MICCAI 2025 Papers — Page 2
International Conference on Medical Image Computing and Computer-Assisted Intervention · 1027 papers
Blind Restoration of High-Resolution Ultrasound Video
Chen, Chu (City University of Hong Kong), Chan, Raymond H. (Hong Kong Centre for Cerebro-cardiovascular Health Engineering)
RestorationSuper ResolutionConvolutional Neural NetworkVideoUltrasound
🎯 What it does: A self-supervised ultrasound video super-resolution method called Deep Ultrasound Prior (DUP) is designed to achieve blind recovery and denoising.
Blood Pressure Assisted Cerebral Microbleed Segmentation via Meta-matching
Kwon, Junmo (Sungkyunkwan University), Park, Hyunjin (VUNO Inc.)
SegmentationConvolutional Neural NetworkImageMultimodalityBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes a BP-nnU-Net framework that integrates blood pressure information for the segmentation of cerebral microbleeds (CMB).
BME2: A Plug-and-Play Bridge-Based Module for Misalignment Estimation and Elimination in Multi-Scan Image Restoration
Chen, Wenxuan (Tsinghua University), Shen, Dinggang (Shanghai United Imaging Intelligence Co., Ltd.)
RestorationSuper ResolutionConvolutional Neural NetworkAuto EncoderImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: A pluggable multimodal/multi-timepoint image restoration module (BME 2) is proposed to roughly estimate and recursively refine the deformation field across scans, thereby eliminating mismatches between images and improving restoration quality.
Boosting 3D Liver Shape Datasets with Diffusion Models and Implicit Neural Representations
Nguyen, Khoa Tuan (Ghent University), De Neve, Wesley (Ghent University)
GenerationData SynthesisTransformerDiffusion modelMesh
🎯 What it does: The researchers analyzed the shortcomings of existing 3D liver datasets and proposed generating high-quality synthetic liver models through HyperDiffusion and implicit neural representations (INR) to expand the dataset.
Boosting Generalizability in NPC ART Prediction via Multi-Omics Feature Mapping
Sheng, Jiabao, Cai, Jing (Hong Kong Polytechnic University)
ClassificationDomain AdaptationConvolutional Neural NetworkMultimodalityBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: A model based on multi-omics feature mapping (Genomap) was constructed to predict whether nasopharyngeal carcinoma patients are suitable for adaptive radiotherapy, and a visual nomogram was further generated.
Boosting Medical Image Synthesis via Registration-guided Consistency and Disentanglement Learning
Li, Chuanpu (Southern Medical University), Yang, Wei (Huazhong University of Science and Technology)
GenerationData SynthesisGenerative Adversarial NetworkImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: This paper proposes a medical image synthesis framework that combines registration-guided consistency with decoupled learning, suppressing misalignment noise during the training process by applying the same deformation before and after synthesis and using alignment loss.
Bowsher prior Enhanced Unsupervised PET image Denoising
Wu, Zhongxue (Zhejiang University of Technology), Chen, Zan (Zhejiang University of Technology)
RestorationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance ImagingPositron Emission Tomography
🎯 What it does: A framework for unsupervised PET image denoising based on Bowsher prior is proposed, utilizing previous CDIP denoising results and MR images to generate the Bowsher prior, and further enhancing image quality through the spatial attention network SA-Net.
Brain activation mapping based on Regional Synchronization of fMRI signals embedded in Graph Eigenmodes
Tang, Zhenyu (Beihang University), Su, Jingyong (Harbin Institute of Technology)
Graph Neural NetworkBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A nonlinear brain activation mapping framework RS-GEm based on graph Laplacian feature patterns is proposed, which identifies task-related activation regions by calculating regional synchrony under the feature patterns of brain graphs and combining clustering scores.
Brain Wiring Knowledge Graph Reasoning: A Region Embedding Approach for Logical Neuronal Relation Inference
Zhou, Zhengyun (Wuhan University), Du, Bo (Wuhan University)
Graph Neural NetworkGraphBiomedical Data
🎯 What it does: This paper constructs a brain connectivity graph knowledge graph from fruit flies and human cortex, and utilizes Lie group space for regional embedding to achieve logical reasoning of neuronal relationships.
Brain-Environment Cross-Attention (BECA) Meta-Matching: A New Perspective of Brain Connectome Zero-Shot Learning
Wei, Ziquan (University of North Carolina at Chapel Hill), Wu, Guorong (POSTECH)
ClassificationAnomaly DetectionMeta LearningTransformerSupervised Fine-TuningBiomedical DataAlzheimer's Disease
🎯 What it does: A zero-shot learning framework based on brain-environment cross-attention, BECA, is proposed to achieve early diagnosis of brain network diseases using a brain-based model pre-trained with logistic regression.
Brain-Heart-Gut Guided Multi-Constraint Knowledge Distillation for Early Alzheimer’s Disease Diagnosis
Li, Fan (ShanghaiTech University), Shen, Dinggang (Shanghai United Imaging Intelligence Co., Ltd.)
ClassificationKnowledge DistillationConvolutional Neural NetworkTransformerContrastive LearningImageBiomedical DataPositron Emission TomographyAlzheimer's Disease
🎯 What it does: This paper proposes a brain-heart-gut interactive information fusion and multi-constraint knowledge distillation framework based on whole-body PET to enhance the diagnostic accuracy of brain imaging in early Alzheimer's disease.
BrainAlign: EEG-Vision Alignment via Frequency-Aware Temporal Encoder and Differentiable Cluster Assigner
Shi, Enze (Northwestern Polytechnical University), Zhang, Shu (Northwestern Polytechnical University)
ClassificationRetrievalVision Language ModelContrastive LearningMultimodalityTime Series
🎯 What it does: Using contrastive learning to align EEG features with visual language models (VLM) to decode visual semantics from EEG.
BrainMT: A Hybrid Mamba-Transformer Architecture for Modeling Long-Range Dependencies in Functional MRI Data
Kannan, Arunkumar (Johns Hopkins University), Caffo, Brian (Johns Hopkins University)
ClassificationRecognitionOptimizationComputational EfficiencyTransformerTime SeriesBiomedical DataMagnetic Resonance Imaging
🎯 What it does: We propose BrainMT, an end-to-end hybrid Mamba-Transformer network for predicting phenotypes (gender classification and cognitive intelligence regression) from raw functional MRI volumes, capable of capturing long-range spatiotemporal dependencies.
