentiating molecular types through Gd-EOB-DTPA-enhanced MRI.","authors":"Hui Jiang, Jin-Rong Qu, Li-Feng Wang, Peng-Rui Gao, Bing-Jie Zheng, Hong-Kai Zhang, Li-Na Jiang","doi":"10.1186/s12880-025-01648-7","DOIUrl":"https://doi.org/10.1186/s12880-025-01648-7","url":null,"abstract":"<p><strong>Objective: </strong>The primary objective of this study is to evaluate the diagnostic efficacy of gadolinium ethoxybenzyl diethylenetriaminepentaacetic acid (Gd-EOB-DTPA) -enhanced magnetic resonance imaging (MRI) in distinguishing breast cancer liver metastasis (BCLM) across different molecular types.</p><p><strong>Methods: </strong>Between August 2014 and July 2021, a cohort of 270 patients histologically diagnosed with BCLM underwent examination through dynamic contrast-enhanced MRI (DCE-MRI). The data collection encompassed clinical information of patients, as well as information on the quantity, shape, boundary, and fusion state of liver metastases. Additionally, MR sequences including T2-weighted imaging with fat suppression (FS), diffusion-weighted imaging (DWI), MR arterial phase, and hepatobiliary phase (HBP) were collected. The chi-squared test was employed to study the correlations between different molecular types of BCLM and imaging features observed in MRI.</p><p><strong>Results: </strong>Significant differences were observed in the HBP image features among various subtypes of breast cancer (P = 0.022). The morphology (oval, irregular) and fusion state (converging, separated lesions) of BCLM exhibited statistically significant differences based on breast cancer subtypes (P = 0.022, 0.004). No statistical differences were found in the quantity of BCLM, the boundary of metastasis (clear or vague), and imaging features of the T2WI-FS and DWI concerning the molecular subtypes of BCLM (P = 0.693, 0.161, 0.629, 0.629).</p><p><strong>Conclusion: </strong>The findings suggest that MRI, particularly Gd-EOB-DTPA-enhanced MRI, they displayed varied enhancement patterns, including the low signal, \"target sign\", \"rim enhancement\", and \"doughnut-like enhancement\". Most basal-like metastases demonstrated a low signal, the other molecular types primarily showing the \"target sign\". This is invaluable in the imaging diagnosis of BCLM across different molecular type.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"104"},"PeriodicalIF":2.9,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11951506/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143742220","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-based reconstruction for three-dimensional volumetric brain MRI: a qualitative and quantitative assessment.","authors":"Yeseul Kang, Sang-Young Kim, Jun Hwee Kim, Nak-Hoon Son, Chae Jung Park","doi":"10.1186/s12880-025-01647-8","DOIUrl":"10.1186/s12880-025-01647-8","url":null,"abstract":"<p><strong>Background: </strong>To evaluate the performance of a deep learning reconstruction (DLR) based on Adaptive-Compressed sensing (CS)-Network for brain MRI and validate it in a clinical setting.</p><p><strong>Methods: </strong>Ten healthy volunteers and 22 consecutive patients were prospectively enrolled. Volunteers underwent 3D brain MRI including T1 without CS factor (9:16 min, reference standard); with CS factor of 2 without DLR (CS2, 4:6 min); with CS factor of 2 with DLR (DLR-CS2); with CS factor of 4 without DLR (CS4, 2:6 min); and with CS factor of 4 with DLR (DLR-CS4). The patients' MRI included the CS2 and DLR-CS4. The volumes of lateral ventricles, hippocampus, choroid plexus, and white matter hypointensity were calculated and compared among the sequences. Three radiologists independently assessed anatomical conspicuity, overall image quality, artifacts, signal-to-noise ratio (SNR), and sharpness using a 5-point scale for each sequence.</p><p><strong>Results: </strong>Applying acceleration factors of 2 and 4 reduced the scan time to 65.4% and 33.5%, respectively, of that of the reference standard. Volumes of all the measured subregions showed no significant differences among different sequences in all participants. In qualitative analysis, the interrater agreement was excellent (κ = 0.844-0.926). In volunteers, quality of DLR-CS4 were comparable to those of CS2 for all metrics except for the overall image quality and SNR despite a 51.2% scan time reduction. In patients, DLR-CS4 showed quality comparable to that of CS2 for all metrics.