Philips (China)

Hypoxic Ischemic Encephalopathy (HIE) represents a brain dysfunction, affecting approximately 1 to 5 per 1000 full-term neonates. The precise delineation and segmentation of HIE-related lesions in neonatal brain Magnetic Resonance Images (MRI) are pivotal in advancing outcome predictions, identifying patients at high risk, elucidating neurological manifestations, and assessing treatment efficacies. Despite its importance, the development of algorithms for segmenting HIE lesions from MRI volumes has been impeded by data scarcity. Addressing this critical gap, we organized the first BONBID-HIE challenge with diffusion MRI data (Apparent Diffusion Coefficient (ADC) maps) for HIE lesion segmentation, in conjunction with the MICCAI 2023. Totally 14 algorithms were submitted, employing a gamut of cutting-edge automatic machine-learning-based segmentation algorithms. Our comprehensive analysis of HIE lesion segmentation and submitted algorithms facilitates an in-depth evaluation of the current technological zenith, outlines directions for future advancements, and highlights persistent hurdles. To foster ongoing research and benchmarking, the annotated HIE dataset, developed algorithm dockers, and unified evaluation codes are accessible through a dedicated online platform (https://bonbid-hie2023.grand-challenge.org).

To compare two region-of-interest (ROI) measurement methods based on mDIXON-Quant for distinguishing healthy volunteers (HV), chronic kidney disease (CKD) patients with low (≤ 15%) and high (> 15%) glomerulosclerosis (GS), and establish a non-invasive auxiliary protocol. A total of 42 CKD patients and 25 HV underwent mDIXON-Quant MRI. CKD patients were stratified into low (n = 24) and high (n = 18) GS groups via renal biopsy. Two ROI methods were applied: Method 1 (cortex/medulla separation, 15–20 mm² circular ROIs at renal hilum, upper/lower poles) and Method 2 (whole-kidney contour tracing). R2* and fat fraction (FF) parameters were analyzed using ANOVA, LSD tests, and DeLong tests for diagnostic efficacy (AUC). R2* parameters (RcR2*, RR2*) showed significant differences across groups (P < 0.05), increasing with GS severity. LcR2* and RmR2* distinguished HV from high GS (P < 0.05), while LFF differentiated low vs. high GS (P < 0.05). Combining FF with R2* improved AUC from 0.685 to 0.877 (P < 0.05) for low/high GS discrimination. Method 1’s RcR2* (AUC = 0.957) and Method 2’s RR2* (AUC = 0.9) were most accurate for distinguishing high GS from HV, with no significant difference between them (P > 0.05). RcR2* outperformed medullary parameters (P < 0.05). The present study demonstrates that employing the Method 2(whole-kidney contour tracing) based on mDIXON-Quant technology enables auxiliary quantitative assessment of the severity of GS via the R2 parameter of the right kidney, thereby confirming its role as an adjunctive tool in GS evaluation.

To develop a radiomics model utilizing contrast-enhanced computed tomography (CECT) for predicting the prognosis of post-acute pancreatitis diabetes mellitus (PPDM-A) and to explain the model’s internal predictive mechanisms using Shapley Additive exPlanations (SHAP). 226 PPDM-A patients were retrospectively recruited from three centers, with 107 in training, 46 in internal, and 73 in external cohorts. There were 34, 15 and 28 patients with complications in each cohort. The complications included microvascular complications, infection, diabetic ketosis and hypoglycemia. In PPDM-A patients’ first pancreatitis episode, 2398 radiomics features were extracted from CECT images (arterial and venous phases). FeAture Explorer generated the machine learning pipeline and selected important radiomics features. Gaussian processes classifiers built radiomics and clinical-radiomics models, while Naive Bayes classifiers built the clinical model. The SHAP method was applied to provide insights into the model’s predictive process. The radiomics model predicted PPDM-A complications with the area under the receiver operating characteristic curve (AUC) of 0.95, 0.888, and 0.948 in training, internal, and external cohorts. In external cohort, the radiomics model significantly outperformed the clinical model (AUC 0.948 vs. 0.713, p = 0.002), while the combined model showed no significant difference from the radiomics model (AUC 0.933 vs. 0.948, p = 0.638). The SHAP technology provided physicians with insights into the global and individual impacts of radiomic features on model predictions. The CECT‑based radiomics model showed favorable prognostic performance for the prognosis of PPDM‑A. SHAP analysis interpreted the model’s mechanism, enhancing its clinical reliability and transparency.