BrainPrompt: Domain Adaptation with Prompt Learning for Multi-site Brain Network Analysis
Zhang, Liuzeng (Northeastern University), Zaiane, Osmar R. (Amii)
Domain AdaptationKnowledge DistillationTransformerPrompt EngineeringBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Proposes the BrainPrompt framework, which utilizes prompt learning to achieve domain adaptation of multi-site brain networks for distinguishing autism spectrum disorders.
BrainPrompt: Multi-Level Brain Prompt Enhancement for Neurological Condition Identification
Xu, Jiaxing (Nanyang Technological University), Feng, Mengling (National University of Singapore)
ClassificationGraph Neural NetworkLarge Language ModelPrompt EngineeringGraphBiomedical DataAlzheimer's Disease
🎯 What it does: A multi-layer Prompt-based brain network classification framework called BrainPrompt is proposed, integrating ROI, subject, and disease-level Prompts with GNN;
BraTS-UMamba: Adaptive Mamba UNet with Dual-Band Frequency based Feature Enhancement for Brain Tumor Segmentation
Yao, Haoran (Henan Normal University), Berkovsky, Shlomo (Macquarie University)
SegmentationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes the BraTS-UMamba structure based on Mamba for 3D MRI segmentation of brain tumors.
BREA-Depth: Bronchoscopy Realistic Airway-geometric Depth Estimation
Zhang, Francis Xiatian (University of Edinburgh), Khadem, Mohsen (University of Edinburgh)
SegmentationDepth EstimationTransformerGenerative Adversarial NetworkImageVideo
🎯 What it does: This study proposes the BREA-Depth framework, which utilizes foundational model adaptation, depth-aware CycleGAN, and airway structure-aware loss to achieve monocular depth estimation in airway endoscopy, and introduces a new structural consistency evaluation metric.
BridgeSplat: Bidirectionally Coupled CT and Non-Rigid Gaussian Splatting for Deformable Intraoperative Surgical Navigation
Fehrentz, Maximilian (Harvard Medical School, Brigham and Women's Hospital), Navab, Nassir (Technische Universität München)
Object TrackingSegmentationOptimizationGaussian SplattingImageVideoComputed Tomography
🎯 What it does: Combining CT with 4D Gaussian Splatting to track in real-time and directly update the deformation of preoperative CT in monocular RGB videos;
Bridging Classical and Learning-based Iterative Registration through Deep Equilibrium Models
Zhang, Yi (Sichuan University), Tao, Qian (Delft University of Technology)
OptimizationBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: A deep equilibrium model (DEQ)-based unsupervised medical image deformation registration framework, DEQReg, is proposed to address the contradiction between convergence of traditional optimization methods and non-convergence of learning-based iterative methods, as well as the memory bottleneck.
Bridging Knowledge Discrepancy in Retinal Image Analysis through Federated Multi-Task Learning
Yang, Jing (National Institute for Data Science in Health and Medicine, Xiamen University), Wang, Liansheng (Shanghai Changhai Hospital)
ClassificationSegmentationFederated LearningTransformerContrastive LearningImageBiomedical Data
🎯 What it does: This paper proposes the FedBKD framework, which aims to bridge the knowledge gap between global and local models in a federated multi-task learning environment for disease recognition and segmentation of retinal images using a base model.
Bridging Radiological Images and Factors with Vision-Language Model for Accurate Diagnosis of Proliferative Hepatocellular Carcinoma
Huang, Yanyan (University of Hong Kong), Yu, Lequan (University of Hong Kong)
ClassificationTransformerPrompt EngineeringVision Language ModelImageTextMultimodalityTabularComputed Tomography
🎯 What it does: This paper proposes the FM-Bridge method, which achieves accurate diagnosis of proliferative hepatocellular carcinoma (HCC) by textually transforming the tabulated imaging factors evaluated by clinical experts and utilizing a visual-language model (VLM) for cross-modal alignment, integrating CT images and tabular data.
Bridging the Gap in Missing Modalities: Leveraging Knowledge Distillation and Style Matching for Brain Tumor Segmentation
Zhu, Shenghao (Hangzhou Dianzi University), Wang, Changmiao (Shenzhen Research Institute of Big Data)
SegmentationKnowledge DistillationTransformerMultimodalityBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes a new framework called MST-KDNet for brain tumor segmentation in the absence of multimodal MRI.
C-NCA: Chained Neural Cellular Automata for Fast and Accurate Thermal Ablation Estimation
Mehtali, Jonas (University of Strasbourg), Essert, Caroline (University of Strasbourg)
Convolutional Neural NetworkBiomedical DataComputed Tomography
🎯 What it does: A thermal ablation estimation model based on Chain Neural Cellular Automata (C-NCA) has been developed, capable of predicting cell death for multiple needle thermal ablation in milliseconds.
C²MAOT: Cross-modal Complementary Masked Autoencoder with Optimal Transport for Cancer Segmentation in PET-CT Images
Huang, Jiaju (Macao Polytechnic University), Tan, Tao (Macao Polytechnic University)
SegmentationConvolutional Neural NetworkAuto EncoderImageMultimodalityBiomedical DataComputed TomographyPositron Emission Tomography
🎯 What it does: A cross-modal self-supervised pre-training framework C²MAOT is proposed for tumor segmentation in PET-CT images.
CA-SAM2: SAM2-based Context-Aware Network with Auto-Prompting for Nuclei Instance Segmentation
Huang, Hanbin (Soochow University), Fu, Guohong (Soochow University)
SegmentationTransformerImage
🎯 What it does: A CA-SAM2 network based on SAM2 is proposed for instance segmentation of nuclei in pathological images, enhancing segmentation accuracy through context injection and feature refinement.
