MICCAI 2024 Papers — Page 4
International Conference on Medical Image Computing and Computer-Assisted Intervention · 856 papers
Explainable vertebral fracture analysis with uncertainty estimation using differentiable rule-based classification
Wåhlstrand Skärström, Victor (Chalmers University of Technology), Häggström, Ida (Chalmers University of Technology)
ClassificationExplainability and InterpretabilityConvolutional Neural NetworkFlow-based ModelImageBiomedical Data
🎯 What it does: An end-to-end interpretable spinal compression fracture assessment system (XVFA) is proposed, which first locates the vertebrae and predicts the positions of key points, and then uses a differentiable Genant semi-quantitative rule for fracture level and morphology classification, providing uncertainty estimates.
Explanation-driven Cyclic Learning for High-Quality Brain MRI Reconstruction from Unknown Degradation
Jiang, Ning (Peking University), Sui, Yao (Peking University)
RestorationExplainability and InterpretabilityTransformerImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes a framework based on explanation-driven cyclic learning that can recover high-quality images from brain MRI scans containing various unknown degradation sources;
Exploiting Latent Classes for Medical Image Segmentation from Partially Labeled Datasets
Zhao, Xiangyu (Shanghai United Imaging Intelligence Co., Ltd.), Shen, Dinggang (Shanghai United Imaging Intelligence Co., Ltd.)
SegmentationKnowledge DistillationConvolutional Neural NetworkBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Proposes to enhance medical image segmentation using unlabeled potential categories of ROI.
Exploiting Supervision Information in Weakly Paired Images for IHC Virtual Staining
Li, Yueheng (Harbin Institute of Technology (Shenzhen)), Zhang, Yongbing (Harbin Institute of Technology Shenzhen)
Image TranslationGenerationGenerative Adversarial NetworkContrastive LearningImageBiomedical Data
🎯 What it does: This paper proposes a weakly supervised IHC virtual staining method that utilizes pathological information from consecutive tissue sections to achieve image conversion from H&E to IHC.
Exploring Spatio-Temporal Interpretable Dynamic Brain Function with Transformer for Brain Disorder Diagnosis
Li, Lanting (Northeastern University), Zaiane, Osmar R. (Amii)
ClassificationExplainability and InterpretabilityTransformerTime SeriesBiomedical DataMagnetic Resonance Imaging
🎯 What it does: An end-to-end Transformer framework called BISTformer is proposed for spatiotemporal clustering of brain functional modules and diagnosing brain diseases.
F2TNet: FMRI to T1w MRI Knowledge Transfer Network for Brain Multi-phenotype Prediction
He, Zhibin (Northwestern Polytechnical University), Yuan, Yixuan (Southern University of Science and Technology)
Graph Neural NetworkTransformerContrastive LearningBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Proposes F2TNet, which infers using low-cost T1w MRI by transferring fMRI knowledge to T1w MRI and simultaneously predicting multiple phenotypes.
FACMIC: Federated Adaptative CLIP Model for Medical Image Classification
Wu, Yihang, Chaddad, Ahmad
ClassificationDomain AdaptationContrastive LearningImage
🎯 What it does: A domain adaptation framework based on contrastive learning is proposed, utilizing feature alignment between the source domain and the target domain to enhance cross-domain image classification performance.
Fair and Accurate Skin Disease Image Classification by Alignment with Clinical Labels
Aayushman (Indian Institute of Science Education and Research), Gupta, Gagan Raj (Indian Institute of Technology)
ClassificationTransformerSupervised Fine-TuningImageText
🎯 What it does: Proposes PatchAlign, which aligns skin image patches with clinical text labels through Masked Graph Optimal Transport to enhance the accuracy and fairness of skin disease classification.
FairDiff: Fair Segmentation with Point-Image Diffusion
Li, Wenyi (Tsinghua University), Zhao, Hao (Harvard University)
SegmentationData SynthesisDiffusion modelImagePoint CloudBiomedical Data
🎯 What it does: Generate synthetic SLO retinal images that conform to boundary constraints through Point-Image Diffusion, and combine the synthetic data with real data in an Equal-Scale manner for training a fair segmentation model.
FairQuantize: Achieving Fairness Through Weight Quantization for Dermatological Disease Diagnosis
Guo, Yuanbo (University of Notre Dame), Shi, Yiyu (University of Notre Dame)
ClassificationCompressionConvolutional Neural NetworkImage
🎯 What it does: By quantizing the weights of deep models based on power binary, using fairness scores derived from Hessian, selectively quantizing certain weights to enhance diagnostic fairness among different populations while maintaining overall accuracy.
FALFormer: Feature-aware Landmarks self-attention for Whole-slide Image Classification
Bui, Doanh C. (Korea University), Kwak, Jin Tae (Korea University)
ClassificationTransformerImage
🎯 What it does: A Transformer-based FALFormer model is proposed, utilizing Feature-Aware Landmarks Self-Attention (FALSA) for efficient classification on complete WSI.
