BMC Medical Imaging最新文献

{"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":"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":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13670486/pdf/","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":"OA","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":"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":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13660289/pdf/","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":"OA","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":"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":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13660128/pdf/","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":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A CT-based deep learning model for the automated risk stratification of refractory Mycoplasma pneumoniae pneumonia in children.","authors":"Zhoumeng Ying, Ge Hu, Jing Li, Wei Han, Fei Yang, Zheming Li, Zhenchen Zhu, Baofeng Zhang, Zhen Zhou, Weixiong Tan, Zhu Zhu, Mengyu Duan, Zhengyu Jin, Lan Song, Gang Yu","doi":"10.1186/s12880-026-02590-y","DOIUrl":"10.1186/s12880-026-02590-y","url":null,"abstract":"<p><strong>Background: </strong>The accurate identification of children with refractory Mycoplasma pneumoniae pneumonia (RMPP) remains challenging. This study aimed to develop a transformer-based model utilizing clinically indicated chest computed tomography (CT) to stratify pediatric RMPP risk at a critical decision point.</p><p><strong>Methods: </strong>Non-contrast chest CT data from a multicenter retrospective cohort of 1224 pediatric patients with Mycoplasma pneumoniae pneumonia who underwent clinically indicated CT were used to develop a transformer-based deep learning framework (trans-DLF). The primary cohort comprised training (n = 506), validation (n = 140), and internal testing (n = 139) cohorts, with two independent external cohorts (n = 331 and n = 108) used to evaluate generalizability. Model performance was assessed by the area under the receiver operating characteristic curve (AUC) and compared against a three-dimensional convolutional neural network (3D-CNN), a clinical model, and a multimodal nomogram. Interpretability was examined using gradient-weighted class activation mapping (Grad-CAM).</p><p><strong>Results: </strong>The median age was 6.83 years (interquartile range, 5.0-8.6 years), and 609 (49.8%) were male. The trans-DLF demonstrated strong performance across all cohorts: training (AUC 0.97; 95% confidence interval [CI], 0.96-0.98), validation (0.91; 0.86-0.96), internal testing (0.90; 0.85-0.95), and external testing (0.89; 0.84-0.94 and 0.89; 0.82-0.95). It significantly outperformed the clinical model (p < 0.001), while its AUCs were not significantly different from those of the multimodal nomogram. The model maintained good performance in outpatient settings (AUC 0.87) with good calibration and net clinical benefit. Grad-CAM suggested that predictions were influenced by clinically meaningful features, particularly consolidations.</p><p><strong>Conclusion: </strong>The trans-DLF provides a streamlined and efficient approach to RMPP risk assessment in children who have already undergone clinically indicated chest CT and may support timely, evidence-based decision-making without additional tests.</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":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13660281/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148468638","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":"Pre-treatment MRI-derived fractal dimension as a prognostic marker in cervical cancer treated with definitive radiotherapy with or without concurrent chemotherapy.","authors":"Sedef Gökhan Açıkgöz, Ayfer Bakır, Büşra Demir Çendek, Havva Beyaz, Süheyla Aytaç Arslan, Fevziye İlknur Kayalı, Rahşan Habiboğlu, Yılmaz Tezcan","doi":"10.1186/s12880-026-02589-5","DOIUrl":"10.1186/s12880-026-02589-5","url":null,"abstract":"<p><strong>Background: </strong>Pre-treatment magnetic resonance imaging (MRI) plays a central role in local staging and treatment planning for cervical cancer. Fractal dimension (FD) analysis quantifies tumor structural complexity on MRI and has emerged as a non-invasive imaging biomarker. This study aimed to evaluate the prognostic significance of MRI-derived FD in patients with cervical cancer treated with definitive radiotherapy (RT) with or without concurrent chemotherapy (CCRT).</p><p><strong>Methods: </strong>This retrospective study included 84 patients with histologically confirmed cervical cancer treated with definitive RT, most of whom received concurrent chemotherapy (CCRT), between 2019 and 2025. FD was calculated from pre-treatment T2-weighted MRI using the box-counting method. Fractal analysis was performed on axial, coronal, and sagittal planes, and the mean FD was obtained by averaging values across all planes. Associations between FD and HPV/p16 status, baseline hemoglobin levels, FIGO stage, and tumor volume were assessed using Spearman correlation analysis. Progression-free survival (PFS) and overall survival (OS) were analyzed using Cox proportional hazards regression models.