</p><p><strong>Conclusions: </strong>DLR allowed the scan time reduction by at least half without sacrificing image quality and volumetric quantification accuracy, supporting its reliability and efficiency.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"102"},"PeriodicalIF":2.9,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11951731/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143728376","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":"Automated segmentation of brain metastases in T1-weighted contrast-enhanced MR images pre and post stereotactic radiosurgery.","authors":"Hemalatha Kanakarajan, Wouter De Baene, Patrick Hanssens, Margriet Sitskoorn","doi":"10.1186/s12880-025-01643-y","DOIUrl":"10.1186/s12880-025-01643-y","url":null,"abstract":"<p><strong>Background and purpose: </strong>Accurate segmentation of brain metastases on Magnetic Resonance Imaging (MRI) is tedious and time-consuming for radiologists that could be optimized with deep learning (DL). Previous studies assessed several DL algorithms focusing only on training and testing the models on the planning MRI only. The purpose of this study is to evaluate well-known DL approaches (nnU-Net and MedNeXt) for their performance on both planning and follow-up MRI.</p><p><strong>Materials and methods: </strong>Pre-treatment brain MRIs were retrospectively collected for 255 patients at Elisabeth-TweeSteden Hospital (ETZ): 201 for training and 54 for testing, including follow-up MRIs for the test set. To increase heterogeneity, we added the publicly available MRI scans from the Mathematical oncology laboratory of 75 patients to the training data. The performance was compared between the two models, with and without the addition of the public data. To statistically compare the Dice Similarity Coefficient (DSC) of the two models trained on different datasets over multiple time points, we used Linear Mixed Models.</p><p><strong>Results: </strong>All models obtained a good DSC (DSC > = 0.93) for planning MRI. MedNeXt trained with combined data provided the best DSC for follow-ups at 6, 15, and 21 months (DSC of 0.74, 0.74, and 0.70 respectively) and jointly the best DSC for follow-ups at three months with MedNeXt trained with ETZ data only (DSC of 0.78) and 12 months with nnU-Net trained with combined data (DSC of 0.71). On the other hand, nnU-Net trained with combined data provided the best sensitivity and FNR for most follow-ups. The statistical analysis showed that MedNeXt provides higher DSC for both datasets and the addition of public data to the training dataset results in a statistically significant increase in performance in both models.</p><p><strong>Conclusion: </strong>The models achieved a good performance score for planning MRI. Though the models performed less effectively for follow-ups, the addition of public data enhanced their performance, providing a viable solution to improve their efficacy for the follow-ups. These algorithms hold promise as a valuable tool for clinicians for automated segmentation of planning and follow-up MRI scans during stereotactic radiosurgery treatment planning and response evaluations, respectively.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"101"},"PeriodicalIF":2.9,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11948752/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143717909","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":"Accuracy of ultrasonographic transcerebellar diameter for dating in third trimester of pregnancy in Nigerian women: a cross-sectional study.","authors":"Okechukwu Uche Ofoegbu, Nicholas Irurhe, Tersur Terry Saalu, Oluwaseun Emmanuel Familusi, Charity Opeoluwapo Maduagu, Lucky Enajite Tietie, Olaniyi Araotan Kusamotu, Ochuwa Adiketu Babah","doi":"10.1186/s12880-025-01634-z","DOIUrl":"10.1186/s12880-025-01634-z","url":null,"abstract":"<p><strong>Background: </strong>Accurate prediction of foetal gestational age is of critical importance as it can positively affect the outcome of pregnancy. Routine sonographic estimation of gestational age using biparietal diameter, head circumference, abdominal circumference and femur length is popular but has limitations especially when used as a singly or in late pregnancy. Often pregnant women in low-middle-income countries like Nigeria register for antenatal care late in pregnancy, necessitating the need for a single, cost-effective parameter that requires minimal skills to measure gestational age accurately in late pregnancies. This study examined the accuracy of ultrasonographic transcerebellar diameter compared to other foetal biometric parameters for dating in third trimester of pregnancy.