Calibration in Multiple Instance Learning: Evaluating Aggregation Methods for Ultrasound-Based Diagnosis
Geysels, Axel (Ku Leuven), Timmerman, Dirk
ClassificationConvolutional Neural NetworkImageBiomedical DataUltrasound
🎯 What it does: Evaluate the probability calibration of multiple instance learning (MIL) aggregation methods in ultrasound diagnosis and propose an inverse entropy weighted attention aggregation scheme.
CAPE: Connectivity-Aware Path Enforcement Loss for Curvilinear Structure Delineation
Esmaeilzadeh, Elyar (Bilkent University), Oner, Doruk (Bilkent University)
SegmentationConvolutional Neural NetworkImageBiomedical Data
🎯 What it does: A connectivity-based loss function called CAPE is proposed, aimed at improving the topological correctness of segmentation for curved structures (such as neurons and blood vessels) by comparing the shortest path costs between predictions and ground truths.
CardiacCLIP: Video-based CLIP Adaptation for LVEF Prediction in a Few-shot Manner
Du, Yao (Hong Kong University of Science and Technology), Li, Xiaomeng (Southern Medical University)
ClassificationDomain AdaptationOptimizationConvolutional Neural NetworkVision Language ModelContrastive LearningVideoTextBiomedical DataUltrasound
🎯 What it does: This paper presents CardiacCLIP, a CLIP adaptation framework for cardiac ultrasound videos, aimed at predicting left ventricular ejection fraction (LVEF) in a few-shot environment.
CardiacFlow: 3D+t Four-Chamber Cardiac Shape Completion and Generation via Flow Matching
Ma, Qiang (Imperial College London), Bai, Wenjia (Imperial College London)
SegmentationGenerationFlow-based ModelBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: A framework called CardiacFlow is proposed for implicit four-chamber ventricular shape completion and generation based on flow matching, achieving efficient one-step generation and shape completion.
CardioInterp: Generative Modeling for Cardiovascular OCT Interpolation with Anatomical Continuity and Fidelity
Li, Linyuan (Chinese University of Hong Kong), Yuan, Wu (Chinese University of Hong Kong)
RestorationGenerationData SynthesisSuper ResolutionDiffusion modelAuto EncoderImageBiomedical DataUltrasound
🎯 What it does: The CardioInterp model is proposed, utilizing a latent diffusion model and a dual-path fusion decoder to perform high-quality interpolation of B-slices in cardiovascular OCT, generating continuous and high-resolution images.
CARE-VL: A Domain-Specialized Vision-Language Model for Early ASD Screening
Yoo, Cheol-Hwan (ETRI), Jang, Jaeyoon (ETRI)
ClassificationRecognitionTransformerLarge Language ModelSupervised Fine-TuningVision Language ModelVideoMultimodality
🎯 What it does: A domain-specific visual-language model named CARE-VL is proposed to identify children's social behaviors from social interaction videos and achieve early screening for autism spectrum disorder (ASD) through LLM aggregation.
Cascaded 3D Diffusion Models for Whole-body 3D 18-F FDG PET/CT synthesis from Demographics
Yoon, Siyeop (Massachusetts General Hospital and Harvard Medical School), Li, Quanzheng (Massachusetts General Hospital and Harvard Medical School)
GenerationData SynthesisDiffusion modelScore-based ModelBiomedical DataComputed TomographyPositron Emission Tomography
🎯 What it does: A full-body PET/CT synthesis framework based on a cascaded three-dimensional diffusion model is proposed, which can generate high-fidelity 18-F FDG PET/CT volumes using only demographic variables such as age, gender, height, and weight, for virtual clinical trials and AI data augmentation.
CAT-SG: A Large Dynamic Scene Graph Dataset for Fine-Grained Understanding of Cataract Surgery
Holm, Felix (Technical University Munich), Navab, Nassir (Technische Universität München)
RecognitionSegmentationTransformerVideo
🎯 What it does: Constructed CAT-SG, the first dynamic scene graph dataset for cataract surgery, with detailed annotations of tool-tissue interactions and technical steps;
CATVis: Context-Aware Thought Visualization
Mehmood, Tariq (Lahore University of Management Sciences), Taj, Murtaza (Lahore University of Management Sciences)
GenerationRetrievalTransformerDiffusion modelContrastive LearningImageMultimodalityElectrocardiogram
🎯 What it does: This paper proposes a five-stage end-to-end framework that decodes visual stimuli from EEG signals and generates images similar to the original using Stable Diffusion.
CAUDA-MI: Cross Attention-Guided Unsupervised Domain Adaptation with Mutual Information for Cardiac MRI Segmentation
Du, Dianrong (Northwestern Polytechnical University), Xia, Yong (Northwestern Polytechnical University)
SegmentationDomain AdaptationConvolutional Neural NetworkAuto EncoderGenerative Adversarial NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Unsupervised domain adaptation segmentation task for cardiac MRI across different modalities (bSSFP source domain → LGE target domain).
Causality-driven Spatio-temporal Generator for Multi-phase Contrast-enhanced CT Synthesis
Zhu, Qikui (Case Western Reserve University), Li, Shuo (Harbin Institute of Technology)
GenerationData SynthesisTransformerAuto EncoderGenerative Adversarial NetworkImageBiomedical DataComputed Tomography
🎯 What it does: The CSGen model is proposed to synthesize multi-phase contrast-enhanced CT images directly from non-contrast CT, reducing radiation and allergy risks.
Causality-Inspired Graph Neural Network for Interpretable Strabismus Subtype Classification
Zheng, Jiawen (Shantou University), Fan, Zhun (UESTC)
ClassificationExplainability and InterpretabilityComputational EfficiencyGraph Neural NetworkImageBiomedical Data
🎯 What it does: This paper proposes a Causal Inference Graph Neural Network (CI-GNN) that achieves strabismus subtype classification by extracting ocular visual features and constructing a causal graph.
CBrain: Cross-Modal Learning for Brain Vigilance Detection in Resting-State fMRI
Li, Chang (Vanderbilt University), Chang, Catie (Vanderbilt University)
ClassificationRecognitionTransformerContrastive LearningMultimodalityBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Using an EEG-assisted cross-modal learning method, a model is trained to predict alertness states solely based on fMRI segments.
