MICCAI 2025 Papers — Page 6
International Conference on Medical Image Computing and Computer-Assisted Intervention · 1027 papers
LiteTracker: Leveraging Temporal Causality for Accurate Low-latency Tissue Tracking
Karaoglu, Mert Asim (ImFusion GmbH), Ladikos, Alexander (Technische Universität München)
Object TrackingComputational EfficiencyTransformerVideoBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A low-latency organization tracking method called LiteTracker is proposed, based on CoTracker3 and achieving real-time end-to-end tracking.
LKA: Large Kernel Adapter for Enhanced Medical Image Classification
Zhu, Ziquan (University of Leicester), Liu, Zhe (Shenzhen University)
ClassificationTransformerImageBiomedical Data
🎯 What it does: This paper proposes the Large Kernel Adapter (LKA), which enhances the receptive field by introducing channel-level large kernel convolutions when adapting pre-trained models, thereby improving the accuracy of medical image classification.
LLM-Powered Cross-Modal Alignment for Explainable Seizure Detection from EEG
Riazi, Maryam (Boston University), Venkataraman, Archana (Boston University)
Anomaly DetectionExplainability and InterpretabilityRecurrent Neural NetworkLarge Language ModelContrastive LearningMultimodalityTime SeriesBiomedical DataElectronic Health Records
🎯 What it does: The SzXAI framework is proposed, which achieves interpretable predictions of EEG etiology on any epilepsy detection model through cross-modal alignment and attention pooling, and automatically generates readable summaries using LLM.
LNODE: Uncovering the Latent Dynamics of Aβ in Alzheimer’s Disease
Wen, Zheyu (University of Texas at Austin), Biros, George (University of Texas at Austin)
Time SeriesBiomedical DataPositron Emission TomographyAlzheimer's DiseaseOrdinary Differential Equation
🎯 What it does: This paper constructs a network ODE model with latent states, LNODE, to model the disease progression of Aβ-PET in 585 ADNI subjects, while inferring individual and group parameters to explore the subtypes of Aβ progression.
Localization Lens for Improving Medical Vision-Language Models
Farooq, Hasan (Lahore University of Management Sciences), Mahmood, Arif (Information Technology University of the Punjab)
RecognitionSegmentationTransformerVision Language ModelContrastive LearningImageMultimodalityBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes the 'Positioning Lens' - a set of expert-validated multiple medical image enhancement representations, combined with pixel rearrangement and decoupled contrastive loss, to improve the performance of medical visual-language models (Med-VLM) in anatomical structure and spatial positioning reasoning.
Location-Aware Parameter Fine-Tuning for Multimodal Image Segmentation
Gao, Sicong (University of New South Wales), Song, Yang (University of New South Wales)
SegmentationSupervised Fine-TuningPrompt EngineeringImageMultimodalityBiomedical DataComputed TomographyUltrasound
🎯 What it does: A lung infection segmentation framework is proposed based on CLIP to generate multimodal prompts and perform lightweight fine-tuning on SAM2.
Location-Guided Automated Lesion Captioning in Whole-body PET/CT Images
Yu, Mingyang, Shen, Dinggang (Shanghai United Imaging Intelligence Co., Ltd.)
Object DetectionSegmentationTransformerPrompt EngineeringImageMultimodalityBiomedical DataComputed TomographyPositron Emission Tomography
🎯 What it does: A framework for automatic lesion description in whole-body PET/CT is proposed, combining CLIP-based localization, localization guidance prompts (CGLP), and dynamic window settings (DWS).
Longitudinal anatomical attention maps for recognizing diagnostic errors from radiologists’ eye movements
Anikina, Anna (University of Copenhagen), Ibragimov, Bulat (University of Iowa)
RecognitionSegmentationRecurrent Neural NetworkTransformerImageBiomedical Data
🎯 What it does: This paper proposes a long-term attention mapping method that combines eye-tracking information with visual Transformers to predict diagnostic errors in chest X-ray readings.
Longitudinal MRI-Clinical Multimodal Fusion for pCR Prediction in Breast Cancer
Ma, Dingrui (Shanghai Jiao Tong University), Guan, Xinping (Shanghai Jiao Tong University)
ClassificationConvolutional Neural NetworkMultimodalityBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A multi-modal deep learning framework LMF is proposed to predict whether breast cancer patients achieve pathological complete response (pCR) after neoadjuvant chemotherapy, combining MRI images with clinical information and explicitly modeling chemotherapy-induced imaging changes.
LTSE: Language-guided Tissue Referring Segmentation in Pathology Images with Adaptive Expert Mixture
Tang, Jiao (Nanjing University of Aeronautics and Astronautics), Zhang, Daoqiang (Nanjing University of Aeronautics and Astronautics)
SegmentationTransformerLarge Language ModelMixture of ExpertsImageTextMultimodalityBiomedical Data
🎯 What it does: This paper proposes a pathology image language-guided tissue segmentation assistant LTSE based on a multimodal large language model, which can accurately segment target tissue areas based on text descriptions provided by doctors.
LVPNet: A Latent-variable-based Prediction-driven End-to-end Framework for Lossless Compression of Medical Images
Song, Chenyue (Harbin Institute of Technology), Li, Xiang (Nanyang Technological University)
CompressionConvolutional Neural NetworkImageBiomedical Data
🎯 What it does: An end-to-end lossless medical image compression framework named LVPNet is proposed, which utilizes a Global Multi-Scale Perception Module (GMSM) to extract low-dimensional latent variables and generates pixel distributions through a prediction module, followed by entropy coding.
Lymph Node Metastasis Classification with Prototype-guided Multiple Instance Aggregation and Heterogeneous Feature Fusion
Li, Haoshen (Peking University), Jin, Dakai (Alibaba Group)
ClassificationConvolutional Neural NetworkImageBiomedical DataComputed Tomography
🎯 What it does: This paper proposes a dual-stream prototype-guided multi-instance learning framework that integrates slice-level features and heterogeneous medical imaging features for the determination of lymph node metastasis in esophageal cancer patients from CT scans.