</p><p><strong>Methodology: </strong>An analytic cross-sectional study conducted at Lagos University Teaching Hospital, Idi-Araba, Lagos, on 110 pregnant women in their third trimester. Data was collected using an interviewer administered questionnaire. Transabdominal ultrasound scan was done to determine the gestational age by measuring the biparietal diameter, head circumference, abdominal circumference, femur length and transcerebellar diameter. Spearman's correlation coefficient was used to determine the correlation between the biometric measurements; Accuracy was determine using gestational age from menstrual date as gold standard and comparisons made using Chi square test.</p><p><strong>Results: </strong>Mean age of participants was 31.5 ± 5.8 years; mean gestational age 236 ± 25 days. Compared to biparietal diameter, head circumference, abdominal circumference, and femur length, transcerebellar diameter correlates best with gestational age (r = 0.8837, p < 0.001). At an error margin of ± 2weeks, transcerebellar diameter had a high predictive accuracy of 84.6%, though significantly less than that for abdominal circumference alone, 86.4% (p = 0.003), and also less than that for all four well known foetal biometric parameters (biparietal diameter, head circumference, abdominal circumference, and femur length) combined, 85.5% (p < 0.001).</p><p><strong>Conclusion: </strong>Transcerebellar diameter has a better correlation with gestational age than other routine foetal biometric parameters and has high predictive accuracy for dating in third trimester of pregnancy. It may thus play a relevant role in low resource settings where there is shortage of staff and limited skills in obstetric ultrasonography.</p><p><strong>Clinical trial number: </strong>Not applicable for this study.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"100"},"PeriodicalIF":2.9,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11934699/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143708337","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":"Intelligent detection and grading diagnosis of fresh rib fractures based on deep learning.","authors":"Tongxin Li, Mingyi Liao, Yong Fu, Fanghong Zhang, Luya Shen, Junliang Che, Shulei Wu, Jie Liu, Wei Wu, Ping He, Qingyuan Xu, Yi Wu","doi":"10.1186/s12880-025-01641-0","DOIUrl":"10.1186/s12880-025-01641-0","url":null,"abstract":"<p><strong>Background: </strong>Accurate detection and grading of fresh rib fractures are crucial for patient management but remain challenging due to the complexity of rib structures on CT images.</p><p><strong>Methods: </strong>Chest CT images from 383 patients with rib fractures were retrospectively analyzed. The dataset was divided into a training set (n = 306) and an internal testing set (n = 77). An external testing set of 50 patients from the public RibFrac dataset was included. Fractures were classified into severe and non-severe categories. A modified YOLO-based deep learning model was developed for detection and grading. Performance was compared with thoracic surgeons using precision, recall, mAP50, and F1 score.</p><p><strong>Results: </strong>The deep learning model showed excellent performance in diagnosing fresh rib fractures. For all fractures types in internal test set, the precision, recall, mAP50, and F1 score were 0.963, 0.934, 0.972, and 0.948, respectively. The model outperformed thoracic surgeons of varying experience levels (all p < 0.01).</p><p><strong>Conclusion: </strong>The proposed deep learning model can automatically detect and grade fresh rib fractures with accuracy comparable to that of physicians. This model helps improve diagnostic accuracy, reduce physician workload, save medical resources, and strengthen health care in resource-limited areas.