CD-PolypNet: Cross-Domain Polyp Segmentation Network with Internal Feature Distillation and Dual-Stream Boundary Focus via Large Vision Model
Yue, Changpeng (Hangzhou Dianzi University), Wang, Shuai (Lishui Institute of Hangzhou Dianzi University)
SegmentationKnowledge DistillationConvolutional Neural NetworkImageMagnetic Resonance Imaging
🎯 What it does: A cross-domain polyp segmentation network CD-PolypNet based on the large visual model SAM has been constructed, combining internal feature distillation and dual-stream boundary focusing.
CellStyle: Improved Zero-Shot Cell Segmentation via Style Transfer
Yilmaz, Rüveyda (RWTH Aachen University), Stegmaier, Johannes (RWTH Aachen University)
SegmentationDomain AdaptationConvolutional Neural NetworkDiffusion modelImageBiomedical Data
🎯 What it does: The CellStyle method is proposed, utilizing an unsupervised diffusion model for style transfer on unlabeled target data, mapping attributes such as texture and color from the target to labeled source data, generating synthetic images with original annotations for fine-tuning zero-shot cell instance segmentation models.
CENet: Context Enhancement Network for Medical Image Segmentation
Bozorgpour, Afshin (University of Regensburg), Merhof, Dorit (Hannover Medical School)
SegmentationConvolutional Neural NetworkTransformerImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: Proposes CENet, an improved medical image segmentation model to enhance boundary details and multi-scale feature representation.
Cerebrovascular Diseases Screening from Color Fundus Photography via Cross-View Fusion and Graph-Based Discrimination
Tian, Congyu (Shenzhen Institutes of Advanced Technology), Si, Weixin (Guangzhou First People's Hospital)
ClassificationGraph Neural NetworkTransformerAuto EncoderImage
🎯 What it does: A brain vascular disease screening method based on color fundus photographs, CVGB-Net, is proposed, which integrates pixel-level and semantic-level features and performs discrimination through a graph network.
Cervical-RG: Automated Cervical Cancer Report Generation from 3D Multi-sequence MRI via CoT-guided Hierarchical Experts
Zhang, Hanwen (Beijing Institute Of Technology), Zhao, Weibing (Shenzhen Msu-Bit University)
GenerationTransformerLarge Language ModelMixture of ExpertsImageTextBiomedical DataMagnetic Resonance ImagingChain-of-Thought
🎯 What it does: Automatically generate cervical cancer reports, integrating 3D multi-sequence MRI and FIGO staging;
CF-Seg: Counterfactuals meet Segmentation
Mehta, Raghav (Imperial College London), Glocker, Ben (Imperial College London)
SegmentationGenerationConvolutional Neural NetworkAuto EncoderImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: The CF-Seg framework is proposed, which uses a deep structural causal model to generate pseudo-healthy control images, and then employs a pre-trained U-Net to perform anatomical structure segmentation on these pseudo-healthy images, thus eliminating the need to retrain the segmentation model.
CholecMamba: A Mamba-based Multimodal Reasoning Model for Cholecystectomy Surgery
Wang, Zipei (Chinese Academy of Sciences), Dong, Di (University of Chinese Academy of Sciences)
RecognitionSegmentationTransformerLarge Language ModelReinforcement LearningVideoMultimodality
🎯 What it does: CholecMamba is proposed—a multimodal reasoning model based on Mamba for comprehensive analysis and segmentation of cholecystectomy surgery videos.
Class-Conditioned Image Synthesis with Diffusion for Imbalanced Diabetic Retinopathy Grading
Zhang, Haochen (UC San Diego), An, Cheolhong (UC San Diego)
GenerationData SynthesisDiffusion modelImage
🎯 What it does: This paper utilizes a conditional diffusion model to generate fundus images of diabetic retinopathy (DR) to alleviate the imbalance in training data.
CLIMD: A Curriculum Learning Framework for Imbalanced Multimodal Diagnosis
Han, Kai (Jiangsu University), Liu, Zhe (Shenzhen University)
ClassificationSegmentationConvolutional Neural NetworkSupervised Fine-TuningMultimodalityBiomedical Data
🎯 What it does: A framework called CLIMD based on curriculum learning is proposed to alleviate the class imbalance problem in multimodal diagnosis.
ClinGRAD: Clinically-Guided Genomics and Radiomics Interpretable GNN for Dementia Diagnosis
Hassan, Salma (Mohamed Bin Zayed University of Artificial Intelligence), Yaqub, Mohammad (Mohamed bin Zayed University of Artificial Intelligence)
ClassificationExplainability and InterpretabilityGraph Neural NetworkMultimodalityBiomedical DataMagnetic Resonance ImagingAlzheimer's Disease
🎯 What it does: ClinGRAD, a clinical-guided heterogeneous graph neural network, was developed to diagnose Alzheimer's disease through multi-scale integration of genomics and radiomics.
Clinical Data-Driven Retrieval-Augmented Model for Lung Nodule Malignancy Prediction
Hou, Ruibo (Ritsumeikan University), Chen, Yen-Wei (Ritsumeikan University)
ClassificationRetrievalConvolutional Neural NetworkVision Language ModelImageTextMultimodalityComputed TomographyElectronic Health RecordsRetrieval-Augmented Generation
🎯 What it does: A clinical data-driven retrieval-enhanced visual-language model framework is proposed for predicting the malignancy of lung nodules.
Clinical Prior Guided Cross-Modal Hierarchical Fusion for Histological Subtyping of Lung Cancer in CT Scans
Fan, Chenchen (Zhejiang University of Finance and Economics), Wang, Changmiao (Shenzhen Research Institute of Big Data)
ClassificationObject DetectionConvolutional Neural NetworkContrastive LearningImageMultimodalityBiomedical DataComputed Tomography
🎯 What it does: This paper proposes an end-to-end CM-DAC framework that combines YOLOv11 slice detection, multimodal contrastive pre-training, and cross-modal hierarchical fusion to achieve high-precision subtype classification of lung cancer using CT images and clinical prior information.