Lymphoma Prognosis with Lesion-Anatomy Context Fusion and Attention-Based Multi-Lesion Aggregation
Zhang, Song (Chinese Academy of Sciences), Yan, Ke (China Medical University)
ClassificationSegmentationOptimizationMultimodalityBiomedical DataComputed TomographyPositron Emission Tomography
🎯 What it does: A prognosis model for lymphoma, LAMP, based on PET/CT, is proposed to predict the prognosis (PFS/OS) of DLBCL patients through lesion-anatomical context fusion and attention-based multi-lesion aggregation.
M3HL: Mutual Mask Mix with High-Low Level Feature Consistency for Semi-Supervised Medical Image Segmentation
Liu, Yajun (Shanghai Jiao Tong University), Li, Dongying (Shanghai Jiao Tong University)
SegmentationImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes a semi-supervised medical image segmentation method called MHL3, based on Mutual Mask Mix and consistency of high and low-level features.
MAARTA:Multi-Agentic Adaptive Radiology Teaching Assistant
Awasthi, Akash (University of Houston), Nguyen, Hien V. (University of Houston)
Large Language ModelAgentic AIImageTextBiomedical DataMagnetic Resonance ImagingChain-of-Thought
🎯 What it does: Proposes the MAARTA multi-agent adaptive radiology teaching assistant, which constructs cognitive maps using eye movement data and reports to provide personalized perceptual error feedback.
MadCLIP: Few-shot Medical Anomaly Detection with CLIP
Shiri, Mahshid (University of Verona), Murino, Vittorio (University of Verona)
Anomaly DetectionTransformerContrastive LearningImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: This paper proposes a few-shot medical anomaly detection framework called MadCLIP based on CLIP, which learns normal and abnormal features through a dual-branch adapter and learnable text prompts, achieving image-level anomaly classification and pixel-level anomaly segmentation.
MAGNET-AD: Multitask Spatiotemporal GNN for Interpretable Prediction of PACC and Conversion Time in Preclinical Alzheimer
Hassan, Salma (Mohamed Bin Zayed University of Artificial Intelligence), Yaqub, Mohammad (Mohamed bin Zayed University of Artificial Intelligence)
Explainability and InterpretabilityDrug DiscoveryGraph Neural NetworkMultimodalityBiomedical DataAlzheimer's DiseaseElectronic Health Records
🎯 What it does: A multi-task spatiotemporal graph neural network called MAGNET-AD is proposed for predicting PACC scores and conversion times in preclinical Alzheimer's disease patients.
MAGO-SP: Detection and Correction of Water-Fat Swaps in Magnitude-Only VIBE MRI
Graf, Robert (Technical University of Munich), Kirschke, Jan (Technical University of Munich)
SegmentationGenerationOptimizationDiffusion modelImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes a complete automated pipeline (MAGO-SP) for detecting and correcting water-fat exchange errors in volumetric images (VIBE) caused by missing magnitude information. The pipeline includes: ① Using the nnU-Net segmentation network to identify whether water or fat regions have been exchanged; ② Employing the Palette Conditional Denoising Diffusion Network to generate a prior for the 'water' image; ③ Using the prior as an initial value, combined with the physical constraints of the MAGO/MAGORINO optimization model to restore accurate water-fat separation.
MAK-GAN: Multi-level Adaptive Convolutional Kernels for Asymmetric Multi-modal PET Reconstruction
Zeng, Xinyi (Sichuan University), Shen, Dinggang (Shanghai United Imaging Intelligence Co., Ltd.)
RestorationGenerationConvolutional Neural NetworkTransformerGenerative Adversarial NetworkMultimodalityBiomedical DataMagnetic Resonance ImagingPositron Emission TomographyAlzheimer's Disease
🎯 What it does: The MAK-GAN framework is proposed to reconstruct low-dose PET into standard-dose PET, utilizing MRI auxiliary information for asymmetric multimodal reconstruction.
MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment
Yan, Siyuan (Monash University), Ge, Zongyuan (Melbourne University)
ClassificationRetrievalTransformerLarge Language ModelVision Language ModelContrastive LearningImageTextMultimodality
🎯 What it does: A multi-faceted knowledge-enhanced visual-language pre-training framework called MAKE is proposed, specifically designed for dermatological zero-shot diagnosis, concept annotation, and cross-modal retrieval.
Mamba Guided Boundary Prior Matters: A New Perspective for Generalized Polyp Segmentation
Dutta, Tapas K. (University of Surrey), Jha, Debesh (University of South Dakota)
SegmentationKnowledge DistillationImageBiomedical Data
🎯 What it does: Aiming at the segmentation problem of weakly bounded polymorphic polyps in colonoscopy images, the SAM-MaGuP framework is proposed.
MAMBA-Based Weakly Supervised Medical Image Segmentation with Cross-Modal Textual Information
Pan, Zhen (Shandong Normal University), Zheng, Yuanjie (Shandong Normal University)
SegmentationTransformerContrastive LearningImageTextMultimodalityBiomedical Data
🎯 What it does: A weakly supervised medical image segmentation framework based on Mamba, TIFCMamba, is proposed, utilizing text descriptions as supervisory information and achieving segmentation through cross-modal alignment.
MambaMER: Adaptive EEG-Guided Multimodal Emotion Recognition with Mamba
Ping, Xiangle (Shandong Normal University), Zheng, Yuanjie (Shandong Normal University)
RecognitionTransformerMultimodality
🎯 What it does: A framework for EEG-guided adaptive multimodal emotion recognition based on Mamba is proposed, which utilizes multi-scale EEG to suppress interference from eye movement features and achieves cross-modal deep interaction through a dual fusion mechanism.
MammoTracker: Mask-Guided Lesion Tracking in Temporal Mammograms
Liu, Xuan (Duke University), Lo, Joseph Y. (Duke University)
Object TrackingConvolutional Neural NetworkContrastive LearningImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A mask-guided framework for tracking temporal lesions in mammography (MammoTracker) is proposed, achieving lesion localization through a three-stage process from coarse to fine.
Marker-less Head Pose Tracking for Image-guided Cerebral Artery Navigation
Wang, Qiuying (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences), Liu, Jia (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences)
Object TrackingPose EstimationConvolutional Neural NetworkImageMagnetic Resonance Imaging
🎯 What it does: Construct a 3D facial model guided by MRI, utilizing a markerless RGBD camera for real-time head pose tracking, and project cerebral artery images onto the head's RGB images for navigation.