</p><p><strong>Results: </strong>The median FD was 1.44 (range: 1.20-1.61). FD showed a weak but statistically significant positive correlation with FIGO stage (p = 0.024) and a moderate positive correlation with tumor volume (p < 0.001). No significant associations were observed between FD and HPV/p16 status or baseline hemoglobin levels (p > 0.05). Each 0.1-unit increase in FD was significantly associated with worse OS (hazard ratio [HR] = 4.668, p < 0.001) and PFS (HR = 4.769, p < 0.001). FD was not significantly associated with local recurrence or distant metastasis.</p><p><strong>Conclusions: </strong>MRI-based fractal analysis may provide a quantitative measure of tumor morphological complexity and intratumoral heterogeneity and demonstrates a significant association with survival outcomes in cervical cancer patients treated with definitive RT or CCRT. FD analysis, derived from routine pre-treatment MRI, may complement conventional clinical parameters for risk stratification; however, further validation in larger and less selected patient cohorts is required.</p><p><strong>Trial registration: </strong>Not applicable.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13556101/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148468692","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":"PatchGAN-guided semi-supervised U-Net for carotid plaque segmentation in ultrasound under limited annotation conditions.","authors":"Saritha Lalitha Ravindran, Dipti Jadhav, Sandeep Sangle, Pankaj Kumar Jain, Andrew Nicolaides, Luca Saba, Ajith Abraham, Jasjit S Suri","doi":"10.1186/s12880-026-02574-y","DOIUrl":"10.1186/s12880-026-02574-y","url":null,"abstract":"<p><strong>Objective: </strong>Artificial intelligence models are increasingly used for stroke risk evaluation and clinical decision-making. However, the scarcity of expert masks, low contrast, and noise in ultrasound images affect segmentation performance.</p><p><strong>Methods: </strong>Our study innovatively integrated an adversarial PatchGAN discriminator into a batch-normalized semi-supervised U-Net generator to enhance carotid plaque segmentation in ultrasound images with limited expert annotation. The discriminator provides patch-level localized feedback to enhance boundary delineation and structural consistency of the predicted masks. The model was trained using a hybrid loss function and self-training strategy. The performance of our framework was compared with a fine-tuned semi-supervised U-Net model. Both frameworks were trained under identical experimental settings using 30% of the labeled data; the remaining unlabeled images were utilized to generate pseudo-labels for data augmentation. A confidence threshold of 0.7 was applied to filter unreliable predictions.</p><p><strong>Results: </strong>We conducted experiments on a dataset of 970 internal carotid artery ultrasound images from the Imperial College of London, UK. The experimental results showed that the proposed framework achieved a Dice coefficient of 86.12 and a Jaccard index of 75.66, outperforming the baseline U-Net (84.22 and 73.12, respectively).</p><p><strong>Conclusions: </strong>The integration of patch-level adversarial feedback into a semi-supervised framework enhanced the segmentation accuracy and improved the reliability of pseudo-labels under limited supervision. The results were comparable to those of state-of-the-art deep learning models, which require a large pool of labeled data.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13656442/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148468682","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 sex-specific reference values of Evans' Index and cranial dimensions on brain CT in a south-eastern Nigerian hospital population.","authors":"Ebere Ibezim, Chinedu Anthony Iwu, Michael Agogbuo","doi":"10.1186/s12880-026-02591-x","DOIUrl":"10.1186/s12880-026-02591-x","url":null,"abstract":"<p><strong>Background: </strong>Evans' Index (EI) is a widely used linear radiological measure of ventricular size on computed tomography (CT) and magnetic resonance imaging. Despite the increasing use of volumetric neuroimaging techniques, EI remains a practical and commonly applied marker of ventricular enlargement in routine clinical practice. However, age- and sex-specific hospital-based reference values are limited in sub-Saharan Africa, where population-specific data are essential for accurate interpretation. This study aimed to establish age- and sex-specific hospital-based reference values for Evans' Index and cranial dimensions in a south-eastern Nigerian population using CT scans reported as normal despite clinical indications.</p><p><strong>Methods: </strong>This retrospective cross-sectional study analysed 676 normal non-contrast cranial CT scans. Maximum anterior horn diameter (MAHD) and maximum internal cranial diameter (MICD) were measured at the level of the frontal horns, and EI was calculated as MAHD/MICD. Results from the non-normally distributed data were presented as median with quartile ranges (Q1-Q3) and percentile-based reference ranges (2.5th-97.5th percentiles). Associations with age and sex were assessed using non-parametric tests, and measurement reproducibility was evaluated using intraclass correlation coefficient analysis.