FastSAM3D: An Efficient Segment Anything Model for 3D Volumetric Medical Images
Shen, Yiqing (Johns Hopkins University), Unberath, Mathias (University of Arkansas)
SegmentationComputational EfficiencyKnowledge DistillationTransformerVision Language ModelBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: Introducing FastSAM3D, an efficient Segment Anything model specifically designed for 3D medical imaging, supporting fast interactive voxel-level segmentation;
FD-SOS: Vision-Language Open-Set Detectors for Bone Fenestration and Dehiscence Detection from Intraoral Images
Elbatel, Marawan, Li, Xiaomeng (Southern Medical University)
Object DetectionTransformerVision Language ModelContrastive LearningImageMultimodalityBiomedical DataComputed Tomography
🎯 What it does: A framework for detecting bone window defects (FD) based on open set detection, called FD-SOS, is proposed, which can achieve automatic diagnosis of bone window defects and absence solely from intraoral views.
Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend
Woodland, McKell (University of Texas MD Anderson Cancer Center), Brock, Kristy K. (University of Texas MD Anderson Cancer Center)
GenerationData SynthesisGenerative Adversarial NetworkImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: This study evaluates and compares the consistency of feature extractors trained on ImageNet and RadImageNet in the assessment of medical image generation models (StyleGAN2), and verifies the effectiveness of augmentation techniques such as DiffAugment.
Feature Fusion Based on Mutual-Cross-Attention Mechanism for EEG Emotion Recognition
Zhao, Yimin (Southwest Jiaotong University), Gu, Jin (Southwest Jiaotong University)
ClassificationRecognitionConvolutional Neural NetworkTime SeriesBiomedical Data
🎯 What it does: This paper proposes a feature fusion method based on the Mutual Cross Attention mechanism (MCA), combined with a custom 3D-CNN, to classify emotions using DE and PSD features from EEG.
Feature Selection Gates with Gradient Routing for Endoscopic Image Computing
Roffo, Giorgio (Cosmo Intelligent Medical Devices), Cherubini, Andrea (Cosmo Intelligent Medical Devices)
ClassificationOptimizationConvolutional Neural NetworkTransformerImage
🎯 What it does: Proposed Feature Selection Gates and Gradient Routing to improve the colon polyp size estimation model.
Feature-prompting GBMSeg: One-Shot Reference Guided Training-Free Prompt Engineering for Glomerular Basement Membrane Segmentation
Liu, Xueyu (Taiyuan University of Technology), Zheng, Wen (Taiyuan University of Technology)
SegmentationTransformerPrompt EngineeringImage
🎯 What it does: A training-free GBM segmentation framework called GBMSeg is proposed, which can achieve automatic segmentation of the glomerular basement membrane using a single annotated reference TEM image.
Federated Multi-Centric Image Segmentation with Uneven Label Distribution
Galati, Francesco (EURECOM), Zuluaga, Maria A. (EURECOM)
SegmentationDomain AdaptationFederated LearningGenerative Adversarial NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: In the task of medical image segmentation with multiple centers, uneven distribution, and lack of labels, a federated learning framework is proposed. It first constructs a multimodal data factory through federated training to generate a shared decoupled latent space; subsequently, asynchronous domain adaptation is performed on unlabeled clients to achieve segmentation without data sharing across centers.
FedEvi: Improving Federated Medical Image Segmentation via Evidential Weight Aggregation
Chen, Jiayi (Northwestern Polytechnical University), Xia, Yong (Northwestern Polytechnical University)
SegmentationFederated LearningConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes FedEvi, an evidence-based federated learning method that dynamically adjusts aggregation weights using global generalization gaps and local reliability to enhance the generalization performance of multi-center medical image segmentation.
FedFMS: Exploring Federated Foundation Models for Medical Image Segmentation
Liu, Yuxi (Peking University), Zhu, Yuesheng (Peking University)
SegmentationFederated LearningSafty and PrivacyTransformerImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Proposes the FedFMS framework, introducing SAM and its efficient variant MSA into federated learning for multi-center medical image segmentation, and conducts experimental validation on four types of non-IID datasets.
FedIA: Federated Medical Image Segmentation with Heterogeneous Annotation Completeness
Xiang, Yangyang (Huazhong University of Science and Technology), Yan, Zengqiang (Huazhong University of Science and Technology)
SegmentationFederated LearningConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: A federated learning framework named FedIA is proposed to address the issue of uneven labeling completeness among different clients in medical image segmentation.
FedMedICL: Towards Holistic Evaluation of Distribution Shifts in Federated Medical Imaging
Alhamoud, Kumail (Massachusetts Institute of Technology), Ghassemi, Marzyeh (King Abdullah University of Science and Technology)
Federated LearningConvolutional Neural NetworkImageMultimodalityBiomedical DataBenchmark
🎯 What it does: Proposes the FedMedICL framework and benchmark for simultaneously evaluating label, demographic, and temporal distribution shifts in federated medical imaging, and simulates disease spread through continual learning.