Non-contrast coronary MR angiography (CMRA) is a validated, non-invasive, radiation-free technique for coronary stenosis assessment. However, its application to myocardial bridging (MB) is limited, with large-scale evidence for its diagnostic performance lacking. To evaluate the diagnostic accuracy and morphological consistency of non-contrast CMRA for detecting MB, using photon-counting coronary CT angiography (CCTA) as the reference standard. Retrospective. One hundred and ninety-six patients with suspected or confirmed coronary artery disease (men: 141; mean age: 62.9 ± 10.6 years) who underwent both photon-counting CCTA and CMRA. 3.0T; 3D nonselective pulse non-enhanced whole-heart balanced steady-state free precession sequence. The presence and morphology (location, length, depth, stenosis severity) of MB were assessed using both CMRA and CCTA and compared. Diagnostic performance for diagnosing MB using CMRA was calculated. Diagnostic performance was assessed using sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV); morphological characteristics of MB were compared using Bland-Altman analysis and intraclass correlation coefficients (ICC). A two-sided p < 0.05 indicated statistical significance. CCTA identified 92 MBs in 87 patients (44.4%; 82 single- and 5 multi-segment), and CMRA detected 89 MBs in 84 patients (42.9%; 79 single- and 5 multi-segment). CMRA had a diagnostic accuracy of 98.5%, sensitivity of 96.6%, specificity of 100%, NPV of 97.3%, and PPV of 100%. CMRA and CCTA demonstrated excellent agreement in the assessment of morphological characteristics for location (ICC = 0.98), length (ICC = 0.98), and depth (ICC = 0.98), with moderate agreement for stenosis severity (ICC = 0.71). Non-contrast CMRA showed excellent diagnostic performance for MB assessment and has potential to be a feasible, non-invasive, radiation-free, and contrast-free alternative to CCTA. Stage 2.

MR-HSG offers radiation-free multiplanar visualization for evaluating fallopian tube patency, but persistent challenges in achieving consistent high-quality visualization, particularly in smaller-diameter segments, limit clinical adoption. Previous studies modifying contrast viscosity achieved only partial improvements. This study aimed to use standardized phantom models simulating the female pelvis to systematically explore factors affecting MR-HSG image quality and provide evidence-based guidance for protocol optimization. Nine standardized phantoms were constructed using agar gel with embedded tubes of three inner diameters (4mm, 2mm, and 1.4mm) representing ampullary, isthmic, and interstitial segments. Three contrast agents with different viscosities were tested: gadolinium-saline (2.6 mPa·s), gadolinium-iopromide (7.9 mPa·s), and gadolinium-iodixanol (8.7 mPa·s) at 37°C. T1-weighted 3D-mDIXON sequences with keyhole technology were employed on a 1.5T MRI scanner. Signal intensity measurements and qualitative assessment (good/fair/poor) were performed by blinded evaluators. No significant differences in signal intensity were found between contrast agents of different viscosities (P>0.05). However, tube diameter significantly affected imaging quality (P<0.001). The 4 mm tubes showed the highest SI (5554.49±1042) with 100% good imaging, the 2 mm tubes showed intermediate SI (733.65±78.76) with 100% fair imaging, and the 1.4 mm tubes showed the lowest SI (444.55±34.70) with 100% poor imaging across all contrast agents. Fallopian tube inner diameter is the primary determinant of MR-HSG imaging quality, while contrast agent viscosity (within 2.6-8.7 mPa·s range) shows no significant effect under controlled conditions. This study provides foundational data for understanding physical factors affecting MRHSG quality and suggests that anatomical factors may be more critical than contrast properties for clinical protocol optimization, potentially reducing procedure costs while maintaining diagnostic quality. Optimizing spatial resolution to minimize partial volume effects may be more beneficial than modifying contrast agent properties for improving visualization of narrow fallopian tube segments. Clinical validation studies are warranted to confirm these findings in the complex in vivo environment.

Reoperation for papillary thyroid carcinoma (PTC) requires precise lymph node metastasis assessment, yet ultrasound (US) alone may be insufficient in complex or high-risk cases. This study evaluated whether supplementing US with magnetic resonance imaging (MRI) improves surgical guidance and outcomes in reoperation. We retrospectively analyzed 375 patients who underwent reoperation between 2014 and 2022. Propensity score matching yielded 101 patients in the USUS-only group and 62 in the US+MRI group. Pathological and imaging data were compared to assess diagnostic performance, surgical outcomes, biochemical responses, and recurrence-free survival. The combined approach significantly increased sensitivity for detecting central lymph node metastasis from 52.5% to 90.9% and resulted in higher rates of central neck dissections (65.1% versus 45.5%) with greater lymph node yield (median: 29 versus 20) but lower lymph node ratios. More patients in the combined group achieved excellent biochemical responses (50.0% versus 27.7%). While overall recurrence-free survival (RFS) was not significantly different, the US+MRI group showed improved RFS among patients with ≥2 positive central nodes (HR = 0.24, p = 0.032). Importantly, complication rates were comparable, suggesting that improved outcomes were achieved without added surgical risk. Combined US and MRI assessment enhances diagnostic performance and may improve surgical and oncological outcomes in select high-risk patients undergoing PTC reoperation.

