BMC Medical Imaging最新文献

{"title":"The impact of protective eyewear and device position on operator radiation dose during handheld portable X‑ray device use.","authors":"Sinem Coşkun Albayrak, Alican Kuran, Murat Doğuş Günel","doi":"10.1186/s12880-026-02593-9","DOIUrl":"https://doi.org/10.1186/s12880-026-02593-9","url":null,"abstract":"<p><strong>Objectives: </strong>The use of handheld dental X-ray devices has been increasing, raising concerns about operator radiation exposure. This study evaluated the effects of handheld dental X-ray device positioning and protective eyewear on the absorbed dose received by the operator's eye lens and pituitary gland.</p><p><strong>Methods: </strong>Calibrated optically stimulated luminescent dosimeters were placed at the eye lens and sphenoid regions of an anthropomorphic head phantom. Measurements were obtained under different device positioning scenarios, with and without protective eyewear. Four operator positions were evaluated, and 30 repeated irradiations were performed under each condition, both with and without protective eyewear, resulting in a total of 720 individual measurements.</p><p><strong>Results: </strong>Both operator positioning and the use of protective eyewear significantly influenced absorbed dose levels. Protective eyewear reduced ocular and sphenoidal exposure across all evaluated positions, with the greatest reduction observed when combined with optimal device angulation. Across all positions, the use of protective eyewear decreased absorbed dose by approximately 48-70% (p < 0.001 for all comparisons), with the largest reductions observed under the shielding condition.</p><p><strong>Conclusions: </strong>Appropriate operator positioning and the consistent use of protective eyewear are essential for minimizing radiation exposure to radiosensitive structures during handheld dental X-ray procedures. Under the conditions evaluated in this phantom study, the combination of a 45° device angulation and protective eyewear resulted in the lowest absorbed dose values, suggesting that this approach may help reduce operator radiation exposure.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148547504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The value of double inversion recovery MRI sequences in the diagnosis of inflammatory demyelinating diseases of the spinal cord.","authors":"Yannan Zhang, Qian Xiao, Dan Zhu, Xiaoxia Zhang, Yibin Wang, Genlin Zong, Ailan Cheng, Shuguang Chu","doi":"10.1186/s12880-026-02595-7","DOIUrl":"https://doi.org/10.1186/s12880-026-02595-7","url":null,"abstract":"<p><strong>Background: </strong>Spinal inflammatory demyelinating diseases (IDDs) often exhibit overlapping imaging features across different etiologies. This study aims to compare and analyze the differences in qualitative diagnostic capability (specificity) and lesion detection performance (including lesion count and lesion contrast) between DIR and T2-weighted imaging (T2WI) in spinal cord IDDs, thereby exploring the diagnostic value of the DIR in these conditions.</p><p><strong>Methods: </strong>Retrospectively analyzed MRI data of 20 spinal demyelinating disease patients (13 MS, 4 ADEM, 3 NMOSD) from March 2022 to November 2024. Two radiologists independently performed qualitative diagnosis for all patients using DIR and T2WI images. They then counted the lesions on spinal cord DIR and T2WI, and calculated the contrast-to-noise ratio (CNR) and signal intensity ratio (SIR) for all lesions. Lesion contrast differences were compared using CNR and SIR values. Inter-observer agreement was measured by ICC analysis.</p><p><strong>Results: </strong>Inter-observer agreement was excellent for DIR (κ = 0.83) and substantial for T2WI (κ = 0.76). Consensus diagnosed 16 cases on DIR versus 6 on T2WI. Lesion count agreement was good (ICC > 0.75) both on T2WI and DIR. DIR detected 77.78% more lesions (p < 0.05). DIR showed higher CNR (8.74 ± 2.04 vs. 2.83 ± 0.74) and SIR (0.98 ± 0.40 vs. 0.37 ± 0.14) than T2WI (both p < 0.01).</p><p><strong>Conclusions: </strong>Compared with conventional T2WI, DIR demonstrated significantly improved lesion detection capability, revealing more lesions with higher CNR and SIR values. DIR sequences showed superior diagnostic performance (specificity) for spinal IDDs than T2WI. We recommend DIR sequences as a supplementary MRI protocol for evaluating spinal IDDs.