Mengyun Qiao

Berke Doga Basaran, Mengyun Qiao, Paul M. Matthews et al.

Understanding the intensity characteristics of brain lesions is key for defining image-based biomarkers in neurological studies and for predicting disease burden and outcome. In this work, we present a novel foreground-based generative method for modelling the local lesion characteristics that can both generate synthetic lesions on healthy images and synthesize subject-specific pseudo-healthy images from pathological images. Furthermore, the proposed method can be used as a data augmentation module to generate synthetic images for training brain image segmentation networks. Experiments on multiple sclerosis (MS) brain images acquired on magnetic resonance imaging (MRI) demonstrate that the proposed method can generate highly realistic pseudo-healthy and pseudo-pathological brain images. Data augmentation using the synthetic images improves the brain image segmentation performance compared to traditional data augmentation methods as well as a recent lesion-aware data augmentation technique, CarveMix. The code will be released at https://github.com/dogabasaran/lesion-synthesis.

Hadrien Reynaud, Mengyun Qiao, Mischa Dombrowski et al.

Image synthesis is expected to provide value for the translation of machine learning methods into clinical practice. Fundamental problems like model robustness, domain transfer, causal modelling, and operator training become approachable through synthetic data. Especially, heavily operator-dependant modalities like Ultrasound imaging require robust frameworks for image and video generation. So far, video generation has only been possible by providing input data that is as rich as the output data, e.g., image sequence plus conditioning in, video out. However, clinical documentation is usually scarce and only single images are reported and stored, thus retrospective patient-specific analysis or the generation of rich training data becomes impossible with current approaches. In this paper, we extend elucidated diffusion models for video modelling to generate plausible video sequences from single images and arbitrary conditioning with clinical parameters. We explore this idea within the context of echocardiograms by looking into the variation of the Left Ventricle Ejection Fraction, the most essential clinical metric gained from these examinations. We use the publicly available EchoNet-Dynamic dataset for all our experiments. Our image to sequence approach achieves an $R^2$ score of 93%, which is 38 points higher than recently proposed sequence to sequence generation methods. Code and models will be available at: https://github.com/HReynaud/EchoDiffusion.

Berke Doga Basaran, Weitong Zhang, Mengyun Qiao et al.

Data augmentation has become a de facto component of deep learning-based medical image segmentation methods. Most data augmentation techniques used in medical imaging focus on spatial and intensity transformations to improve the diversity of training images. They are often designed at the image level, augmenting the full image, and do not pay attention to specific abnormalities within the image. Here, we present LesionMix, a novel and simple lesion-aware data augmentation method. It performs augmentation at the lesion level, increasing the diversity of lesion shape, location, intensity and load distribution, and allowing both lesion populating and inpainting. Experiments on different modalities and different lesion datasets, including four brain MR lesion datasets and one liver CT lesion dataset, demonstrate that LesionMix achieves promising performance in lesion image segmentation, outperforming several recent Mix-based data augmentation methods. The code will be released at https://github.com/dogabasaran/lesionmix.

Mengyun Qiao, Berke Doga Basaran, Huaqi Qiu et al.

Cardiovascular disease, the leading cause of death globally, is an age-related disease. Understanding the morphological and functional changes of the heart during ageing is a key scientific question, the answer to which will help us define important risk factors of cardiovascular disease and monitor disease progression. In this work, we propose a novel conditional generative model to describe the changes of 3D anatomy of the heart during ageing. The proposed model is flexible and allows integration of multiple clinical factors (e.g. age, gender) into the generating process. We train the model on a large-scale cross-sectional dataset of cardiac anatomies and evaluate on both cross-sectional and longitudinal datasets. The model demonstrates excellent performance in predicting the longitudinal evolution of the ageing heart and modelling its data distribution. The codes are available at https://github.com/MengyunQ/AgeHeart.

Mengyun Qiao, Shuo Wang, Huaqi Qiu et al.

Two key questions in cardiac image analysis are to assess the anatomy and motion of the heart from images; and to understand how they are associated with non-imaging clinical factors such as gender, age and diseases. While the first question can often be addressed by image segmentation and motion tracking algorithms, our capability to model and to answer the second question is still limited. In this work, we propose a novel conditional generative model to describe the 4D spatio-temporal anatomy of the heart and its interaction with non-imaging clinical factors. The clinical factors are integrated as the conditions of the generative modelling, which allows us to investigate how these factors influence the cardiac anatomy. We evaluate the model performance in mainly two tasks, anatomical sequence completion and sequence generation. The model achieves a high performance in anatomical sequence completion, comparable to or outperforming other state-of-the-art generative models. In terms of sequence generation, given clinical conditions, the model can generate realistic synthetic 4D sequential anatomies that share similar distributions with the real data.