MARSeg: Enhancing Medical Image Segmentation with MAR and Adaptive Feature Fusion
Hwang, Jeonghyun (Ewha Womans University), Choi, Jang-Hwan (Ewha Womans University)
SegmentationDiffusion modelAuto EncoderImageBiomedical DataComputed Tomography
🎯 What it does: A multi-stage segmentation framework MARSeg based on the Masked Autoregressive model is proposed, combined with an adaptive feature fusion module to achieve fine medical image segmentation.
Mask2Surface: Motion Correction and Super-Resolution for Cardiac Surface Reconstruction Using Latent Diffusion
Zhang, Zichen (ShanghaiTech University), Cui, Zhiming (ShanghaiTech University)
RestorationSegmentationSuper ResolutionConvolutional Neural NetworkDiffusion modelAuto EncoderImagePoint CloudMagnetic Resonance Imaging
🎯 What it does: This study proposes a CMR motion correction and super-resolution method based on a latent diffusion model for reconstructing high-fidelity left ventricular myocardial surfaces.
Masked Contrastive Language-Image Modeling For Brain Segmentation
Liang, Jianwen (Southern University of Science and Technology), Tang, Xiaoying (Chinese University of Hong Kong)
SegmentationConvolutional Neural NetworkContrastive LearningImageTextBiomedical DataMagnetic Resonance ImagingAlzheimer's Disease
🎯 What it does: A Mask Contrastive Language-Image Modeling (MCLIM) framework is proposed, which combines text descriptions generated from brain atlases with a masked image recovery task to achieve self-supervised pre-training for brain MRI.
MAST-Pro: Dynamic Mixture-of-Experts for Adaptive Segmentation of Pan-Tumors with Knowledge-Driven Prompts
Meng, Runqi (ShanghaiTech University), Shen, Dinggang (Shanghai United Imaging Intelligence Co., Ltd.)
SegmentationConvolutional Neural NetworkSupervised Fine-TuningPrompt EngineeringMixture of ExpertsBiomedical DataComputed Tomography
🎯 What it does: The MAST-Pro framework is proposed for multi-tumor segmentation, combining dynamic mixture of experts and text/anatomical prompts to enhance segmentation accuracy.
MatchGen: Detecting Medical Abnormal Region by Generating Matched Normal Regions
Ma, Xinyu (McMaster University), Chu, Lingyang (McMaster University)
SegmentationAnomaly DetectionOptimizationAuto EncoderGenerative Adversarial NetworkImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: This paper proposes a framework (MatchGen) for optimizing pseudo-normal images during the testing phase, which improves the accuracy of medical anomaly region detection by minimizing the pixel-level differences between the input image and the generated image.
MAUP: Training-free Multi-center Adaptive Uncertainty-aware Prompting for Cross-domain Few-shot Medical Image Segmentation
Zhu, Yazhou (Nanjing University of Science and Technology), Zhang, Haofeng (Nanjing University of Science and Technology)
SegmentationPrompt EngineeringImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: This paper proposes a training-free multi-center adaptive uncertainty-aware prompting strategy (MAUP) that utilizes the pre-trained Segment Anything Model to achieve cross-domain few-shot medical image segmentation.
Maverick: Collaboration-free Federated Unlearning for Medical Privacy
Ong, Win Kent (Universiti Malaya), Chan, Chee Seng (Universiti Malaya)
Federated LearningSafty and PrivacyComputational EfficiencyConvolutional Neural NetworkGaussian SplattingBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Maverick is proposed, a collaboration-free federated unlearning framework that allows individual clients to locally implement forgetting of their data without the participation of other clients.
MCA-RG: Enhancing LLMs with Medical Concept Alignment for Radiology Report Generation
Xing, Qilong (Huazhong University of Science and Technology), Yang, Wei (Huazhong University of Science and Technology)
GenerationTransformerLarge Language ModelSupervised Fine-TuningContrastive LearningTextMultimodalityElectronic Health Records
🎯 What it does: This paper proposes the MCA-RG framework, which aligns and enhances imaging features using medical concepts (anatomy and pathology) and guides large language models to generate radiology reports based on conceptual features.
MDAA-Diff: CT-Guided Multi-Dose Adaptive Attention Diffusion Model for PET Denoising
Niu, Xiaolong (Southern Medical University), Lu, Lijun (Southern Medical University)
RestorationDiffusion modelBiomedical DataComputed TomographyPositron Emission Tomography
🎯 What it does: This paper proposes a multi-dose adaptive attention diffusion model (MDAA-Diff) based on CT guidance, aimed at restoring low-dose PET to standard-dose PET.
MDPG: Multi-domain Diffusion Prior Guidance for MRI Reconstruction
Zhang, Lingtong (University of Science and Technology of China), Qiu, Bensheng (University of Science and Technology of China)
RestorationDiffusion modelBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A multi-domain diffusion prior-guided MRI reconstruction framework (MDPG) is proposed, which combines the prior guidance of a pre-trained latent diffusion model (LDM) in both latent and image domains. By utilizing the Visual-Mamba backbone, Latent Guided Attention (LGA), Dual-Domain Fusion Branch (DFB), and k-space regularization based on the NACS set, the quality of compressed sensing MRI reconstruction is significantly improved.
Med-BiasX: Robust Medical Visual Question Answering with Language Biases
Zhu, Huanjia (South China Normal University), Chen, Bingzhi (Shenzhen University)
RecognitionOptimizationVision Language ModelImageMultimodalityBiomedical DataBenchmark
🎯 What it does: This paper proposes the Med-BiasX framework, which addresses the issue of language bias in medical visual question answering by designing two mechanisms: energy constraint and distribution calibration, to enhance the model's reliance on image information and robustness.
Med-LEGO: Editing and Adapting toward Generalist Medical Image Diagnosis
Zhu, Yitao (ShanghaiTech University), Wang, Qian (United Imaging Intelligence)
ClassificationDomain AdaptationComputational EfficiencyTransformerSupervised Fine-TuningImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Proposes the Med-LEGO framework, which utilizes SVD-LoRA to integrate multi-task specific models into a general medical imaging diagnostic model without the need for additional training.