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148547517","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":"Optimizing carotid plaque visualization: the advantage of subtraction imaging from dual-layer spectral CT.","authors":"Yuanyuan Wu, Xueke Zhang, Zeyuan Cao, Xin Shen, Shaokun Hu, Dongliang Hu, Yiru Shen, Manman Cui, Duchang Zhai, Xingbiao Chen, Shenghong Ju, Wu Cai","doi":"10.1186/s12880-026-02596-6","DOIUrl":"https://doi.org/10.1186/s12880-026-02596-6","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Computed tomography angiography (CTA) has become the primary method for detecting carotid atherosclerosis. However, the visibility of the arterial wall on the CTA is poor because of the high attenuation lumen filled with contrast agent. To optimize the display of the carotid arterial walls, this study proposed a black blood technique by generating subtraction images (CTA&lt;sub&gt;sub&lt;/sub&gt;) based on dual-layer spectral CT, and explored its role in the assessment of carotid atherosclerotic plaques.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Materials and methods: &lt;/strong&gt;CTA&lt;sub&gt;sub&lt;/sub&gt; were generated by subtracting virtual monochrome images (VMI) from virtual non-contrast images (VNC) obtained from SDCT scans. Two senior radiologists and two junior radiologists read conventional CTA images (CTA&lt;sub&gt;con&lt;/sub&gt;) with and without CTA&lt;sub&gt;sub&lt;/sub&gt; respectively. The inter-reader agreement for plaque classification of each extracranial carotid artery and diagnostic confidence were compared. The extracranial carotid wall visibility, outer margin conspicuity of non-calcified components, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of the non-calcified components as well as the stenosis rate at the narrowest level were compared between CTA&lt;sub&gt;sub&lt;/sub&gt; and CTA&lt;sub&gt;con&lt;/sub&gt;. Using high-resolution magnetic resonance imaging (hrMRI) as the standard, the accuracy in plaque burden estimation on CTA&lt;sub&gt;con&lt;/sub&gt; and CTA&lt;sub&gt;sub&lt;/sub&gt; were compared. The paired t-test and the Wilcoxon signed-rank test were used for the comparison between CTA&lt;sub&gt;sub&lt;/sub&gt; and CTA&lt;sub&gt;con&lt;/sub&gt;. The Cohen κ value and the intraclass correlation coefficient (ICC) were used to evaluate the consistency.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;A total of 119 patients were included in the comparisons between CTA&lt;sub&gt;sub&lt;/sub&gt; and CTA&lt;sub&gt;con&lt;/sub&gt; and a total of 31 patients were enrolled in the plaque burden comparison between CTA and hrMRI. CTA&lt;sub&gt;sub&lt;/sub&gt; improved the consistency of plaque classification between radiologists and increased their diagnostic confidence. CTA&lt;sub&gt;sub&lt;/sub&gt; also provide better arterial wall visibility and clearer outer margin conspicuity of non-calcified components. The SNR and CNRs of non-calcified components were obviously elevated on CTA&lt;sub&gt;sub&lt;/sub&gt; (SNR: 12.86 ± 6.51 vs. 7.77 ± 4.30; CNR&lt;sub&gt;non-calcified/fat&lt;/sub&gt;: 33.13 ± 2.65 vs. 24.96 ± 7.90; CNR&lt;sub&gt;non-calcified/muscle&lt;/sub&gt;: 8.58 ± 4.27 vs. 6.64 ± 4.11, all p &lt; 0.001). Moreover, CTA&lt;sub&gt;sub&lt;/sub&gt; displayed good to excellent consistency with CTA&lt;sub&gt;con&lt;/sub&gt; in stenosis rate measurement (NASCET: ICC = 0.919; ECST: ICC = 0.889, both p &lt; 0.001) and a more closer estimation of plaque burden to hrMRI than CTA&lt;sub&gt;con&lt;/sub&gt;(ICC = 0.938 vs. 0.842, p &lt; 0.001).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;As a complement to CTA&lt;sub&gt;con&lt;/sub&gt;, CTA&lt;sub&gt;sub&lt;/sub&gt; not only improves visualization of the extracranial carotid wall and non-calcified plaque components but also enables accurate quantificat","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148535163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel biological interpretation of neuropsychiatric symptoms in patients with allergic rhinitis: insights from brain functional connectivity gradient and serum multi-omics analysis.","authors":"Ting Yang, Tongpeng Chu, Xiaoyu Song, Hanrui Wang, Yao Wang, Ning Mao, Kaili Che, Fanghui Dong, Wanchen Liu, Anan Li, Chao Ren, Yakui Mou, Xicheng Song","doi":"10.1186/s12880-026-02602-x","DOIUrl":"https://doi.org/10.1186/s12880-026-02602-x","url":null,"abstract":"<p><strong>Background: </strong>The \"nose-brain axis\" has been proposed as a key mechanism linking allergic rhinitis (AR) to central nervous system (CNS) dysfunction; however, alterations in functional connectivity (FC) gradients remain unexplored in AR. This cross-sectional study aimed to investigate the correlation between brain FC gradients and AR-related peripheral multi-omics profiles, as well as their clinical significance, through multimodal cross scale analysis.