Clinical Prior-Guided Tumor Generation for Breast Ultrasound with Cross Domain Adaptation
Pan, Haoyu (Shenzhen University), Zheng, Qingqing (Shenzhen University of Advanced Technology)
ClassificationSegmentationGenerationData SynthesisDomain AdaptationDiffusion modelImageBiomedical DataUltrasound
🎯 What it does: A breast ultrasound tumor generation framework based on clinical priors (BI-RADs) has been developed, utilizing shape masks and text descriptions to achieve unlabelled controllable generation in diffusion models, and cross-domain adaptation is realized through LoRA. The generated synthetic images can be directly used to enhance classification and segmentation tasks.
Clinical Validation of Deep Learning for Real-Time Tissue Oxygenation Estimation Using Spectral Imaging
De Winne, Jens (Imec), Ceelen, Wim (Ghent University Hospital)
Domain AdaptationOptimizationConvolutional Neural NetworkImageBiomedical Data
🎯 What it does: This paper develops and evaluates methods based on deep learning (FCN, CNN, and domain adversarial networks) for real-time estimation of tissue oxygenation levels through multispectral imaging.
Clinically-guided Data Synthesis for Laryngeal Lesion Detection
Baldini, Chiara (Istituto Italiano di Tecnologia), Mattos, Leonardo S. (Istituto Italiano di Tecnologia)
Object DetectionData SynthesisDiffusion modelImageBiomedical Data
🎯 What it does: Using implicit diffusion models (LDM) and ControlNet, annotated laryngoscopic images are generated based on clinical information and annotation boxes to expand medical image datasets and improve the performance of laryngeal lesion detection.
CLIP-DSA: Textual Knowledge-Guided Cerebrovascular Diseases Recognition in Multi-View Digital Subtraction Angiography
Xie, Qihang (Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences), Zhang, Jiong (Chinese Academy of Sciences)
ClassificationRecognitionConvolutional Neural NetworkVision Language ModelContrastive LearningImageMultimodalityBiomedical Data
🎯 What it does: Proposes the CLIP-DSA framework, which utilizes CLIP textual knowledge to guide the classification of cerebrovascular diseases in multi-view DSA sequences.
ClipGS: Clippable Gaussian Splatting for Interactive Cinematic Visualization of Volumetric Medical Data
Li, Chengkun (Chinese University of Hong Kong), Dou, Qi (Huazhong University of Science and Technology)
Gaussian SplattingBiomedical DataMagnetic Resonance Imaging
🎯 What it does: The ClipGS framework is proposed to achieve interactive cinematic-level volumetric medical visualization based on clipable Gaussian splatting.
Co-Seg: Mutual Prompt-Guided Collaborative Learning for Tissue and Nuclei Segmentation
Xu, Qing (University of Lincoln), Chen, Zhen (University of Lincoln)
SegmentationTransformerPrompt EngineeringBiomedical Data
🎯 What it does: A Co-Seg framework is proposed, utilizing mutual prompts to achieve collaborative segmentation of tissues and cell nuclei;
Coarse-to-Fine Medical Image Translation by Incorporating Deterministic Guidance and Probabilistic Refinement
Tian, Hongnian (Jiangnan University), Pan, Xiang (Hangzhou Dianzi University)
Image TranslationData SynthesisDiffusion modelAuto EncoderImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: A coarse-to-fine medical image translation framework C2FMIT is proposed, utilizing a dual mechanism of deterministic structure guidance and probabilistic refinement to achieve high-quality functional enhancement image synthesis.
CoC: Chain-of-Cancer based on Cross-Modal Autoregressive Traction for Survival Prediction
Zhou, Haipeng (Hong Kong University of Science and Technology Guangzhou), Zhu, Lei (Hong Kong University of Science and Technology)
ClassificationConvolutional Neural NetworkTransformerPrompt EngineeringMultimodalityBiomedical DataChain-of-Thought
🎯 What it does: Proposes the Chain-of-Cancer (CoC) framework, which utilizes three clinical modalities—genomics, methylation, and whole-slide pathology images—along with text prompts for tumor survival prediction.
CoCa-CXR: Contrastive Captioners Learn Strong Temporal Structures for Chest X-Ray Vision-Language Understanding
Chen, Yixiong (Johns Hopkins University), Yang, Lin (Westlake University)
ClassificationGenerationTransformerLarge Language ModelSupervised Fine-TuningVision Language ModelContrastive LearningImageTextMultimodalityTime Series
🎯 What it does: This paper proposes a visual-language model named CoCa-CXR, specifically designed for time series analysis and report generation of chest X-ray images.
Collateral Circulation guided Multi-modality Fusion Network for Postoperative Infarct Prediction
Guo, Yichen (Beihang University), Li, Shengxi (Beihang University)
Object DetectionSegmentationTransformerMixture of ExpertsImageMultimodalityBiomedical DataComputed Tomography
🎯 What it does: This paper constructs the first brain CT perfusion (CTP) dataset that includes information on collateral vessels and proposes a multimodal fusion network based on the status of collateral vessels (CCGM). It extracts spatiotemporal features through a bidirectional Mamba, fuses multimodal information using a mixture of experts mechanism, and achieves two-stage stroke localization and segmentation guided by collateral priors.
Compact Training-free NAS with Alternating Evolution Game for Medical Image Segmentation
Sun, Xiaoxue (Nankai University), Song, Pei-Cheng (Nankai University)
SegmentationNeural Architecture SearchImageBiomedical Data
🎯 What it does: A training-free NAS framework based on alternating evolutionary game, AEG-cTFNAS, is proposed for medical image segmentation.
Concept-induced Graph Perception Model for Interpretable Diagnosis
Zhao, Lei (Hunan university), Tan, Guanghua (Hunan university)
ClassificationExplainability and InterpretabilityGraph Neural NetworkTransformerContrastive LearningImageBiomedical DataUltrasound
🎯 What it does: A concept graph-based explainable diagnostic model (CGP) is proposed, which perceives concepts at the sub-region level using the CAP module and obtains the final diagnostic result through dual-scale graph reasoning with DCGB.
Conditional Graph Diffusion with Topological Constraints for Brain Network Generation
Park, Joonhyuk (Pohang University of Science and Technology), Kim, Won Hwa (Pohang University of Science and Technology)
ClassificationGenerationData SynthesisGraph Neural NetworkTransformerDiffusion modelGraphBiomedical DataMagnetic Resonance ImagingAlzheimer's Disease
🎯 What it does: A conditional graph diffusion model, ConGD, is proposed to generate brain networks under the conditions of disease labels and topological structures, addressing the issues of data scarcity and class imbalance in brain network data.