MedAgentSim: Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions
Almansoori, Mohammad (Mohamed bin Zayed University of Artificial Intelligence), Cholakkal, Hisham (Mohamed bin Zayed University of Artificial Intelligence)
TransformerLarge Language ModelVision Language ModelTextMultimodalityBiomedical DataElectronic Health RecordsBenchmarkRetrieval-Augmented GenerationChain-of-Thought
🎯 What it does: This paper presents MedAgentSim, an open-source multi-agent clinical simulation environment where doctors, patients, and measurement agents actively obtain test results and diagnose conditions through multi-turn dialogues, while introducing a self-improvement mechanism to enhance the performance of LLMs in dynamic diagnostic scenarios.
MedDiff-FT: Data-Efficient Diffusion Model Fine-tuning with Structural Guidance for Controllable Medical Image Synthesis
Xie, Jianhao (Peking University Shenzhen Graduate School), Luo, Guibo (Peking University Shenzhen Graduate School)
SegmentationGenerationData SynthesisDiffusion modelImageBiomedical DataUltrasound
🎯 What it does: Using a small number (about 30) of medical image-mask pairs, we fine-tuned Stable Diffusion 1.5 to achieve controllable generation of medical image-mask pairs with structural dependencies and domain specificity. We enhanced the generation quality through automatic quality assessment and mask erosion; the generated data was used to augment five medical segmentation datasets, significantly improving the performance of downstream segmentation models.
MedGCD: Generalized Category Discovery in Medical Imaging
Das, Ankit (Agency for Science, Technology and Research), Savitha, Ramasamy (Agency for Science, Technology and Research)
ClassificationRecognitionConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A general category discovery framework for medical images, MedGCD, is proposed, which can cluster new categories and classify known categories by utilizing weak-strong data augmentation, dual strong view consistency, and confidence-aware pairing objectives in the presence of both labeled and unknown categories.
MedGNN: General Medical Image Recognition Network via GNN Visual Representations
Ye, Jiayu (Guangdong University of Technology), Cheng, Guanwei (Alibaba International Digital Commerce Group)
ClassificationRecognitionGraph Neural NetworkImageBiomedical DataAlzheimer's Disease
🎯 What it does: Construct a graph-structured visual representation of medical images and propose the MedGNN model for image classification.
MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization
Xu, Huihui (Shanghai Artificial Intelligence Laboratory), He, Junjun (Shanghai Artificial Intelligence Laboratory)
Object DetectionSegmentationTransformerReinforcement LearningVision Language ModelImageBiomedical Data
🎯 What it does: This paper proposes a medical image localization framework MedGround-R1 based on reinforcement learning, utilizing GRPO for CoT-free training on VLM, and enhancing localization accuracy through spatial-semantic rewards and the Chain-of-Box template.
MeDi: Metadata-Guided Diffusion Models for Mitigating Biases in Tumor Classification
Drexlin, David Jacob (Technische Universität Berlin), Müller, Klaus-Robert (Technische Universität Berlin)
ClassificationGenerationData SynthesisDiffusion modelImage
🎯 What it does: A framework called MeDi (Metadata-Guided Diffusion) is proposed and implemented, which simultaneously considers class labels and multidimensional metadata (such as medical center, race, gender, etc.) in the generation of pathological images, thereby achieving targeted data augmentation for underrepresented subgroups and mitigating bias.
Medical Contrastive Learning of Positive and Negative Mentions
Wu, WeiLong (Tsinghua University), Wu, Ji (Tsinghua University)
ClassificationRetrievalLarge Language ModelContrastive LearningImageTextMultimodalityBiomedical DataComputed Tomography
🎯 What it does: A visual entailment-based triplet contrastive learning framework VECL is proposed, which achieves more precise cross-modal feature alignment using positive and negative medical report mentions.
Medical Large Vision Language Models with Multi-Image Visual Ability
Yang, Xikai (Chinese University of Hong Kong), Heng, Pheng-Ann (Chinese University of Hong Kong)
TransformerLarge Language ModelSupervised Fine-TuningVision Language ModelImageTextMultimodalityBiomedical DataBenchmark
🎯 What it does: A Med-MIM dataset containing 83.2K medical multi-image QA instruction samples was constructed, and based on this, internal and external testing benchmarks were developed.
Medical-Knowledge Driven Multiple Instance Learning for Classifying Severe Abdominal Anomalies on Prenatal Ultrasound
Liang, Huanwen (Shenzhen University), Ni, Dong (People's Hospital of Guangxi Zhuang Autonomous Region)
ClassificationAnomaly DetectionTransformerPrompt EngineeringMixture of ExpertsImageBiomedical DataUltrasound
🎯 What it does: A case-level prenatal abdominal ultrasound anomaly classification method based on multi-instance learning is proposed, which can complete diagnosis without standard plane localization.
MedICL: In-Context Learning for Semantically Enhanced AKI Prediction in Cardiac Surgery
Su, Chenyang (City University of Hong Kong), Meng, Gaofeng (Chinese Academy of Sciences)
ClassificationAnomaly DetectionTransformerLarge Language ModelTextTabularBiomedical DataElectronic Health Records
🎯 What it does: Proposes the MedICL framework, which enhances the prediction of acute kidney injury after cardiac surgery through contextual learning combined with semantic matching and task adaptation.
MedIQA: A Scalable Foundation Model for Prompt-Driven Medical Image Quality Assessment
Xun, Siyi (Macao Polytechnic University), Tan, Tao (Macao Polytechnic University)
TransformerPrompt EngineeringImageMultimodalityBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: This paper presents MedIQA, a prompt-driven foundational model for medical image quality assessment.
MedNNS: Supernet-based Medical Task-Adaptive Neural Network Search
Mecharbat, Lotfi Abdelkrim (Mohammed Bin Zayed University of Artificial Intelligence), Yaqub, Mohammad (Mohamed bin Zayed University of Artificial Intelligence)
ClassificationNeural Architecture SearchImageMultimodalityBiomedical Data
🎯 What it does: This paper proposes a medical task adaptive neural network search framework based on a super network, MedNNS, which can simultaneously select the optimal network structure and corresponding pre-trained weights when given a medical dataset.
MedPro-DG: Domain-Aware Masked Contrastive Prompt Learning of Institution Generalization for Outcome Prediction
Wang, Rongfang (Xidian University), Wang, Kai (KUMC)
ClassificationDomain AdaptationConvolutional Neural NetworkPrompt EngineeringContrastive LearningImageTextBiomedical DataComputed TomographyElectronic Health Records
🎯 What it does: This paper proposes the MedPro-DG framework, which combines CT images and clinical variables to achieve domain generalization for multi-institutional head and neck cancer outcome prediction through visual-language fusion.