</p><p><strong>Methods: </strong>We enrolled cross-scale data from 22 AR patients and 20 healthy controls (HCs), including resting-state functional magnetic resonance imaging (rs-fMRI), serum proteomics and metabolomics, and clinical assessments. FC gradient analysis was employed to investigate hierarchical brain functional organization, with gradient values compared at global, regional, and network levels. Multivariate partial least squares (PLS) analysis was used to integrate the multidimensional associations among FC gradients, peripheral molecular signatures, and behavioral phenotypes.</p><p><strong>Results: </strong>No significant differences were observed at the global or Yeo's seven canonical networks. However, refined regional analysis revealed significant FC gradient alterations predominantly within the Default mode (DMN), Somatomotor (SMN), and Limbic (LN) networks, particularly in RH_Default_Temp_5 (p = 0.0031) and LH_Limbic_OFC_4 (p = 0.0034). These regional gradient abnormalities correlated significantly with AR severity and neuropsychiatric symptoms (p < 0.05), indicating \"local fine-tuning\" rather than \"global collapse\" in brain functional remodeling. Multi-omic profiling identified 121 differentially expressed proteins, 197 positive-ion-mode metabolites, 134 negative-ion-mode metabolites. The integrative analysis demonstrated significant associations between these peripheral molecular signatures and AR-related FC gradient alterations. These differentially expressed molecules were primarily enriched in immune response, complement activation, lipids and lipid-like molecules, and cholesterol metabolism pathways.</p><p><strong>Conclusion: </strong>This study provides the first evidence of distinct FC gradient alterations in AR that are coupled to peripheral multi-omic shifts, offering novel insights into CNS mechanisms of AR and identifying potential molecular-neuroimaging biomarkers candidates for precision diagnosis and targeted therapy.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148547486","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":"Capability of multiparametric MRI to detect diabetic nephropathy in high-risk patients with type 2 diabetes: a prospective preliminary study.","authors":"Wei Mao, Xiaoqiang Ding, Caixia Fu, Bernd Kuehn, Dominik Nickel, Robert Grimm, Thomas Benkert, Mengsu Zeng, Jianjun Zhou","doi":"10.1186/s12880-026-02588-6","DOIUrl":"https://doi.org/10.1186/s12880-026-02588-6","url":null,"abstract":"<p><strong>Background: </strong>Early diagnosis and treatment of diabetic nephropathy (DN) is important for improving prognosis of patients, but the noninvasive and reliable diagnostic tool is lacking. We aim to investigate the ability of multiparametric MRI for detecting early DN in high-risk patients with type 2 diabetes.</p><p><strong>Methods: </strong>Between June 2023 and October 2024, we prospectively recruited 80 patients(diabetic patients group, n = 42, 53.4 ± 10.0 years old; DN patients group, n = 38, 47.9 ± 10.9 years old) and 16 healthy volunteers(control group, 49.5 ± 9.5 years old). All participants were examined using multiparametric MRI(IVIM, DKI, ASL and T1 mapping). The true diffusion coefficient(D), perfusion fraction(f), mean diffusivity(MD), mean kurtosis(MK), renal blood flow(RBF), T1 values in renal cortex were measured. Renal cortical MRI parameters among 3 groups were compared by one-way analysis of variance. Correlation between estimated glomerular filtration rate(eGFR), 24-hour urine albumin(24 h-UA) and renal cortical MRI parameters was evaluated using Spearman correlation analysis. The diagnostic performances of MRI parameters compared with biochemical indexes for detecting early DN were assessed using receiver operating characteristic curves.</p><p><strong>Results: </strong>Renal cortical MRI parameters demonstrated statistically significant differences among 3 groups(P < 0.050). The eGFR, 24 h-UA significantly correlated with renal cortical MRI parameters(P < 0. 001). The areas under the curve(AUCs) for discriminating diabetic patients group from DN patients group were 0.706, 0.864, 0.732, 0.718, 0.910 and 0.718 for D, f, MD, MK, RBF and T1 values. AUCs of renal cortical f, RBF values were significantly larger than that of eGFR, serum creatinine, 24 h-UA, fasting blood glucose(P < 0.050).</p><p><strong>Conclusions: </strong>Intravoxel incoherent motion diffusion-weighted imaging and arterial spin labeling exhibited considerable promise as noninvasive tools for detecting DN in high-risk patients with type 2 diabetes.