Results
- Showing results for:
- Reset all filters
Search results
-
Journal articleTam KMM, Brown NC, Bronstein M, et al., 2026,
Learning constrained static equilibrium for thrust network inverse form-finding via physics-informed geometric deep learning on CW complexes
, Advanced Engineering Informatics, Vol: 70, ISSN: 1474-0346This work integrates Geometric Deep Learning (GDL) with physics-informed modelling to approximate solutions to a constrained, ill-conditioned, and nonlinear inverse shell form-finding problem across diverse geometries and patterns. Given a target geometry and pattern design as meshes, the proposed neural framework predicts a funicular shell—defined by edge forces and vertex positions—that satisfies static equilibrium and closely matches the target form. Three main contributions are introduced: (1) a relaxed, numerically stable physics objective using efficient differentiable graph operators to mitigate the ill-conditioning of the nonlinear problem; (2) a stochastic augmentation strategy that enriches training with geometries of varying funicular feasibility, enhancing generalisation to infeasible inputs; and (3) a hierarchical GDL architecture that learns directly from irregular n -gon surface meshes, modelled as cell complexes to incorporate vertex, edge, and face features in both inputs and outputs. This approach eliminates the need for simplification of graph datastructures common in existing methods, improving mesh modelling versatility. Extensive studies examine the numerical stability of physics formulations, robustness for out-of-distribution designs, and the expressivity of the GDL architecture. While focused on a specific inverse form-finding task, this work offers general insights into addressing ill-posed inverse problems, showing how physics-based learning can support optimisation of mesh-based architectural structures under variable connectivity and design constraints.
-
Journal articleCaravaca-Fontán F, Fakhouri F, Licht C, et al., 2026,
Delphi Consensus on Surrogate End Points in C3 Glomerulopathy and Primary Immune Complex–Mediated Membranoproliferative Glomerulonephritis
, Kidney International Reports, Vol: 11, ISSN: 2468-0249Introduction: C3 glomerulopathy (C3G) and primary immune complex–mediated membranoproliferative glomerulonephritis (IC-MPGN) are rare kidney diseases driven by complement dysregulation. Proteinuria is a commonly used clinical end point in trials involving these conditions. However, its recognition as a validated end point by regulatory bodies remains limited, despite growing evidence supporting its prognostic value as a surrogate biomarker for the development of kidney failure. The aim of this study was to establish consensus on the clinical relevance of proteinuria as a prognostic and treatment end point in C3G and primary IC-MPGN. Methods: A 2-round modified Delphi process was conducted, informed by literature review and expert input. A steering committee composed of 4 European nephrologists, 1 Canadian nephrologist, and 1 European rheumatologist developed 31 statements covering the following 3 domains: (i) treatment efficacy end points, (ii) current assessment end points, and (iii) the role of proteinuria. Statements formed part of an online survey using a 4-point Likert scale, distributed to a broader panel of nephrologists and kidney pathologists across Europe. Results: Fifty-one and 50 responses were received in rounds 1 and 2. Of the 31 statements, 29 reached consensus (≥ 75% agreement). Key consensus points included the following: (i) reduction in proteinuria preserves long-term kidney function and is a treatment goal; (ii) longitudinal monitoring of proteinuria, alongside other markers is valuable for guiding treatment; (iii) a ≥ 50% proteinuria reduction over 6 months indicates meaningful therapeutic benefit; and (iv) proteinuria < 1 g/d is associated with improved outcomes. Conclusion: This study demonstrates consensus supporting proteinuria as a meaningful treatment end point for C3G and primary IC-MPGN.