MedSoft-Diffusion: Medical Semantic-Guided Diffusion Model with Soft Mask Conditioning for Vertebral Disease Diagnosis
He, Shidan (Sun Yat-Sen University), Zhao, Shen (Tianjin University of Technology)
ClassificationGenerationDiffusion modelImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Developed the MedSoft-Diffusion framework, which generates vertebral medical images with specified lesion characteristics in latent diffusion models through a Medical Semantic Controller (MSC) and Soft Mask Illustration Strategy (SMIS);
MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
Pan, Jiazhen (Technical University of Munich), Rueckert, Daniel (Technical University of Munich)
OptimizationTransformerReinforcement LearningVision Language ModelMultimodalityBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: Designed and trained MedVLM-R1, a visual language model capable of explicitly generating reasoning processes in medical visual question answering, utilizing GRPO reinforcement learning to encourage the model to produce logical reasoning on its own.
MELON: Multimodal Mixture-of-Experts with Spectral-Temporal Fusion for Long-Term MObility EstimatioN in Critical Care
Zhang, Jiaqing (University of Florida), Rashidi, Parisa (University of Florida)
ClassificationRecognitionTransformerMixture of ExpertsMultimodalityTime SeriesBiomedical DataElectronic Health Records
🎯 What it does: This paper proposes a dual-branch multimodal framework named MELON for predicting the movement status of ICU patients over a 12-hour period.
Memory-Augmented Incomplete Multimodal Survival Prediction via Cross-Slide and Gene-Attentive Hypergraph Learning
Qu, Mingcheng (Harbin Institute of Technology), Fan, Lei (University of New South Wales)
ClassificationGraph Neural NetworkContrastive LearningMultimodalityBiomedical Data
🎯 What it does: A memory-enhanced multimodal survival prediction framework M²Surv is proposed, which can simultaneously handle multiple pathological slides (including FFPE and FF) and genomic data, while maintaining high predictive performance even in the presence of missing modalities.
Memory-Augmented SAM2 for Training-Free Surgical Video Segmentation
Yin, Ming (University of Exeter), Fu, Zeyu (University of Exeter)
SegmentationVideo
🎯 What it does: This paper proposes a training-agnostic MA-SAM2 framework that achieves multi-object surgical video segmentation with a single prompt, addressing the misjudgment and tracking failure issues of SAM2 in fast motion, occlusion, and complex interactions.
Mesh4D: A Motion-Aware Multi-View Variational Autoencoder for 3D+t Mesh Reconstruction
Qiao, Mengyun (University College London), Bai, Wenjia (Imperial College London)
GenerationData SynthesisTransformerAuto EncoderImageVideoMeshBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Utilizing multi-view cardiac MRI image sequences, the model jointly learns cardiac shape and motion, generating a complete 3D+t mesh model directly from the images.
Meta-analysis guided multi-task graph transformer network for diagnosis of neurological disease and cognitive deficits
Xia, Jing (Nanyang Technological University), Rajapakse, Jagath C. (Nanyang Technological University)
ClassificationGraph Neural NetworkTransformerGraphBiomedical DataMagnetic Resonance ImagingAlzheimer's Disease
🎯 What it does: A multi-task graph Transformer network based on meta-analysis is proposed, which can simultaneously predict neurological diseases (such as schizophrenia and ADHD) and related cognitive deficits, revealing changes in functional connectivity.
Meta-Learning Physics-Informed Neural Networks for Personalized Cardiac Modeling
Toloubidokhti, Maryam (Rochester Institute of Technology), Wang, Linwei (Rochester Institute of Technology)
Meta LearningBiomedical DataMagnetic Resonance ImagingElectrocardiogramPhysics Related
🎯 What it does: This paper proposes a meta-learning based PINN framework for rapid personalization of cardiac models.
Meta-Learning-Driven CT Morphology Disentangled Diffusion Model for Multi-Region SPECT Attenuation Correction
Yang, Haoran (Jiangnan University), Pan, Xiang (Hangzhou Dianzi University)
RestorationGenerationMeta LearningDiffusion modelImageBiomedical DataComputed TomographyPositron Emission Tomography
🎯 What it does: A SPECT attenuation correction method based on diffusion models has been developed, which achieves decoupling of CT priors through a morphological structure attention fusion module and completes the correction using only SPECT images during the inference phase.
Metastatic Lymph Node Station Classification in Esophageal Cancer via Prior-guided Supervision and Station-Aware Mixture-of-Experts
Li, Haoshen (Peking University), Jin, Dakai (Alibaba Group)
ClassificationObject DetectionMixture of ExpertsImageBiomedical DataComputed Tomography
🎯 What it does: A CT-based LN site metastasis prediction model was developed using LN site labels from large-scale pathology reports.
MG-UNet: A Memory-Guided UNet for Lesion Segmentation in Chest Images
Ding, Shuaipeng (Chongqing Normal University), Wang, Chao (Chongqing Normal University)
SegmentationConvolutional Neural NetworkImageMultimodalityBiomedical DataComputed Tomography
🎯 What it does: Proposes the Memory-Guided UNet model, which utilizes a learnable memory pool to store textual information during the training phase, enabling chest imaging lesion segmentation without text input during inference.
MGG-Net: A Multi-Modal Feature Extraction and Global-Aware Feature Graph-Based Deep Learning Network for MGMT Status Classification in Glioma
Liu, Haoyang (Tohoku University), Homma, Noriyasu (Tohoku University)
ClassificationConvolutional Neural NetworkGraph Neural NetworkImageMultimodalityBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes MGG-Net, a multi-scale multi-modal feature extraction network that combines CNN and GCN for non-invasive prediction of the MGMT methylation status of gliomas using multi-sequence MRI and radiomics.