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148535198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated morphometric segmentation analysis of hand X-ray image using deep learning network.","authors":"Yiyang Zhang, Zhukai Zhuang, Pengli Yu, Yachong Guo, Xiaocheng Shi, Wei Wang","doi":"10.1186/s12880-026-02511-z","DOIUrl":"https://doi.org/10.1186/s12880-026-02511-z","url":null,"abstract":"<p><strong>Background: </strong>The rapid development of deep learning in computer vision has led to increasing interest in its applications to medical image analysis. While many studies have focused on morphometric measurements from MR and CT images, comparatively few works have applied deep learning to extract morphometric features from hand X-ray images.</p><p><strong>Objectives: </strong>This research aims to establish a scheme for deep learning based automatic segmentation and morphology feature extraction of hand X-ray images with accuracy and efficiency.</p><p><strong>Methods: </strong>A total of 668 hand X-ray images from patients were obtained and were randomly classified as 498 training images(74.6%), 102 validation images(15.2%) and 68 testing images(10.2%). A combination of nnU-net and YOLO deep learning model is applied to perform the automatic segmentation. The outcomes were benchmarked against manual segmentations performed by experienced clinicians, enabling an assessment of the model's accuracy and overall performance. An in-house program was applied to the segmented part to extract the morphology features, such as Finger Bone Length(FBL) and Finger Bone Width(FBW).</p><p><strong>Results: </strong>For nnU-net training, the IoU score on the training dataset is 0.9596 and the IoU score on the validation dataset is 0.9584. For YOLOv8 training, we got an accuracy of 0.9816 and a loss of 0.0627. For feature extraction, the Pearson and Spearmann coefficient between automatic and manual results along with ICC shows the consistency of our automatic feature extraction method and human extracted method at a 95% confidence level, and the mean difference is close to zero. As a result, our scheme proved both accurate and precise.</p><p><strong>Conclusions: </strong>We present a two-stage, clinically interpretable workflow for hand X-ray analysis that combines nnU-Net-based hand ROI segmentation with YOLO bone-wise instance segmentation, followed by automated extraction of finger-bone morphometric indicators (FBL/FBW). Beyond reporting segmentation/detection metrics, we quantitatively validate the extracted morphometrics against expert measurements using correlation, ICC, and Bland-Altman analysis, demonstrating consistent bone-wise agreement and supporting the potential utility of the pipeline for standardized clinical measurements.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148535207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A combi-elasto ultrasound based deep learning model on liver fibrosis staging for suspected MASLD/MASH patients.","authors":"Daolin Xie, Fei Pei, Minghua Ying, Lei Ding, Shun Lv, Qiuping Zhao, Xin Li, Xiaoyan Wang","doi":"10.1186/s12880-026-02539-1","DOIUrl":"https://doi.org/10.1186/s12880-026-02539-1","url":null,"abstract":"<p><strong>Objectives: </strong>Metabolic dysfunction-associated steatotic liver disease (MASLD) and metabolic dysfunction-associated steatohepatitis (MASH) weakened the diagnostic ability of traditional elastography ultrasound on liver fibrosis. Combi-elasto ultrasound can simultaneously reflect the information of fibrosis degree and fat accumulation, thus have better potential and generality for liver fibrosis. We aim to develop a combi-elasto ultrasound based deep learning (DL) model for fibrosis staging in suspected MASLD/MASH patients.</p><p><strong>Methods: </strong>Patients with overweight, type-2 diabetes, hypertension or dyslipidemia, and without alcoholic, drug-induced, and genetic hepatitis history were defined as suspected MASLD/MASH patients. Fibrosis stages were classified as none or mild (F0/F1), moderate (F2), and severe (F3/F4). Combi-elasto images from ten centers were collected to build the DL model. OpenCV was applied to automatically extract image information, Resnet-50 was used to analyze image feature, and adversarial training (AT) algorithm was introduced to enhance model generality. Traditional DL model without AT algorithm, and other seven classical fibrosis models were also built to compare with AT-DL model. Subgroup analysis on pathological confirmed normal, MASLD and MASH patients were performed to test model generality.