-
Journal articleKong E, Cucco A, Custovic A, et al., 2026,
Machine learning in allergy research: A bibliometric review
, IMMUNOLOGY LETTERS, Vol: 277, ISSN: 0165-2478 -
Conference paperQiao M, Zheng J, Zhang W, et al., 2026,
Mesh4D: A Motion-Aware Multi-view Variational Autoencoder for 3D+t Mesh Reconstruction
, Pages: 343-353, ISSN: 0302-9743Reconstructing temporally coherent 3D meshes of the beating heart from multi-view MR images is an important but challenging problem. The challenge is entangled by the complexity in integrating multi-view data, the sparse coverage of a 3D geometry by 2D image slices, and the interplay between geometry and motion. Current approaches often treat mesh reconstruction and motion estimation as two separate problems. Here we propose Mesh4D, a novel motion-aware method that jointly learns cardiac shape and motion, directly from multi-view MR image sequences. The method introduces three key innovations: (1) A cross-attention encoder that fuses multi-view image information, (2) A transformer-based variational autoencoder (VAE) that jointly model the image feature and motion, and (3) A deformation decoder that generates continuous deformation fields and temporally smooth 3D+t cardiac meshes. Incorporating geometric regularisation and motion consistency constraints, Mesh4D can reconstruct high-quality 3D+t meshes (7,698 vertices, 15,384 faces) of the heart ventricles across 50 time frames, within less than 3 s. When compared to existing approaches, Mesh4D achieves notable improvements in reconstruction accuracy and motion smoothness, offering an efficient image-to-mesh solution for quantifying shape and motion of the heart and creating digital heart models.
-
Conference paperMa Q, Meng Q, Qiao M, et al., 2026,
CardiacFlow: 3D+t Four-Chamber Cardiac Shape Completion and Generation via Flow Matching
, Pages: 89-99, ISSN: 0302-9743Learning 3D+t shape completion and generation from multi-view cardiac magnetic resonance (CMR) images requires a large amount of high-resolution 3D whole-heart segmentations (WHS) to capture shape priors. In this work, we leverage flow matching techniques to learn deep generative flows for augmentation, completion, and generation of 3D+t shapes of four cardiac chambers represented implicitly by segmentations. Firstly, we introduce a latent rectified flow to generate 3D cardiac shapes for data augmentation, learned from a limited number of 3D WHS data. Then, a label completion network is trained on both real and synthetic data to reconstruct 3D+t shapes from sparse multi-view CMR segmentations. Lastly, we propose CardiacFlow, a novel one-step generative flow model for efficient 3D+t four-chamber cardiac shape generation, conditioned on the periodic Gaussian kernel encoding of time frames. The experiments on the WHS datasets demonstrate that flow-based data augmentation reduces geometric errors by 16% in 3D shape completion. The evaluation on the UK Biobank dataset validates that CardiacFlow achieves superior generation quality and periodic consistency compared to existing baselines. The code of CardiacFlow is released publicly at https://github.com/m-qiang/CardiacFlow.
-
Conference paperZhang W, Qiao M, Zang C, et al., 2026,
Multi-agent Reasoning for Cardiovascular Imaging Phenotype Analysis
, Pages: 429-439, ISSN: 0302-9743Identifying the associations between imaging phenotypes and disease risk factors and outcomes is essential for understanding disease mechanisms and improving diagnosis and prognosis models. However, traditional approaches rely on human-driven hypothesis testing and selection of association factors, often overlooking complex, non-linear dependencies among imaging phenotypes and other multi-modal data. To address this, we introduce a Multi-agent Exploratory Synergy for the Heart (MESHAgents) framework that leverages large language models as agents to dynamically elicit, surface, and decide confounders and phenotypes in association studies, using cardiovascular imaging as a proof of concept. Specifically, we orchestrate a multi-disciplinary team of AI agents, which spontaneously generate and converge on insights through iterative, self-organizing reasoning. The framework dynamically synthesizes statistical correlations with multi-expert consensus, providing an automated pipeline for phenome-wide association studies (PheWAS). We demonstrate the system’s capabilities through a population-based study of imaging phenotypes of the heart and aorta. MESHAgents autonomously uncovered correlations between imaging phenotypes and a wide range of non-imaging factors, identifying additional confounder variables beyond standard demographic factors. Validation on diagnosis tasks reveals that MESHAgents-discovered phenotypes achieve performance comparable to expert-selected phenotypes, with mean AUC differences as small as -0.004<inf>±0.010</inf> on disease classification tasks. Notably, the recall score improves for 6 out of 9 disease types. Our framework provides clinically relevant imaging phenotypes with transparent reasoning, offering a scalable alternative to expert-driven methods.