MIBF-Net: Multi-modal Information Balanced Fusion Network for Clinical Diagnosis via Patient Narratives and Lesion Image
Tang, Zixuan (Sun Yet-Sen University), Zhao, Shen (Tianjin University of Technology)
ClassificationGenerationRetrievalConvolutional Neural NetworkTransformerLarge Language ModelImageTextMultimodalityElectronic Health RecordsRetrieval-Augmented Generation
🎯 What it does: Combining patient narratives with lesion images, we propose a Retrieval-Augmented Medical Report Generation Module (RANGM) and a Multi-Modal Information Balanced Fusion Network (MIBF-Net), enhancing diagnostic performance through Modal Prediction Deviation Loss (MP-Loss).
MiCo: Multiple Instance Learning with Context-Aware Clustering for Whole Slide Image Analysis
Li, Junjian (Central South University), Wang, Jianxin (Institute of Guizhou Aerospace Measuring and Testing Technology)
ClassificationSegmentationImageBiomedical Data
🎯 What it does: MiCo is proposed under the multi-instance learning framework, utilizing context-aware clustering to improve cross-region semantic association modeling for whole slide images (WSI).
MicroMIL: Graph-Based Multiple Instance Learning for Context-Aware Diagnosis with Microscopic Images
Kim, JongWoo (Korea Advanced Institute of Science and Technology), Yi, Mun Yong (Korea Advanced Institute of Science and Technology)
ClassificationObject DetectionGraph Neural NetworkImageBiomedical Data
🎯 What it does: This paper designs and implements a weakly supervised multi-instance learning framework called MicroMIL for traditional optical microscope images, achieving tumor diagnosis through representative image extraction and graph convolutional networks.
Mind the Detail: Uncovering Clinically Relevant Image Details in Accelerated MRI with Semantically Diverse Reconstructions
Morshuis, Jan Nikolas (University of Tübingen), Hein, Matthias (University of Tübingen)
RestorationObject DetectionSegmentationTransformerDiffusion modelImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A post-processing method called Semantically Diverse Reconstructions (SDR) is proposed, which generates a set of semantically diverse reconstructions consistent with the sampled data based on existing MRI reconstructions, in order to reduce the risk of lesion miss detection caused by under-sampling.
MindLink: Subject-agnostic Cross-Subject Brain Decoding Framework
Jung, Sungyoon (Pohang University of Science and Technology), Kim, Won Hwa (Pohang University of Science and Technology)
Domain AdaptationRepresentation LearningTransformerDiffusion modelContrastive LearningImageMultimodalityBiomedical DataMagnetic Resonance Imaging
🎯 What it does: The MindLink framework is proposed to construct a unified model for spatial structure-preserving brain image decoding of 3D fMRI across multiple subjects.
Minuscule Cell Detection in AS-OCT Images with Progressive Field-of-View Focusing
Chen, Boyu, Taylor, Paul (University College London)
Object DetectionSegmentationImageUltrasound
🎯 What it does: The MCD framework is proposed to achieve automatic detection and counting of extremely small inflammatory cells in AS-OCT images.
Mission Balance: Generating Under-represented Class Samples using Video Diffusion Models
Venkatesh, Danush Kumar (TUD), Speidel, Stefanie (National Center for Tumor Diseases)
RecognitionGenerationData SynthesisTransformerDiffusion modelVideoBiomedical Data
🎯 What it does: Utilize a text-conditioned diffusion model to synthesize low-frequency out-of-class surgical video samples to alleviate data imbalance.
MixStyleFlow: Domain Generalization in Medical Image Segmentation using Normalizing Flows
Safdari, Reza (University of Hong Kong), Bae, Kyongtae Tyler (University of Hong Kong)
SegmentationDomain AdaptationFlow-based ModelImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes a feature style mixing method based on regularized flow (MixStyleFlow) to improve the generalization performance of medical image segmentation models on unseen domains.
MM-DINOv2: Adapting Foundation Models for Multi-Modal Medical Image Analysis
Scholz, Daniel (Technical University of Munich), Wiestler, Benedikt (Technical University of Munich)
ClassificationSegmentationTransformerSupervised Fine-TuningContrastive LearningMultimodalityBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper presents MM-DINOv2, a framework that adapts the pre-trained visual foundation model DINOv2 to multimodal medical imaging tasks, achieving robustness to missing sequences and the ability to utilize unlabeled data through multimodal patch embedding, full-modality masking, and semi-supervised learning.
MMBNA: Masked Multiview Brain Network Analysis via Disentangling for Alzheimer’s Early Diagnosis with fMRI
Meng, Dequan (Shandong Jianzhu University), Liu, Mingxia (University of North Carolina at Chapel Hill)
ClassificationGraph Neural NetworkTransformerTime SeriesBiomedical DataMagnetic Resonance ImagingAlzheimer's Disease
🎯 What it does: The MMBNA framework is proposed, which achieves early diagnosis of Alzheimer's disease under rs-fMRI through multi-measurement brain network construction, random masking, and decoupled learning.
MNM: Multi-level Neuroimaging Meta-analysis with Hyperbolic Brain-Text Representations
Baek, Seunghun (Pohang University of Science and Technology), Kim, Won Hwa (Pohang University of Science and Technology)
RetrievalRepresentation LearningLarge Language ModelContrastive LearningTextBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes a multi-layer neural imaging meta-analysis framework (MNM) based on hyperbolic geometry, which achieves semantic alignment between brain activation maps and corresponding text by embedding them into the same hyperbolic space while maintaining the hierarchical structure of brain activations.
MOC: Meta-Optimized Classifier for Few-Shot Whole Slide Image Classification
Xiang, Tianqi (Hong Kong University of Science and Technology), Li, Xiaomeng (Southern Medical University)
ClassificationMeta LearningVision Language ModelImage
🎯 What it does: This paper proposes a Meta-Optimized Classifier (MOC) for few-shot whole slide image classification, which dynamically combines multiple base classifiers through a meta-learner to achieve global optimal discrimination of images.
MoDiff: A Morphology-Emphasized Diffusion Model for Ambiguous Medical Image Segmentation
Ahn, Jung Su (Yonsei University), Cho, Young-Rae (Yonsei University)
SegmentationDiffusion modelImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: MoDiff is proposed, a diffusion model based on probabilistic label mapping and learnable frequency domain filtering, aimed at addressing the ambiguity problem in medical image segmentation.