Che Liu, Sibo Cheng, Chen Chen et al.

Medical vision-language models enable co-learning and integrating features from medical imaging and clinical text. However, these models are not easy to train and the latent representation space can be complex. Here we propose a novel way for pre-training and regularising medical vision-language models. The proposed method, named Medical vision-language pre-training with Frozen language models and Latent spAce Geometry optimization (M-FLAG), leverages a frozen language model for training stability and efficiency and introduces a novel orthogonality loss to harmonize the latent space geometry. We demonstrate the potential of the pre-trained model on three downstream tasks: medical image classification, segmentation, and object detection. Extensive experiments across five public datasets demonstrate that M-FLAG significantly outperforms existing medical vision-language pre-training approaches and reduces the number of parameters by 78\%. Notably, M-FLAG achieves outstanding performance on the segmentation task while using only 1\% of the RSNA dataset, even outperforming ImageNet pre-trained models that have been fine-tuned using 100\% of the data.

Luca Hagen, Johanna P. Müller, Weitong Zhang et al.

Small vision-language models (2-8B) are well-suited for clin- ical deployment due to privacy constraints, limited connectivity, and low-latency requirements favouring on-device or on-premise inference. However, their limited capacity exacerbates the generation of plausible but incorrect outputs. We extend game-theoretic decoding, previously restricted to text-only, closed-ended NLP tasks, to vision-language mod- els for open-ended Medical VQA. We introduce a semantically aware Wasserstein stopping criterion that replaces lexical order matching, en- abling convergence based on semantic consensus among near-synonymous candidate answers and avoiding unnecessary iterations caused by clini- cally equivalent ranking swaps. On VQA-RAD and PathVQA, we ob- tain consistent, statistically significant improvements over greedy and discriminative baselines. On VQA-RAD, we improve Qwen3-VL-2B by +3.5 percentage points (p < 0.01), surpassing the greedy 4B model, with similar trends at larger scales. On PathVQA, Gemma-3-4B with BDG matches MedGemma-4B under greedy decoding despite no domain- specific fine-tuning. At accuracy parity with classic BDG, the Wasser- stein criterion reduces average convergence iterations by approximately 20%, improving inference efficiency while preserving the game-theoretic equilibrium behaviour. Code is available at https://github.com/luca-hagen/ Wasserstein-BDG-medical-VQA.

Mengyun Qiao, Kathryn A McGurk, Shuo Wang et al.

Understanding the structure and motion of the heart is crucial for diagnosing and managing cardiovascular diseases, the leading cause of global death. There is wide variation in cardiac shape and motion patterns, influenced by demographic, anthropometric and disease factors. Unravelling normal patterns of shape and motion, and understanding how each individual deviates from the norm, would facilitate accurate diagnosis and personalised treatment strategies. To this end, we developed a conditional generative model, MeshHeart, to learn the distribution of shape and motion patterns for the left and right ventricles of the heart. To model the high-dimensional spatio-temporal mesh data, MeshHeart employs a geometric encoder to represent cardiac meshes in a latent space, and a temporal Transformer to model the motion dynamics of latent representations. Based on MeshHeart, we investigate the latent space of 3D+t cardiac mesh sequences and propose a distance metric, latent delta, which quantifies the deviation of a real heart from its personalised normative pattern. In experiments using a large cardiac magnetic resonance image dataset of 38,309 subjects from the UK Biobank, MeshHeart demonstrates high performance in cardiac mesh sequence reconstruction and generation. Latent space features are discriminative for cardiac disease classification, whereas latent delta exhibits strong correlations with clinical phenotypes in phenome-wide association studies. The code and the trained model are released to support further research.

Bei Zhou, Cesare Corrado, Shuang Qian et al.

Accurate maps of atrial electrical activation are essential for personalised treatment of arrhythmias, yet biophysically detailed simulations remain computationally intensive for real-time clinical use or population-scale analyses. Here we introduce a geometry-independent operator-learning framework that predicts local activation time (LAT) fields across diverse left atrial anatomies with near-instantaneous inference. We generated a dataset of 308,700 simulations using a GPU-accelerated electrophysiology solver, systematically varying multiple pacing sites and physiologically varied conduction properties across 147 patient-specific geometries derived from two independent clinical cohorts. All anatomical and functional data are expressed in a Universal Atrium Coordinate system, providing a consistent representation that decouples electrophysiological patterns from mesh topology. Within this coordinate space, we designed a neural operator with a vision-transformer backbone to learn the mapping from structural and electrophysiological inputs to LAT fields. With a mean prediction error of 5.1 ms over a 455 ms maximum simulation time, the model outperforms established operator-learning approaches and performs inference in 0.12 ms per sample. Our framework establishes a general strategy for learning domain-invariant biophysical mappings across variable anatomical domains and enables integration of computational electrophysiology into real-time and large-scale clinical workflows.