ObjectivesTo evaluate the value of quantitative parameters and radiomic features based on dual-layer spectral detector CT (DLCT) in predicting spread through air spaces (STAS) of lung adenocarcinoma (LUAD).MethodsThis study analyzed 266 patients with pathologically confirmed LUAD from two medical centers. Patients from center 1 were divided into training (n = 131) and internal validation (n = 57) sets, while center 2 (n = 78) formed the external validation set. Clinical data, conventional imaging features, and DLCT quantitative parameters were analyzed to develop a clinical-radiological model. Radiomic features were extracted from venous-phase images, including conventional images, virtual monoenergetic images (VMI) at 40 keV, 65 keV, and 100 keV, along with iodine density maps, effective atomic number (Zeff) maps, and electron density (ED) maps. The best-performing radiomics model was combined with clinical-radiological predictors to create a nomogram. Model performance was evaluated through ROC analysis, calibration curves, and decision curve analysis.ResultsMultivariate analysis revealed that tumor-lung interface and ED values were independent predictive factors in the clinical-radiological model. The optimal radiomics model was constructed based on VMI 40 keV, demonstrating AUCs of 0.899, 0.835, and 0.828 in the training, internal validation, and external validation sets, respectively. The nomogram, which incorporated the VMI 40 keV radiomics signature along with tumor-lung interface and ED values, outperformed the clinical-radiological model in the training set (AUC = 0.910 vs. 0.870; P = 0.018) and the internal validation set (AUC = 0.868 vs. 0.798; P = 0.046). While the improvement in the external validation set was not statistically significant (AUC = 0.848 vs. 0.819; P = 0.184).ConclusionThe nomogram, which integrates conventional imaging features, DLCT quantitative parameters and VMI 40 keV radiomic features, demonstrates promising performance and represents a potential valuable non-invasive tool for the preoperative assessment of STAS in LUAD.Supplementary InformationThe online version contains supplementary material available at 10.1186/s12885-025-15436-7.

Background:Atrial fibrillation (AF) is a major complication of hypertrophic cardiomyopathy (HCM) with significant prognostic implications. Current risk prediction models lack the integration of comprehensive cardiac magnetic resonance (CMR) metrics and subtype-specific analyses.Methods:A retrospective study of 405 HCM patients (86 with AF) was performed from 2019 to 2024. After excluding highly correlated variables (|r| > 0.8), the cohort was split into training and validation sets in a 7:3 ratio. Least Absolute Shrinkage and Selection Operator (LASSO) regression and multivariable logistic regression analyses were used to identify predictors, with model performance assessed via receiver operating characteristic (ROC) curves, calibration plots, and decision curve analysis. Subgroup analyses were conducted for obstructive (HOCM) and non-obstructive (HNCM) subtypes.Results:Independent predictors of AF in the overall HCM cohort included right atrial diameter anteroposterior (RAD anteroposterior: odds ratio (OR) = 1.819, 95% confidence interval (CI) 1.130–3.007; p = 0.016), left ventricular end-systolic volume (LVESV: OR = 0.978, 95% CI 0.963–0.991; p = 0.002), septal mitral annular plane systolic excursion (MAPSE septal: OR = 0.850, 95% CI 0.736–0.976; p = 0.023), tricuspid annular plane systolic excursion (TAPSE: OR = 0.919, 95% CI 0.852–0.987; p = 0.022), and maximum left atrial volume (MaxLAV: OR = 1.016, 95% CI 1.004–1.029; p = 0.010). The model achieved an area under the curve (AUC) value of 0.850 in the training set and an AUC of 0.861 in the validation set. The HOCM subtype predictors included septal MAPSE and left atrial ejection fraction (LAEF); meanwhile, the HNCM predictors included septal MAPSE, maximal left atrial volume (MaxLAV), and right atrial ejection fraction (RAEF).Conclusions:A validated multiparametric CMR model can accurately predict AF risk in HCM patients, with subtype-specific predictors enabling personalized monitoring and early intervention.

Environmental, Social and Governance (ESG) criteria have emerged as fundamental pillars for evaluating corporate sustainability, ethical stewardship and governance practices, increasingly guiding investor strategies and public trust. Amid escalating climate challenges, social inequalities and regulatory pressures, transparent and comprehensive ESG reporting has become imperative for enterprises to ensure compliance, attract responsible investment and build long-term resilience. However, ESG reports are inherently complex, encompassing unstructured narratives alongside dense visual data—such as graphs, flowcharts and images—that carry critical contextual and quantitative insights. Traditional text-based language models and document retrieval systems do not address these multimodal complexities, often overlooking or misinterpreting visual components essential for a nuanced assessment of ESG. To bridge this gap, this research introduces an enterprise-grade multimodal Retrieval-Augmented Generation (RAG) framework that goes beyond conventional text embeddings by integrating advanced image, chart and layout processing capabilities. This multimodal approach not only enables dynamic retrieval of external domain knowledge but also ensures contextually precise, holistic insights into ESG disclosures, empowering enterprises with an intelligent, scalable tool to navigate the multifaceted landscape of modern ESG reporting.The empirical evaluation demonstrates a measurable improvement of 6.5% in mean average precision over the strongest prior baseline, validating the framework’s ability to deliver quantifiable enhancements in ESG report analysis.