MoE-SAM: Enhancing SAM for Medical Image Segmentation with Mixture-of-Experts
Li, Ruocheng (Zhejiang University), Bu, Jiajun (Zhejiang University)
SegmentationTransformerPrompt EngineeringMixture of ExpertsImageComputed Tomography
🎯 What it does: This paper proposes MoE-SAM, which enhances medical image segmentation performance by incorporating a Mixture-of-Experts mechanism and a lightweight prompt embedding generator into the image encoder of the SAM pre-trained model.
MoMIL: Mixture of Multi-Instance Learners for Modeling Multiple Compound Activities in High Content Imaging
Pati, Pushpak (Janssen R&D LLC), Xu, Zhoubing (Janssen R&D LLC)
Drug DiscoveryTransformerMixture of ExpertsImage
🎯 What it does: The MoMIL framework is proposed, achieving multi-task prediction of multiple experiments in high content imaging (HCI) through mixed multi-instance learning (MIL).
Mono-Modalizing Extremely Heterogeneous Multi-Modal Medical Image Registration
Choo, Kyobin (Yonsei University), Hwang, Seong Jae (Mediwhale)
SegmentationOptimizationBiomedical DataMagnetic Resonance ImagingPositron Emission TomographyAlzheimer's Disease
🎯 What it does: A framework called M2M-Reg is proposed to transform multimodal image registration into unimodal registration, achieving unsupervised and semi-supervised registration through a cyclic structure and gradient cyclic consistency regularization.
More performant and scalable: Rethinking contrastive vision-language pre-training of radiology in the LLM era
Li, Yingtai (University of Science and Technology of China), Zhou, S. Kevin (Hohai University)
ClassificationRetrievalConvolutional Neural NetworkLarge Language ModelSupervised Fine-TuningContrastive LearningImageTextMultimodalityComputed Tomography
🎯 What it does: Utilize large language models to automatically extract diagnostic labels from radiology reports, and use this for supervised pre-training on a large scale dataset, followed by aligning CT images with reports using CLIP.
MorphoBoost: Morphology-Driven Boundary Enhancement Model for Accurate Segmentation of Langerhans Cells in Corneal Confocal Microscopy Images
Li, Hongshuo (Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences), Zhao, Yitian (Ningbo Institute of Materials Technology and Engineering)
SegmentationConvolutional Neural NetworkImage
🎯 What it does: Designed and implemented the Morphoboost framework, which utilizes morphology-driven data augmentation, dilation-guided localization, and boundary optimization loss to achieve precise segmentation of Langerhans cells in corneal confocal microscopy images.
MOSCARD - Multimodal Opportunistic Screening for Cardiovascular Adverse events with Causal Reasoning and De-confounding
Pi, Jialu (Arizona State University), Banerjee, Imon (Arizona State University)
ClassificationAnomaly DetectionTransformerContrastive LearningMultimodalityBiomedical DataElectronic Health RecordsElectrocardiogram
🎯 What it does: This paper proposes MOSCARD, a multimodal causal inference model that combines chest X-rays and 12-lead ECGs for opportunistic screening of future MACE risk, enhancing prediction fairness and generalization through debiasing and causal intervention.
MoST-IG: Morphology-Guided Spatial Transcriptomics Integration via Visual-Genomic Graph Optimal Transport
Yu, Liting (University of Hong Kong), Yu, Lequan (University of Hong Kong)
ClassificationSegmentationOptimizationGraph Neural NetworkContrastive LearningMultimodalityBiomedical Data
🎯 What it does: A multi-modal framework MoST-IG is proposed, which achieves high-quality fusion across multiple slices by utilizing organizational morphology information and spatial transcriptomics data.
MOST: MR reconstruction Optimization for multiple downStream Tasks via continual learning
Jeong, Hwihun (Seoul National University), Lee, Jongho (Seoul National University)
RestorationSegmentationOptimizationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance ImagingAlzheimer's Disease
🎯 What it does: This study investigates a framework named MOST, which implements sequential fine-tuning of a single MR reconstruction network across multiple downstream tasks, avoiding catastrophic forgetting.
Motion-Boundary-Driven Unsupervised Surgical Instrument Segmentation in Low-Quality Optical Flow
Liu, Yang (King's College London), Ourselin, Sebastien (King's College London)
Object DetectionSegmentationOptical FlowVideoBiomedical Data
🎯 What it does: A completely unsupervised surgical instrument segmentation method is proposed, utilizing motion boundaries to guide and improve optical flow quality;
MOTOR: Multimodal Optimal Transport via Grounded Retrieval in Medical Visual Question Answering
Shaaban, Mai A. (Mohamed bin Zayed University of Artificial Intelligence), Yaqub, Mohammad (Mohamed bin Zayed University of Artificial Intelligence)
RetrievalOptimizationVision Language ModelImageTextMultimodalityBiomedical DataElectronic Health RecordsRetrieval-Augmented Generation
🎯 What it does: The MOTOR method is proposed, which combines multimodal optimal transport (OT) with image-based and text-based retrieval for re-ranking, thereby improving the accuracy of answers in medical visual question answering (MedVQA).
MReg: A Novel Regression Model with MoE-based Video Feature Mining for Mitral Regurgitation Diagnosis
Liu, Zhe (Shenzhen University), Yang, Xin (Shenzhen University)
ClassificationAnomaly DetectionMixture of ExpertsVideoBiomedical DataUltrasound
🎯 What it does: An automatic mitral regurgitation diagnosis model MReg based on four-chamber color Doppler ultrasound video has been developed, achieving graded regression prediction for normal, mild, and moderate to severe regurgitation.
MRI Motion Artifact Correction via Frequency-Assisted Artifact Disentanglement and Confidence-Guided Knowledge Distillation
Wang, Jiazhen (Xi'an Jiaotong University), Sun, Jian (Xi'an Jiaotong University)
RestorationKnowledge DistillationGenerative Adversarial NetworkBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A frequency decomposition-based motion artifact separation and confidence-guided knowledge distillation framework for MRI motion artifact correction (FDMC-Net) is proposed, achieving decoupling and reconstruction of content and artifacts through a bidirectional generative network.
MrTrack: Register Mamba for Needle Tracking with Rapid Reciprocating Motion during Ultrasound-Guided Aspiration Biopsy
Zhang, Yuelin (Chinese University of Hong Kong), Cheng, Shing Shin (Chinese University of Hong Kong)
Object TrackingRobotic IntelligenceTransformerVideoBiomedical DataUltrasound
🎯 What it does: A needle tip tracking method called MrTrack is proposed for rapid reciprocating motion in ultrasound-guided fine needle biopsy.