</p><p><strong>Results: </strong>From January 2022 to December 2023, 295 patients from eight centers were divided into training (n = 204) and validation (n = 91) sets. 101 patients from two independent centers were collected as external test set. In test set, AT-DL model achieved significantly higher accuracy than traditional DL model (0.871 vs. 0.812, p = 0.021) and all other classical models (0.545-0.762, all p < 0.05). For pathological confirmed normal patients, AT-DL and traditional DL models had comparable accuracy (0.881 vs. 0.905, p = 0.274). However, for pathological confirmed MASLD and MASH patients, AT-DL model showed significantly accuracy than traditional DL model (0.900 vs. 0.800, p = 0.028 and 0.828 vs. 0.690, p = 0.003).</p><p><strong>Conclusion: </strong>Combi-elasto ultrasound based AT-DL model had satisfactory performance on fibrosis staging in suspected MASLD/MASH patients, and could reliable non-invasive monitoring of fibrosis progression.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148496930","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":"Predicting local control of brain metastases after Gamma Knife radiosurgery: a multimodal deep learning-radiomics approach.","authors":"Minghui Zhao, Xiaofeng Ding, Xinchen Sun, Qun Chen, Jindong Li","doi":"10.1186/s12880-026-02579-7","DOIUrl":"https://doi.org/10.1186/s12880-026-02579-7","url":null,"abstract":"<p><strong>Background: </strong>Accurate prediction of local control (LC) following Gamma Knife radiosurgery (GKRS) remains clinically challenging for patients with brain metastases (BMs) secondary to breast or lung cancer. The scarcity of validated pre-therapeutic biomarkers currently hinders the development of individualized treatment decision-making strategies.</p><p><strong>Methods: </strong>This retrospective analysis included 324 BMs from 195 patients. To develop and benchmark various predictive frameworks, several models were constructed: clinical-only, radiomics-only, 2D deep learning (DL)-only, fused radiomics-DL (DLR), and a Combined model integrating all three modalities (clinical, radiomic, and DL features). All imaging signatures were derived from pre-treatment contrast-enhanced T1-weighted (T1CE) magnetic resonance imaging (MRI). Model performance was evaluated using the area under the curve (AUC), calibration plots, the Hosmer-Lemeshow test, and decision curve analysis (DCA).</p><p><strong>Results: </strong>The Combined model demonstrated consistently high numerical discriminative performance, achieving an AUC of 0.854 (95% Confidence Interval [CI]: 0.791-0.917) in the training cohort and 0.781 (95% CI: 0.618-0.945) in the independent test cohort. DCA demonstrated that the Combined model yielded superior net clinical benefit across threshold probabilities ranging from 10% to 50%, outperforming all other candidate models. Consequently, a nomogram based on the Combined model was developed to facilitate individualized risk estimation.</p><p><strong>Conclusions: </strong>The integration of clinical parameters, handcrafted radiomic features, and 2D deep learning signatures provides a robust predictive tool for LC following GKRS in patients with brain metastases from breast or lung cancer. This multimodal approach holds significant potential for refining post-radiosurgical management and advancing personalized neuro-oncology care.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148496915","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":"Predicting placenta accreta spectrum antenatally: a deep learning-radiomics dual-model based on intraoperative clinical and histopathologic criteria.","authors":"Yumin Hu, Chenqi Shen, Di Shen, Xiaojun Chen, Hongyan Zhao, Xia Li, Qing Zhou, Feng Shi, Yechao Huang, Wensong Xu, Chenying Lu","doi":"10.1186/s12880-026-02538-2","DOIUrl":"https://doi.org/10.1186/s12880-026-02538-2","url":null,"abstract":"<p><strong>Purpose: </strong>Definitive diagnosis of placenta accreta spectrum (PAS) disorders occurs at delivery by using combined intraoperative clinical and histopathologic diagnostic criteria per the recently updated International Federation of Gynecology and Obstetrics (FIGO) classification system. The purpose of this study is to construct a dual diagnostic model based on intraoperative clinical and histopathologic criteria for PAS in accordance with FIGO's diagnostic criteria.