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"98"},"PeriodicalIF":2.9,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11934624/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143699582","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":"Enhanced tuberculosis detection using Vision Transformers and explainable AI with a Grad-CAM approach on chest X-rays.","authors":"K Vanitha, T R Mahesh, V Vinoth Kumar, Suresh Guluwadi","doi":"10.1186/s12880-025-01630-3","DOIUrl":"10.1186/s12880-025-01630-3","url":null,"abstract":"<p><p>Tuberculosis (TB), caused by Mycobacterium tuberculosis, remains a leading global health challenge, especially in low-resource settings. Accurate diagnosis from chest X-rays is critical yet challenging due to subtle manifestations of TB, particularly in its early stages. Traditional computational methods, primarily using basic convolutional neural networks (CNNs), often require extensive pre-processing and struggle with generalizability across diverse clinical environments. This study introduces a novel Vision Transformer (ViT) model augmented with Gradient-weighted Class Activation Mapping (Grad-CAM) to enhance both diagnostic accuracy and interpretability. The ViT model utilizes self-attention mechanisms to extract long-range dependencies and complex patterns directly from the raw pixel information, whereas Grad-CAM offers visual explanations of model decisions about highlighting significant regions in the X-rays. The model contains a Conv2D stem for initial feature extraction, followed by many transformer encoder blocks, thereby significantly boosting its ability to learn discriminative features without any pre-processing. Performance testing on a validation set had an accuracy of 0.97, recall of 0.99, and F1-score of 0.98 for TB patients. On the test set, the model has accuracy of 0.98, recall of 0.97, and F1-score of 0.98, which is better than existing methods. The addition of Grad-CAM visuals not only improves the transparency of the model but also assists radiologists in assessing and verifying AI-driven diagnoses. These results demonstrate the model's higher diagnostic precision and potential for clinical application in real-world settings, providing a massive improvement in the automated detection of TB.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"96"},"PeriodicalIF":2.9,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11934573/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143699579","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":"Structured reporting of gliomas based on VASARI criteria to improve report content and consistency.","authors":"Olivia Goodkin, Jiaming Wu, Hugh Pemberton, Ferran Prados, Sjoerd B Vos, Stefanie Thust, John Thornton, Tarek Yousry, Sotirios Bisdas, Frederik Barkhof","doi":"10.1186/s12880-025-01603-6","DOIUrl":"10.1186/s12880-025-01603-6","url":null,"abstract":"<p><strong>Purpose: </strong>Gliomas are the commonest malignant brain tumours. Baseline characteristics on structural MRI, such as size, enhancement proportion and eloquent brain involvement inform grading and treatment planning. Currently, free-text imaging reports depend on the individual style and experience of the radiologist. Standardisation may increase consistency of feature reporting.</p><p><strong>Methods: </strong>We compared 100 baseline free-text reports for glioma MRI scans with a structured feature list based on VASARI criteria and performed a full second read to document which VASARI features were in the baseline report.</p><p><strong>Results: </strong>We found that quantitative features including tumour size and proportion of necrosis and oedema/infiltration were commonly not included in free-text reports. Thirty-three percent of reports gave a description of size only, and 38% of reports did not refer to tumour size at all. Detailed information about tumour location including involvement of eloquent areas and infiltration of deep white matter was also missing from the majority of free-text reports. Overall, we graded 6% of reports as having omitted some key VASARI features that would alter patient management.</p><p><strong>Conclusions: </strong>Tumour size and anatomical information is often omitted by neuroradiologists. Comparison with a structured report identified key features that would benefit from standardisation and/or quantification. Structured reporting may improve glioma reporting consistency, clinical communication, and treatment decisions.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"99"},"PeriodicalIF":2.9,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11934815/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143699215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The correlation analysis between Normalized Wall Index and cerebral perfusion in patients with Mild Carotid Artery Stenosis under 3.0T MRI.","authors":"Yonggang Cai, Shouming Chen, Tongyu Shang, Binze Han, Lei Zhang, Changyan Xu, Zhibin He, Ting Yin","doi":"10.1186/s12880-025-01639-8","DOIUrl":"10.1186/s12880-025-01639-8","url":null,"abstract":"<p><strong>Background: </strong>To explore the relationship between Normalized Wall Index (NWI) and Magnetic Resonance Perfusion Imaging Parameters in Patients with Mild Carotid Artery Stenosis.