Conditional Latent Diffusion Models for Irregularly Spaced Longitudinal Radiological Data
Mouadden, Nabil (CentraleSupelec), Vakalopoulou, Maria (CentraleSupelec)
SegmentationGenerationTransformerDiffusion modelImageTextBiomedical DataComputed Tomography
🎯 What it does: This paper proposes a unified Conditional Latent Diffusion Model (CLDM) that can utilize existing 2D or 3D medical image sequences at irregular time intervals to predict latent representations at future time points, thereby completing two types of longitudinal medical imaging tasks: future image segmentation and follow-up report generation.
Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA
Du, Yuetian (Zhejiang University), Zhu, Qiang (Zhejiang University)
TransformerLarge Language ModelPrompt EngineeringMultimodalityBiomedical Data
🎯 What it does: This study investigates the confidence calibration issue of medical multimodal LLMs in visual question answering tasks and proposes and evaluates a calibration method based on multi-strategy fusion questioning and expert LLM assessment.
Confidence in Angle Predictions for Clinical Decision Support
Clement, Allison (Oxford University), Voiculescu, Irina (Oxford University)
Convolutional Neural NetworkImageBiomedical DataUltrasound
🎯 What it does: This paper proposes a method for predicting the distribution of hip joint angles and estimating confidence based on ultrasound images. It utilizes UNet++ to generate heatmaps for key anatomical landmarks, and then derives the angle probability distribution and confidence indicators through Monte Carlo sampling.
Configurable Platform for Biomedical Literature Mining via Multimodal-Driven Extraction
Yuan, Xinpan (Hunan University of Technology), Li, Gan (Hunan University of Technology)
RecognitionSegmentationRetrievalOptimizationGraph Neural NetworkLarge Language ModelSupervised Fine-TuningReinforcement LearningTextMultimodalityBiomedical Data
🎯 What it does: A configurable biomedical literature mining platform is proposed and implemented, integrating literature collection, cross-modal parsing, template-based entity recognition, and visualization, achieving end-to-end knowledge extraction and interaction.
Conformal forecasting for surgical instrument trajectory
Sangalli, Sara (ETH Zurich), Konukoglu, Ender (ETH Zurich)
Object DetectionRobotic IntelligenceTransformerSupervised Fine-TuningVideo
🎯 What it does: This paper applies the Conformal Prediction method to predict the trajectory of surgical instruments in endoscopic neurosurgery, providing reliable uncertainty intervals for angles and lengths.
Conformal Prediction for Image Segmentation Using Morphological Prediction Sets
Mossina, Luca (IRT Saint Exupéry), Friedrich, Corentin (IRT Saint Exupéry)
SegmentationImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A post-hoc confidence interval construction method is proposed that relies solely on binary prediction masks and does not require internal model information (such as sigmoid scores). It utilizes morphological dilation to generate nested prediction sets, ensuring a coverage rate of ≥ 1-α under a given risk α.
Conformal Risk Control for Semantic Uncertainty Quantification in Computed Tomography
Teneggi, Jacopo (Johns Hopkins University), Sulam, Jeremias (Johns Hopkins University)
RestorationSegmentationConvolutional Neural NetworkImageBiomedical DataComputed Tomography
🎯 What it does: A semantic uncertainty quantification method based on conformal risk control, called sem-CRC, is proposed for CT image reconstruction and denoising tasks.
Conservative-Radical Complementary Learning for Class-incremental Medical Image Analysis with Pre-trained Foundation Models
Wu, Xinyao (Chinese University of Hong Kong), Tong, Raymond Kai-yu (Chinese University of Hong Kong)
ClassificationKnowledge DistillationTransformerSupervised Fine-TuningImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A replay-free class incremental learning framework CRCL is proposed, utilizing a pre-trained visual Transformer to achieve continuous diagnosis of medical images through two types of learners (conservative and aggressive).
ConStyX: Content Style Augmentation for Generalizable Medical Image Segmentation
Chen, Xi (Chinese Academy of Sciences), Zaiane, Osmar R. (Amii)
SegmentationDomain AdaptationConvolutional Neural NetworkImageBiomedical Data
🎯 What it does: The ConStyX method is proposed, which enhances the domain generalization ability of medical image segmentation models by simultaneously performing content and style augmentation in the deep feature space.
Continual Retinal Vision-Language Pre-training upon Incremental Imaging Modalities
Yao, Yuang (Southeast University), Zhou, Tao (Nanjing University of Science and Technology)
Knowledge DistillationRepresentation LearningConvolutional Neural NetworkContrastive LearningImageTextMultimodalityBiomedical Data
🎯 What it does: Proposes the RetCoP framework to achieve continuous audiovisual language pre-training for multimodal fundus images.
Contour Makes It Stronger: Cross-Domain Cephalometric Landmark Detection Based on Contour Priors
Liang, Xinyue, Zhou, Yuanfeng (Shandong University)
Object DetectionDomain AdaptationConvolutional Neural NetworkTransformerImageMagnetic Resonance Imaging
🎯 What it does: A cross-domain lateral cephalometric image feature fusion framework based on anatomical contour priors is proposed, achieving joint learning of the cranial soft and hard tissue edge contours and landmark points to enhance the performance of landmark point localization in lateral cephalometric images.
Contrast Flow Pattern and Cross-Phase Specificity-Aware Diffusion Model for NCCT-to-Multiphase CECT Synthesis
Zheng, Kaiyi (Southern Medical University), Zhong, Liming (Southern Medical University)
GenerationData SynthesisDiffusion modelImageBiomedical DataComputed Tomography
🎯 What it does: A method based on a conditional diffusion model for contrast flow pattern and cross-phase specificity perception is proposed, enabling the generation of multi-phase enhanced CT from non-contrast CT.