Long Chen, Ashiv Patel, Mengyun Qiao et al.

Personalized, accurate prediction of aortic aneurysm progression is essential for timely intervention but remains challenging due to the need to model both subtle local deformations and global anatomical changes within complex 3D geometries. We propose MCMeshGAN, the first multimodal conditional mesh-to-mesh generative adversarial network for 3D aneurysm growth prediction. MCMeshGAN introduces a dual-branch architecture combining a novel local KNN-based convolutional network (KCN) to preserve fine-grained geometric details and a global graph convolutional network (GCN) to capture long-range structural context, overcoming the over-smoothing limitations of deep GCNs. A dedicated condition branch encodes clinical attributes (age, sex) and the target time interval to generate anatomically plausible, temporally controlled predictions, enabling retrospective and prospective modeling. We curated TAAMesh, a new longitudinal thoracic aortic aneurysm mesh dataset consisting of 590 multimodal records (CT scans, 3D meshes, and clinical data) from 208 patients. Extensive experiments demonstrate that MCMeshGAN consistently outperforms state-of-the-art baselines in both geometric accuracy and clinically important diameter estimation. This framework offers a robust step toward clinically deployable, personalized 3D disease trajectory modeling. The source code for MCMeshGAN and the baseline methods is publicly available at https://github.com/ImperialCollegeLondon/MCMeshGAN.

Zuoou Li, Weitong Zhang, Jingyuan Wang et al.

Multimodal large language models (MLLMs) are widely used in vision-language reasoning tasks. However, their vulnerability to adversarial prompts remains a serious concern, as safety mechanisms often fail to prevent the generation of harmful outputs. Although recent jailbreak strategies report high success rates, many responses classified as "successful" are actually benign, vague, or unrelated to the intended malicious goal. This mismatch suggests that current evaluation standards may overestimate the effectiveness of such attacks. To address this issue, we introduce a four-axis evaluation framework that considers input on-topicness, input out-of-distribution (OOD) intensity, output harmfulness, and output refusal rate. This framework identifies truly effective jailbreaks. In a substantial empirical study, we reveal a structural trade-off: highly on-topic prompts are frequently blocked by safety filters, whereas those that are too OOD often evade detection but fail to produce harmful content. However, prompts that balance relevance and novelty are more likely to evade filters and trigger dangerous output. Building on this insight, we develop a recursive rewriting strategy called Balanced Structural Decomposition (BSD). The approach restructures malicious prompts into semantically aligned sub-tasks, while introducing subtle OOD signals and visual cues that make the inputs harder to detect. BSD was tested across 13 commercial and open-source MLLMs, where it consistently led to higher attack success rates, more harmful outputs, and fewer refusals. Compared to previous methods, it improves success rates by $67\%$ and harmfulness by $21\%$, revealing a previously underappreciated weakness in current multimodal safety systems.

Xinru Zhang, Ni Ou, Berke Doga Basaran et al.

Brain lesion segmentation plays an essential role in neurological research and diagnosis. As brain lesions can be caused by various pathological alterations, different types of brain lesions tend to manifest with different characteristics on different imaging modalities. Due to this complexity, brain lesion segmentation methods are often developed in a task-specific manner. A specific segmentation model is developed for a particular lesion type and imaging modality. However, the use of task-specific models requires predetermination of the lesion type and imaging modality, which complicates their deployment in real-world scenarios. In this work, we propose a universal foundation model for 3D brain lesion segmentation, which can automatically segment different types of brain lesions for input data of various imaging modalities. We formulate a novel Mixture of Modality Experts (MoME) framework with multiple expert networks attending to different imaging modalities. A hierarchical gating network combines the expert predictions and fosters expertise collaboration. Furthermore, we introduce a curriculum learning strategy during training to avoid the degeneration of each expert network and preserve their specialization. We evaluated the proposed method on nine brain lesion datasets, encompassing five imaging modalities and eight lesion types. The results show that our model outperforms state-of-the-art universal models and provides promising generalization to unseen datasets.

Weitong Zhang, Mengyun Qiao, Chengqi Zang et al.

Identifying associations between imaging phenotypes, disease risk factors, and clinical outcomes is essential for understanding disease mechanisms. 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 Multi-agent Exploratory Synergy for the Heart (MESHAgents): a framework that leverages large language models as agents to dynamically elicit, surface, and decide confounders and phenotypes in association studies. 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 $-0.004_{\pm0.010}$ 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.