</p><p><strong>Results: </strong>Of the 676 participants, 268 (39.6%) were male and 408 (60.4%) were female. The overall median Evans' Index (EI) was 0.28 (Q1-Q3: 0.25-0.30), with a 95% reference range of 0.22-0.32. Females had significantly higher median EI (0.29 vs. 0.26) and larger MAHD compared with males, whereas males had significantly larger MICD (all p < 0.001, Mann-Whitney U test). EI demonstrated a strong positive correlation with age (Spearman's ρ = 0.746; p < 0.001), and multivariable regression analysis confirmed age as an independent predictor of EI. Significant differences in EI, MAHD, and MICD were observed across age groups (Kruskal-Wallis p < 0.001 for all). Median EI increased progressively across age categories (0.24 in 1-18 years, 0.26 in 19-50 years, 0.29 in 51-80 years, and 0.30 in ≥ 81 years), with corresponding increases in MAHD and a modest decline in MICD in older age groups.</p><p><strong>Conclusions: </strong>Evans' Index and cranial dimensions in south-eastern Nigeria vary significantly by age and sex. These hospital-based reference values are consistent with commonly used EI thresholds (≥ 0.30 for ventriculomegaly) while emphasising the need for age- and sex-stratified interpretation in clinical practice. These hospital-based reference values are derived from radiologically normal CT scans obtained during clinically indicated imaging and may not fully represent community-based healthy populations.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13651271/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148454464","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 progressive learning reconstruction for fast and low-dose whole-body PET scans in an integrated PET/MR system.","authors":"Jie Ding, Yihong Yang, Zhe Wang, Haiyan Wang, Na Qi, Zirong Zhou, Xing Chen, Zhiwen You, Chen Xi, Zheng Qian, Lingzhi Hu, Jianmin Yuan, Jun Zhao","doi":"10.1186/s12880-026-02568-w","DOIUrl":"10.1186/s12880-026-02568-w","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;PET/MR combines molecular and functional imaging but faces challenges such as prolonged scans, noise from reduced tracer activity, and suboptimal reconstruction methods (e.g., OSEM). Deep learning techniques, such as deep progressive learning (DPL), show promise in enhancing low-tracer activity PET/CT imaging but remain understudied for PET/MR. As MR acquisition continues to accelerate through technological advances, adaptive PET reconstruction methods will become increasingly important for maintaining overall throughput in integrated PET/MR protocols. This study evaluates DPL on a uPMR790 PET/MR system to determine its potential for reducing injected activity or scan durations in whole-body [&lt;sup&gt;18&lt;/sup&gt;F]FDG PET/MR while preserving image quality.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;In our study, we included 115 patients for whole-body PET/MR examinations, of whom 100 received a full injected activity of [&lt;sup&gt;18&lt;/sup&gt;F]FDG, and 15 received injected activity with half the activity. The list mode PET data from the patients were reorganized to reconstruct PET raw data for each bed position for 420, 210, 140, and 105 s, simulating 1/n (n = 1, 2, 3, 4) of the acquisition time. PET reconstructions were performed using two different methods: ordered subset expectation maximization (OSEM) and DPL [divided into three levels (1, 2, 3)]. In terms of subjective assessment, we conducted a five-point Likert scale visual analysis. For quantitative assessment, we measured the standardized uptake value (SUV) and assessed image quality using the signal-to-noise ratio (SNR), contrast, contrast-to-noise ratio (CNR), coefficient of variation (COV), and target-to-background ratio (TBR).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;According to subjective visual assessment methods, DPL scores were significantly higher than OSEM, with DPL1 achieving the highest scores. The advantage of DPL1 became more pronounced with shorter reconstruction times. In both the full injected activity and half injected activity groups, at one-quarter of the reconstruction time, the average Likert visual scores for OSEM and DPL1 were 2.36 vs. 4.01 in the full injected activity group and 1.23 vs. 3.21 in the half injected activity group, respectively (P &lt; 0.01). Compared to the OSEM group, the DPL1 group exhibited significantly improved image quality with markedly reduced noise; the SNR, CNR, contrast, COV, and TBR values were all significantly higher than those of OSEM. These gains were still observable in obese patients within the DPL1 group. There were no significant differences in the lesion SUVmax and SUVmean measured between the OSEM and DPL1 groups (all P &gt; 0.05); however, lesion volumes measured from DPL1 were smaller than those in the OSEM group.