-
Journal articleKavanagh D, Ariceta G, Vivarelli M, et al., 2026,
Current and Emerging Therapies for C3 Glomerulopathy and Primary (Idiopathic) Immune Complex Membranoproliferative Glomerulonephritis
, Kidney International Reports, Vol: 11, Pages: 17-31, ISSN: 2468-0249C3 glomerulopathy (C3G) and primary (idiopathic) immune complex membranoproliferative glomerulonephritis (IC-MPGN) are rare kidney diseases characterized by dysregulation of the complement system and progressive deposition of C3 and its breakdown products in the glomeruli, ultimately leading to kidney failure in up to 50% of patients within 10 years. Until recently, standard approaches to treatment included supportive measures common to many kidney diseases and immunosuppression to mitigate inflammation, rather than specific therapies addressing the underlying C3 dysregulation. However, recent advances in targeted complement inhibitor therapy have been made in these diseases with positive results from phase 3 clinical trials of both the factor B inhibitor, iptacopan (in adults with native kidney C3G) and the C3/C3b inhibitor, pegcetacoplan (in adults and adolescents with native or posttransplant C3G or primary IC-MPGN). In this review, we summarize what is known and what questions still remain regarding the effect of complement inhibitors on widely accepted surrogate end points for efficacy in C3G/primary IC-MPGN (proteinuria, estimated glomerular filtration rate [eGFR], and kidney biopsy histology). Additional controversies, including candidate patient populations, optimal treatment duration, and how best to monitor patients on complement inhibitor therapy are also discussed, in an effort to prepare the nephrology community for innovative therapeutic options for patients whose long-term prognosis has generally been dismal.
-
Journal articlePinato DJ, 2026,
Oncolytic virotherapy to reverse therapeutic resistance in advanced liver cancer.
, J Hepatol, Vol: 84, Pages: 233-234 -
Journal articleFeleszko W, Caminati M, Gern JE, et al., 2026,
Effect of tezepelumab on asthma exacerbations co-occurring with infection-attributed acute respiratory illnesses.
, Ann Allergy Asthma Immunol, Vol: 136, Pages: 61-65.e1BACKGROUND: Tezepelumab, a human monoclonal antibody, blocks the activity of thymic stromal lymphopoietin. In the phase 2b PATHWAY (NCT02054130) and phase 3 NAVIGATOR (NCT03347279) studies, tezepelumab reduced exacerbations and improved lung function, asthma control, and health-related quality of life vs placebo in patients with severe, uncontrolled asthma. OBJECTIVE: To evaluate the incidence of asthma exacerbations co-occurring with documented acute respiratory illnesses attributed to infections. METHODS: Patients were randomized 1:1 to receive tezepelumab 210 mg subcutaneously or placebo every 4 weeks for 52 weeks. The incidence of asthma exacerbations co-occurring with respiratory illness-related adverse events (AEs) was assessed. Co-occurrence was defined as at least 1 day of overlap between a respiratory illness-related AE and the asthma exacerbation period beginning 7 days before the start of the exacerbation until the end of the asthma exacerbation. RESULTS: Of the 1334 patients (tezepelumab, n = 665; placebo, n = 669) included, 312 experienced at least 1 asthma exacerbation co-occurring with a respiratory illness-related AE attributed to an infection. The incidence of asthma exacerbation co-occurring with a respiratory illness-related AE was lower in the tezepelumab group than in the placebo group overall (18.2% vs 28.6%; exposure-adjusted incidence difference [EAID], -11.1 [95% CI: -15.75, -6.41]) and among patients with perennial allergy (EAID, -11.6 [95% CI: -17.44, -5.69]) and without perennial allergy (EAID, -10.2 [95% CI: -18.16, -2.10]). CONCLUSION: Tezepelumab reduced asthma exacerbations attributed to respiratory infections in patients with severe, uncontrolled asthma compared with placebo, irrespective of perennial allergy status. TRIAL REGISTRATION: This is a pooled analysis of 2 studies registered at Clinicaltrials.gov: PATHWAY (NCT02054130) and NAVIGATOR (NCT03347279).
-
Journal articleHerzog MK-M, Peters A, Shayya N, et al., 2025,
Comparing <i>Campylobacter jejuni</i> to three other enteric pathogens in OligoMM<SUP>12</SUP> mice reveals pathogen-specific host and microbiota responses
, GUT MICROBES, Vol: 17, ISSN: 1949-0976- Cite
- Citations: 1
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.