</p><p><strong>Materials and methods: </strong>This study pooled data from two centers. Diagnostic models based on histopathologic and intraoperative clinical criteria were separately developed using radiomics, deep learning, and clinical features. Subsequently, these individual models were integrated. Moreover, the correlations among clinical indicators, radiomics, and deep-learning features were explored. The Mann-Whitney U test was used for continuous variables with non-normal distribution. Categorical data were analyzed by Fisher's exact test or 2 × 2 or R×C χ2 test. A P value < 0.05 was considered significant.</p><p><strong>Results: </strong>For the FIGO intraoperative clinical criteria model, the fusion model's AUC was 0.964 (0.946-0.982) in the training set and 0.949 (0.902-0.996) in the test set. For the FIGO histopathologic criteria model, the training-set AUC was 0.961 (0.940-0.982), and the validation cohort AUC was 0.936 (0.883-0.990). In addition, several clinical factors and magnetic resonance imaging (MRI) features of PAS were found to correlate with radiomics scores and deep learning scores in both the intraoperative clinical and histopathologic criteria models.</p><p><strong>Conclusion: </strong>In this study, we constructed a dual model that includes FIGO intraoperative clinical and histopathologic criteria for predicting PAS. The two models that integrate deep learning, radiomics, and clinical features have good performance.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148468708","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":"Optimizing coronary artery disease management: the role of CT-derived fractional flow reserve in predicting revascularization and guiding clinical decisions.","authors":"Jian Huang, Tianyu Li, Mingrui Cui, Siyuan Lu, Jing Ye, Ji Zhang, Meng Zhu","doi":"10.1186/s12880-026-02594-8","DOIUrl":"https://doi.org/10.1186/s12880-026-02594-8","url":null,"abstract":"<p><strong>Objective: </strong>Coronary artery disease (CAD) is the most common heart disease, and invasive coronary angiography (ICA) has been recognized as the gold standard for diagnosing CAD. However, this method is influenced by inter-observer and intra-observer variability. The impact of machine learning (ML) algorithm-based fractional flow reserve CT (CT-FFR) software on the prediction of revascularization, the subsequent use of ICA, and the clinical decision-making for patients with suspected CAD remains to be studied. To evaluate the role of CT-FFR in the prediction of coronary revascularization and the optimization of treatment decisions.</p><p><strong>Methods: </strong>A retrospective study of 279 patients who underwent non-emergency CCTA and ICA within 90 days, with ≤ 0.80 indicating significant stenosis. Stenosis severity was categorized based on CCTA and ICA results. Consistency between CT-FFR, CCTA, and ICA was evaluated. Treatment decisions based on CT-FFR were compared to those based on CCTA and ICA, focusing on modifications between OMT and REV. The impact of CT-FFR on ICA utilization and its relationship with subsequent MACE incidence were also assessed.</p><p><strong>Results: </strong>CT-FFR demonstrated strong consistency with ICA (84.2%) and CCTA (78.5%). Median CT-FFR values declined with increasing stenosis severity (CCTA severe stenosis: 0.71; ICA severe stenosis: 0.70 ), confirming its diagnostic reliability. Among 188 patients with positive CT-FFR results, 75.5% underwent revascularization, reflecting high predictive accuracy. Treatment strategies were modified in 75 cases compared to ICA results and 60 cases compared to CCTA, optimizing decisions between OMT and REV. CT-FFR may reduce ICA utilization by 56.0% and the number of arteries requiring revascularization by 25.0%, improving procedural efficiency and reducing unnecessary interventions. Furthermore, CT-FFR demonstrated prognostic value as patients with positive results had a higher incidence of MACE. It also enhanced decision-making for non-obstructive arteries, significantly improving patient management and clinical outcomes.</p><p><strong>Conclusions: </strong>(1) CT-FFR demonstrated high consistency with the diagnostic results of both CCTA and ICA, and CT-FFR values showed a decreasing trend as the degree of stenosis increased. (2) CT-FFR based on deep learning algorithms exhibited high diagnostic performance in predicting revascularization. In addition, patients with positive CT-FFR results had approximately twice the risk of major adverse cardiovascular events (MACE) compared to those with negative results, suggesting its potential superiority in guiding ICA utilization and its promising capability for predicting clinical outcomes.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148468653","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}