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;DPL reconstruction suggests that it may be feasible to reduce the administered activity of [&lt;sup&gt;18&lt;/sup&gt;F]FDG to half or decrease the scanning time to one-quarter in whole-body PET/MR i","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13651066/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148454414","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":"Quantitative CMR-derived pulmonary circulation imaging biomarkers in recent-onset dilated cardiomyopathy associated with pulmonary hemodynamics and clinical improvement.","authors":"Lukáš Opatřil, Mary Luz Mojica-Pisciotti, Roman Panovský, Jan Máchal, Tomáš Holeček, Věra Feitová, Július Godava, Hana Poloczková, Vladimír Kincl, Jan Krejčí","doi":"10.1186/s12880-026-02566-y","DOIUrl":"10.1186/s12880-026-02566-y","url":null,"abstract":"<p><strong>Background: </strong>Recent-onset dilated cardiomyopathy (RODCM), defined as new DCM with heart failure (HF) symptoms appearing within six months, is a less documented form of HF. This study aims to evaluate pulmonary circulation imaging biomarkers (PCIB) obtained by cardiovascular magnetic resonance (CMR) in patients with RODCM to assess their association with pulmonary hypertension, systolic and diastolic function, and clinical improvement.</p><p><strong>Methods: </strong>Ninety RODCM patients with baseline and one-year follow-up CMR, clinical examination, and transthoracic echocardiography were retrospectively included. Twenty-six were excluded following a myocarditis diagnosis confirmed by endomyocardial biopsy (EMB). PCIB (pulmonary transit time (PTT), corrected PTT (PTTc), pulmonary transit beats (PTB), and pulmonary blood volume index (PBVI)) were assessed using a first-pass perfusion CMR sequence. Pulmonary hypertension, diastolic, and systolic function were assessed. Correlations between PCIB and echocardiographic changes were analyzed. Patients were classified as responders/non-responders based on left ventricular ejection fraction (LVEF) improvement.</p><p><strong>Results: </strong>From baseline to follow-up, LVEF increased (25% to 40%), while EDD (65 mm to 61 mm), sPAP (24.2 mmHg to 20.0 mmHg), and E/e' ratio (13 to 9) significantly reduced. Thirty-three patients were labeled as responders. PTT, PTTc, and PTB correlated with ΔE/e', diastolic function improvement, and ΔsPAP. PBVI correlated with ΔsPAP. PTB correlated with ΔNYHA class. The PCIB could not predict whether a patient would be a responder.</p><p><strong>Conclusions: </strong>This study focused on PCIB as outcome predictors in patients with RODCM with EMB-excluded myocarditis. Our findings show that PTB and PTTc correlated with ΔE/e', diastolic function improvement, and ΔsPAP, while PTB additionally correlated with ΔNYHA class.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13651362/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148454431","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":"Association between first-trimester chorionic bump and early pregnancy loss: a two-center retrospective study with exploratory radiomics analysis.","authors":"Jie Shen, Yipeng Zhao, Zhina Wu, Yizhi Wu, Bishi He, Zhe Xu, Nannan Chen, Junmiao Xiang","doi":"10.1186/s12880-026-02577-9","DOIUrl":"10.1186/s12880-026-02577-9","url":null,"abstract":"<p><strong>Introduction: </strong>The chorionic bump (CB) is a rare sonographic finding defined as an irregular protrusion from the choriodecidual surface into the gestational sac. Its prognostic significance regarding pregnancy loss remains controversial. This study aimed to evaluate the association between first-trimester CB and pregnancy outcomes and to investigate whether ultrasonographic radiomic features can support early risk stratification.</p><p><strong>Methods: </strong>This two-center retrospective study included 184 women diagnosed with a CB and 1052 matched controls between January 2020 and December 2024. All participants underwent transvaginal ultrasound at 5-10 weeks of gestation. Radiomic features were extracted from regions of interest using PyRadiomics. Furthermore, logistic regression, support vector machine (SVM), and random forest (RF)-alongside SHAP analysis, were employed to analyze the ultrasonographic radiomic features.</p><p><strong>Results: </strong>Sonographically, CB exhibited variable echogenicity and an absence of internal blood flow on color Doppler flow imaging. While no significant differences were found in other secondary pregnancy outcomes, CB was strongly associated with early pregnancy loss. Following feature selection, the optimized RF_Sel model achieved an AUROC of 0.573, accuracy of 0.538, and a precision of 0.539. SHAP analysis identified \"original_firstorder_Minimum\" (first-order minimum intensity) as the feature with the highest decision-making value. Furthermore, lower grayscale minimum intensity on ultrasound, smaller gestational sac (GS) volume, and a higher CB-to-GS volume ratio were identified as significant risk factors for pregnancy loss within the CB population.</p><p><strong>Conclusions: </strong>A first-trimester CB is a significant high-risk factor for early pregnancy loss. However, the radiomics-based model demonstrated limited predictive performance, indicating that radiomic features alone are currently insufficient for clinical risk stratification and should be considered hypothesis-generating. The early sonographic identification of a CB remains vital for assessing clinical risk and guiding obstetric management.</p>","PeriodicalId":9020,"journal":{"name":"BMC Medical Imaging","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13656662/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148454422","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}