Contrastive Anatomy-Contrast Disentanglement: A Domain-General MRI Harmonization Method
Scholz, Daniel (Technical University of Munich), Rueckert, Daniel (Technical University of Munich)
Image HarmonizationDomain AdaptationDiffusion modelAuto EncoderContrastive LearningImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This study proposes an unsupervised domain generalization method for harmonizing MRI scanners based on a diffusion autoencoder, which can harmonize brain MRI images from any unknown scanner to a target domain without requiring multiple scans of the same subject or multiple sequences, while maintaining anatomical structures.
Contrastive Disentanglement Learning Framework for Multi-lead Wearable ECG Denoising
Zhang, Yue (Southern Medical University), Feng, Qianjin (Southern Medical University)
RestorationDomain AdaptationConvolutional Neural NetworkContrastive LearningTime SeriesSequentialBiomedical DataElectrocardiogram
🎯 What it does: A 12-lead wearable ECG denoising framework based on contrastive decoupling learning is proposed, which directly processes 12-lead signals while removing noisy leads without affecting the clean leads.
Contrastive Knowledge-Guided Large Language Models for Medical Report Generation
Sha, Yuyang (Macao Polytechnic University), Li, Kefeng (Macao Polytechnic University)
GenerationGraph Neural NetworkTransformerLarge Language ModelContrastive LearningImageTextMultimodality
🎯 What it does: The KACL framework is proposed, utilizing knowledge injection, contrastive alignment, cross-modal enhancement, and LLM decoders to generate more accurate medical imaging reports.
Contrastive Masked Video Modeling for Coronary Angiography Diagnosis
Shao, Zhiming (Chinese Academy of Sciences), Hui, Hui (Chinese Academy of Sciences)
ClassificationRecognitionRepresentation LearningTransformerContrastive LearningVideoBiomedical Data
🎯 What it does: A self-supervised framework combining masked video modeling and contrastive learning is proposed for the diagnosis of coronary angiography (CAG).
Controllable Flow Matching for 3D Contrast-Enhanced Brain MRI Synthesis from Non-Contrast Scans
Chang, Heng (Xi'an Jiaotong University), Lian, Chunfeng (Xi'an Jiaotong University)
Image TranslationSegmentationGenerationData SynthesisFlow-based ModelImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A controllable flow matching model (CFM) is proposed to achieve one-step synthesis from non-contrast T1w brain MRI to contrast T1ce brain MRI, with precise control over tumor details through tumor segmentation constraints.
Controllable Image Synthesis Workflow for Enhancing Cervical Cell Detection
Hu, Yihuang (Xiamen University), Wang, Liansheng (Shanghai Changhai Hospital)
Object DetectionSegmentationData SynthesisGenerative Adversarial NetworkImage
🎯 What it does: A controllable image synthesis workflow is proposed, utilizing adaptive cell segmentation and style transfer to generate cervical cell images with boundary annotations, enhancing the training of detection models.
Controllable latent diffusion model to evaluate the performance of cardiac segmentation methods
Deleat-besson, Romain (Universite Claude Bernard Lyon 1), Duchateau, Nicolas (Universite Claude Bernard Lyon 1)
SegmentationGenerationData SynthesisDiffusion modelImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Generate synthetic cardiac LGE MRI images that meet clinical attributes or segmentation mask conditions using a controllable latent diffusion model (Stable Diffusion), and evaluate the performance of myocardial infarction segmentation methods with these synthetic images.
Controllable Skin Synthesis via Lesion-Focused Vector Autoregression Model
Sun, Jiajun (Monash University), Zhang, Lei (University of Exeter)
GenerationData SynthesisTransformerAuto EncoderImage
🎯 What it does: A controllable skin lesion image synthesis model based on Lesion-Focused Vector Autoregression (LF-VAR) is proposed, which can generate high-quality and controllable skin images according to lesion measurement scores and lesion types.
CoPA: Hierarchical Concept Prompting and Aggregating Network for Explainable Diagnosis
Dong, Yiheng (Huazhong University of Science and Technology), Yang, Xin (Shenzhen University)
ClassificationExplainability and InterpretabilityTransformerVision Language ModelContrastive LearningImageBiomedical Data
🎯 What it does: The CoPA framework is proposed, which achieves interpretable disease diagnosis through a multi-layer visual concept encoder, a concept alignment bottleneck layer, and a gated aggregation module. This framework utilizes the Concept-aware Embedding Generator (CEG) to extract multi-scale concept representations from each layer and guides the model's focus on specific concepts through Concept Prompt Tuning (CPT), ultimately completing disease prediction through alignment and aggregation.
Core-Periphery Principle Guided State Space Model for Functional Connectome Classification
Chen, Minheng (University of Texas at Arlington), Zhu, Dajiang (University of Georgia)
ClassificationMixture of ExpertsBiomedical DataMagnetic Resonance ImagingAlzheimer's Disease
🎯 What it does: A state space model based on the core-edge principle (CP-SSM) has been designed and implemented for binary classification of functional connectivity graphs.
Coronary Artery Calcification segmentation by using cross-frequency conditioner and geometric priors Learning
Jiang, Weili (Sichuan University), Chen, Mao (Sichuan University)
SegmentationConvolutional Neural NetworkImageComputed Tomography
🎯 What it does: This paper proposes a deep network named CAC-Net for the automatic segmentation of coronary artery calcification in cardiac CT angiography images.
CortexGen: A Geometric Generative Framework for Realistic Cortical Surface Generation Using Latent Flow Matching
Zhu, Yuanzhuo (Xi'an Jiaotong University), Wang, Fan (Xi'an Jiaotong University)
SegmentationGenerationData SynthesisAuto EncoderMeshBiomedical DataMagnetic Resonance ImagingOrdinary Differential Equation
🎯 What it does: CortexGen is proposed, a two-stage generative framework based on geometric variational autoencoders and flow matching, designed to synthesize high-resolution realistic cortical surfaces without the need for MRI data.
Cost-effective Active Learning for Nucleus Detection Using Crowdsourced Annotations with Dynamic Weighting Adjustment
Tang, Jiao (Nanjing University of Aeronautics and Astronautics), Shao, Wei (Nanjing University of Aeronautics and Astronautics)
Object DetectionImage
🎯 What it does: Designed and implemented C2AL, a cost-effective active learning framework for nuclear detection, which utilizes labeling information from multiple crowd workers with different expertise levels and labeling costs to iteratively select the most cost-effective sample-worker pairs for labeling and update the detection model.