</p><p><strong>Methods: </strong>Initially, an analysis was conducted on 40 patients from our institution, and we identified through ultrasonographic examinations conducted between July 2021 and August 2022. These patients exhibited carotid artery plaques with mild luminal narrowing (with stenosis rates ranging from 20 to 50%, following the criteria of the North American Symptomatic Carotid Endarterectomy Trial, NASCET). All cases underwent high-resolution magnetic resonance imaging (MRI) of the carotid arteries and cerebral perfusion assessments using 3.0T MRI during the specified timeframe. Based on whether the cerebral hemisphere in the carotid artery supply region had experienced ischemic events, including Transient Ischemic Attacks (TIAs), patients were categorized into symptomatic and asymptomatic groups. Subsequently, the Normalized Wall Index (NWI) of the carotid arteries and the area of abnormal perfusion on the same side of the brain were calculated for each group.</p><p><strong>Results: </strong>In the symptomatic group, all patients exhibited perfusion abnormalities in the internal carotid artery supply region, whereas only some patients in the asymptomatic group showed such abnormalities. The NWI of plaques in the symptomatic group was significantly higher than that in the asymptomatic group (P < 0.05).</p><p><strong>Conclusion: </strong>The range of prolongation in mean transit time (MTT) and time to peak (TTP) in patients with perfusion abnormalities was positively correlated with NWI and stenosis rates. The association with NWI was more pronounced and statistically significant (P < 0.05).</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"97"},"PeriodicalIF":2.9,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11934482/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143699218","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 surgical clips for target volume delineation in post-lumpectomy breast cancer radiotherapy.","authors":"Xin Xie, Peng Huang, Zhihui Hu, Yuhan Fan, Jiawen Shang, Ke Zhang, Hui Yan","doi":"10.1186/s12880-025-01636-x","DOIUrl":"10.1186/s12880-025-01636-x","url":null,"abstract":"<p><strong>Purpose: </strong>To develop an automatic segmentation model for surgical marks, titanium clips, in target volume delineation of breast cancer radiotherapy after lumpectomy.</p><p><strong>Methods: </strong>A two-stage deep-learning model is used to segment the titanium clips from CT image. The first network, Location Net, is designed to search the region containing all clips from CT. Then the second network, Segmentation Net, is designed to search the locations of clips from the previously detected region. Ablation studies are performed to evaluate the impact of various inputs for both networks. The two-stage deep-learning model is also compared with the other existing deep-learning methods including U-Net, V-Net and UNETR. The segmentation accuracy of these models is evaluated by three metrics: Dice Similarity Coefficient (DSC), 95% Hausdorff Distance (HD95), and Average Surface Distance (ASD).</p><p><strong>Results: </strong>The DSC, HD95 and ASD of the two-stage model are 0.844, 2.008 mm and 0.333 mm, while their values are 0.681, 2.494 mm and 0.785 mm for U-Net, 0.767, 2.331 mm and 0.497 mm for V-Net, 0.714, 2.660 mm and 0.772 mm for UNETR. The proposed 2-stage model achieved the best performance among the four models.</p><p><strong>Conclusion: </strong>With the two-stage searching strategy the accuracy to detect titanium clips can be improved comparing to those existing deep-learning models with one-stage searching strategy. The proposed segmentation model can facilitate the delineation of tumor bed and subsequent target volume for breast cancer radiotherapy after lumpectomy.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":"25 1","pages":"95"},"PeriodicalIF":2.9,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11929263/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676804","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}