MS-IQA: A Multi-Scale Feature Fusion Network for PET/CT Image Quality Assessment
Li, Siqiao, Li, Xiang (Nanyang Technological University)
TransformerImageComputed TomographyPositron Emission Tomography
🎯 What it does: A multi-scale feature fusion network MS-IQA is proposed for no-reference quality assessment of PET/CT images.
MSDG-StyleNet: Multi-source Unsupervised Domain-Generalized CBCT-to-CT Translation with Style-Consistent Disentangled Representations
Long, Xin (Nanchang University), Gan, Fan
Image TranslationDomain AdaptationGenerative Adversarial NetworkImageBiomedical DataComputed Tomography
🎯 What it does: A CBCT-to-CT translation framework based on multi-source unsupervised domain generalization is proposed, utilizing learnable domain style prototypes and decoupled representations to achieve unpaired image translation across institutions.
MSGFlowNet: Learning Effective Connectivity Network based on Sparse Generative Flow Network from fMRI and EEG Data
Su, Zhihao (Beijing University of Technology), Liu, Jinduo (Beijing University of Technology)
TransformerFlow-based ModelMultimodalityBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Proposes MSGFlowNet, which integrates fMRI and EEG data through an attention-guided encoder, utilizes a sparse Transformer to extract features, and then employs a generative flow network to learn the effective connectivity network of the brain.
MSWAL: 3D Multi-class Segmentation of Whole Abdominal Lesions Dataset
Wu, Zhaodong (Xi'an Jiaotong-Liverpool University), Su, Jionglong (Xi'an Jiaotong-Liverpool University)
SegmentationConvolutional Neural NetworkImageBiomedical DataComputed Tomography
🎯 What it does: The first 3D multi-class segmentation dataset for seven types of lesions in the whole abdomen, MSWAL, is proposed, and based on this dataset, an Inception nnU-Net that integrates the Inception module is designed to achieve fine segmentation of gallstones, kidney stones, liver tumors, kidney tumors, pancreatic cancer, liver cysts, and kidney cysts in abdominal CT images.
MT-WilmsNet: A Multi-Level Transformer Fusion Network for Wilms’ Tumor Segmentation and Metastasis Prediction
Zhu, Zhu (Zhejiang University), Yu, Gang (Zhejiang University)
ClassificationSegmentationKnowledge DistillationTransformerImageBiomedical DataComputed Tomography
🎯 What it does: This paper proposes MT-WilmsNet, a multi-level Transformer fusion network that combines global slice attention, wide reinforced Transformer feature pyramid, and UNet-like segmentation for the segmentation and metastasis prediction of Wilms' tumors.
MTCNet: Motion and Topology Consistency Guided Learning for Mitral Valve Segmentation in 4D Ultrasound
Chen, Rusi (Shenzhen University), Ni, Dong (People's Hospital of Guangxi Zhuang Autonomous Region)
SegmentationConvolutional Neural NetworkSupervised Fine-TuningImageBiomedical DataUltrasound
🎯 What it does: A semi-supervised learning framework MTCNet is proposed, based on motion and topological consistency guidance, for precise segmentation of the mitral valve in 4D ultrasound cardiac images.
Multi-Agent Collaboration for Integrating Echocardiography Expertise in Multi-Modal Large Language Models
Qin, Yi (Hong Kong University of Science and Technology), Li, Xiaomeng (Southern Medical University)
TransformerLarge Language ModelAgentic AIPrompt EngineeringImageTextMultimodalityUltrasound
🎯 What it does: A comprehensive academic knowledge base for echocardiography (ECED) has been constructed, containing over 100 types of heart diseases, charts, texts, and other multimodal information. Efficient knowledge extraction is achieved through the multi-agent collaborative MMLLM tool (MACEE). Furthermore, a lightweight expert-enhanced visual instruction tuning framework (EEVIT) is proposed, which injects ECED knowledge into pre-trained multimodal large language models via the Expert-Lens adapter.
Multi-Agent Reasoning for Cardiovascular Imaging Phenotype Analysis
Zhang, Weitong (Imperial College London), Kainz, Bernhard (Imperial College London)
ClassificationTransformerLarge Language ModelAgentic AIBiomedical DataMagnetic Resonance ImagingRetrieval-Augmented Generation
🎯 What it does: This study investigates a multi-agent language model framework called MESHAgents, designed to automatically discover associations between cardiovascular imaging phenotypes and multimodal factors, and to apply these findings in disease diagnosis.
Multi-expert collaboration and knowledge enhancement network for multimodal emotion recognition
Wang, Kun (Nanjing University of Aeronautics and Astronautics), Zhang, Daoqiang (Nanjing University of Aeronautics and Astronautics)
RecognitionTransformerMultimodalityBiomedical Data
🎯 What it does: This paper proposes a multi-expert collaboration and knowledge-enhanced network for fusing EEG and facial expressions for multimodal emotion recognition.
Multi-Level Gated U-Net for Denoising TMR Sensor-Based MCG Signals
Xing, Zeyu (Zhejiang University), Jiang, Tianzi (University of Chinese Academy of Sciences)
RestorationConvolutional Neural NetworkTime SeriesBiomedical Data
🎯 What it does: A multi-layer gated U-Net (MGU-Net) model is proposed and implemented to denoise magnetocardiogram (MCG) signals collected using tunnel magnetoresistance (TMR) sensors.
Multi-Linear 3D Craniofacial Infant Shape Model
Schnabel, Till N. (ETH Zurich), Solenthaler, Barbara (ETH Zurich)
Auto EncoderImagePoint CloudMeshComputed Tomography
🎯 What it does: This paper constructs the first integrated 3D multilinear shape model of an infant's head, incorporating soft tissue, jawbone, and complete skull, called INCRAN.
Multi-Masked Querying Network for Robust Emotion Recognition from Incomplete Multi-Modal Physiological Signals
Xu, Geng-Xin (Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences), Li, Ye (Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences)
RecognitionTransformerMultimodality
🎯 What it does: This paper proposes a Multi-Mask Query Network (MMQ-Net) for robust emotion recognition in the presence of missing and interfering multimodal physiological signals.