Cross-Modal Brain Graph Transformer via Function-Structure Connectivity Network for Brain Disease Diagnosis
Feng, Jingxi (Xi'an Jiaotong University), Wang, Juan (Second Affiliated Hospital Xi'an Jiaotong University)
ClassificationTransformerMultimodalityBiomedical DataAlzheimer's Disease
🎯 What it does: This paper proposes a cross-modal brain graph Transformer (CBGT) that achieves brain disease diagnosis by integrating complementary information from functional and structural connectivity networks.
Cross-Modal Contrastive Learning for Emotion Recognition: Aligning ECG with EEG-Derived Features
Wu, Yi (Beihang University), Li, Shuai (Beijing Anzhen Hospital)
RecognitionTransformerContrastive LearningMultimodalityTime SeriesBiomedical DataElectrocardiogram
🎯 What it does: This paper aligns the emotional semantic features extracted from electroencephalogram (EEG) to electrocardiogram (ECG) through cross-modal contrastive learning, enabling emotion recognition using only ECG.
Cross-Modal CXR-CTPA Knowledge Distillation using latent diffusion priors towards CXR Pulmonary Embolism Diagnosis
Cahan, Noa (Tel Aviv University), Greenspan, Hayit (Tel Aviv University)
ClassificationKnowledge DistillationTransformerDiffusion modelImageBiomedical DataComputed Tomography
🎯 What it does: A cross-modal knowledge distillation method is proposed, which transforms 2D chest X-ray (CXR) embeddings into 3D computed tomography pulmonary angiography (CTPA) embeddings through a latent diffusion prior, enabling pulmonary embolism (PE) diagnosis using only CXR.
Cross-Modal Graph Learning for Perivascular Spaces Segmentation
Chen, Tao (Eindhoven University of Technology), Zhang, Jiong (Chinese Academy of Sciences)
SegmentationGraph Neural NetworkPrompt EngineeringVision Language ModelImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes a cross-modal graph learning framework based on a visual-language model and graph convolutional networks for the automatic segmentation of perivascular spaces (PVS) in T1-weighted magnetic resonance images;
Cross-Modality Masked Learning for Survival Prediction in ICI Treated NSCLC Patients
Xing, Qilong (Huazhong University of Science and Technology), Yang, Wei (Huazhong University of Science and Technology)
TransformerImageMultimodalityTabularComputed Tomography
🎯 What it does: A large-scale multimodal dataset for immunotherapy in NSCLC was constructed, and a cross-modal mask learning framework was proposed for survival prediction.
Cross-Modality Supervised Prostate Segmentation on CBCT for Adaptive Radiotherapy
Kovacs, Balint (German Cancer Research Center Heidelberg), Giske, Kristina (Heidelberg Institute of Radiation Oncology)
SegmentationDomain AdaptationGenerative Adversarial NetworkImageBiomedical DataComputed Tomography
🎯 What it does: A cross-modal supervised prostate CBCT segmentation framework is proposed, utilizing CycleGAN to map high-quality pCT to synthetic CBCT, and training nnU-Net on this basis, while also employing anatomical information enhancement to improve robustness against soft tissue deformation.
Cross-view Generalized Diffusion Model for Sparse-view CT Reconstruction
Chen, Jixiang (Hong Kong University of Science and Technology), Li, Xiaomeng (Southern Medical University)
RestorationDiffusion modelImageComputed Tomography
🎯 What it does: A cross-view general diffusion model (CvGDiff) is proposed for sparse view CT reconstruction, utilizing deterministic artifacts generated by angle downsampling as degradation operators, and sharing semantic information across multiple views.
CS²C: Collaborative Spatial and Spectral Neural Clustering for Organelle Segmentation from Volumetric Electron Microscopy
Jiang, Jimao (Peking University), Pei, Yuru (Peking University)
SegmentationGraph Neural NetworkAuto EncoderImage
🎯 What it does: A joint spatial-spectral deep clustering framework CS C is proposed for unsupervised VEM microscopic image organelle segmentation.
CSAL-3D: Cold-start Active Learning for 3D Medical Image Segmentation via SSL-driven Uncertainty-Reinforced Diversity Sampling
Zhu, Ning (University of Electronic Science and Technology of China), Wang, Guotai (University Of Electronic Science And Technology Of China)
SegmentationTransformerContrastive LearningImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: A CSAL-3D framework is proposed to achieve one-shot active learning for 3D medical image segmentation, combining self-supervised learning-driven uncertainty-enhanced diversity sampling.
CSAP-Assist: Instrument-Agent Dialogue Empowered Vision-Language Models for Collaborative Surgical Action Planning
Zhang, Jie (Chinese University of Hong Kong), Dou, Qi (Huazhong University of Science and Technology)
Robotic IntelligenceTransformerLarge Language ModelVision Language ModelMultimodality
🎯 What it does: The task of Collaborative Surgical Action Planning (CSAP) is proposed, and the CSAP-Assist framework is developed based on a vision-language model, which can generate action plans for multi-tool collaboration according to surgical objectives.
CT-Based Hippocampus Segmentation with Dual-Decoder Network (HDD-Net)
Son, Wonjun (Kyungpook National University), Lee, Hyunyeol (Kyungpook National University)
SegmentationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: A deep learning model HDD-Net for hippocampus segmentation in CT images is proposed.
CTSL: Codebook-based Temporal-Spatial Learning for Accurate Non-Contrast Cardiac Risk Prediction Using Cine MRIs
Su, Haoyang (Fudan University), Wang, Xiaosong (Shanghai Artificial Intelligence Laboratory)
ClassificationKnowledge DistillationRepresentation LearningContrastive LearningImageMultimodalityBiomedical DataMagnetic Resonance ImagingElectronic Health Records
🎯 What it does: This study proposes a self-supervised CTSL framework that learns motion-aware spatiotemporal features from non-contrast short-axis cine MRI sequences and integrates them with electronic health records to predict cardiac MACE risk.