FedMLP: Federated Multi-Label Medical Image Classification under Task Heterogeneity
Sun, Zhaobin (Huazhong University of Science and Technology), Yan, Zengqiang (Huazhong University of Science and Technology)
ClassificationFederated LearningImageBiomedical Data
🎯 What it does: The study proposes the FedMLP model to address task heterogeneity in multi-label medical image classification, solving the problem of missing labels.
FedMRL: Data Heterogeneity Aware Federated Multi-agent Deep Reinforcement Learning for Medical Imaging
Sahoo, Pranab (Indian Institute of Technology Patna), Mondal, Samrat (Indian Institute of Technology Patna)
Federated LearningConvolutional Neural NetworkReinforcement LearningImageBiomedical Data
🎯 What it does: In the framework of federated learning, FedMRL is proposed to address the issue of data heterogeneity in medical imaging.
Fetal MRI Reconstruction by Global Diffusion and Consistent Implicit Representation
Tan, Junpeng (South China University of Technology), Xu, Xiangmin (Southern Medical University)
RestorationDiffusion modelImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A self-supervised fetal brain MRI volume reconstruction method called RDGM is proposed, which uses multi-stacked slices to recover high-quality three-dimensional images.
Few Slices Suffice: Multi-Faceted Consistency Learning with Active Cross-Annotation for Barely-supervised 3D Medical Image Segmentation
Wu, Xinyao (Chinese University of Hong Kong), Tong, Raymond Kai-yu (Chinese University of Hong Kong)
SegmentationKnowledge DistillationImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A framework called MF-ConS based on multi-surface consistency learning is proposed, achieving high-quality medical image segmentation under the condition of sparse annotations for only three orthogonal slices of each 3D scan.
Few-Shot 3D Volumetric Segmentation with Multi-Surrogate Fusion
Zheng, Meng (United Imaging Intelligence), Wu, Ziyan (United Imaging Intelligence)
SegmentationConvolutional Neural NetworkTransformerImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: This paper proposes a lightweight multi-support few-shot 3D medical image segmentation framework called MSFSeg, which can achieve automatic segmentation of unseen 3D targets using only a small number of labeled 2D slices or 3D sequences.
Few-shot Adaptation of Medical Vision-Language Models
Shakeri, Fereshteh (TS Montreal), Ben Ayed, Ismail (ÉTS Montréal)
Domain AdaptationRepresentation LearningTransformerVision Language ModelContrastive LearningMultimodalityBiomedical DataBenchmark
🎯 What it does: Evaluate the adaptation of medical visual language models with a small number of samples, establish benchmarks, and compare various adaptation strategies.
Few-Shot Domain Adaptive Object Detection for Microscopic Images
Inayat, Sumayya (Information Technology University), Ali, Mohsen (Information Technology University)
Object DetectionDomain AdaptationImage
🎯 What it does: This study proposes a few-shot domain adaptive object detection method for microscope images.
Few-Shot Lymph Node Metastasis Classification Meets High Performance on Whole Slide Images via the Informative Non-Parametric Classifier
Li, Yi (Hong Kong University of Science and Technology), Li, Xiaomeng (Southern Medical University)
ClassificationTransformerSupervised Fine-TuningImage
🎯 What it does: An information-based non-parametric classifier (INC) is proposed, which maintains local patch features on a small number of labeled WSIs and uses mask labels for non-parametric similarity matching to achieve few-shot classification of lymph node metastasis.
Fine-grained Context and Multi-modal Alignment for Freehand 3D Ultrasound Reconstruction
Yan, Zhongnuo (Shenzhen University), Ni, Dong (People's Hospital of Guangxi Zhuang Autonomous Region)
Pose EstimationConvolutional Neural NetworkOptical FlowImageMultimodalityUltrasound
🎯 What it does: This study proposes a full-hand 3D ultrasound reconstruction framework named FiMA, which combines three major modules: ReMamba, adaptive multimodal fusion, and online alignment, to achieve high-precision spatial pose estimation of ultrasound sequences.
Fine-grained Prompt Tuning: A Parameter and Memory Efficient Transfer Learning Method for High-resolution Medical Image Classification
Huang, Yijin (Southern University of Science and Technology), Tang, Xiaoying (Chinese University of Hong Kong)
ClassificationTransformerPrompt EngineeringImageBiomedical Data
🎯 What it does: This paper proposes a Fine-grained Prompt Tuning (FPT) framework for achieving parameter and memory-efficient transfer learning in high-resolution medical image classification tasks.
FissionFusion: Fast Geometric Generation and Hierarchical Souping for Medical Image Analysis
Sanjeev, Santosh (Mohamed bin Zayed University of Artificial Intelligence), Yaqub, Mohammad (Mohamed bin Zayed University of Artificial Intelligence)
ClassificationSegmentationOptimizationConvolutional Neural NetworkTransformerSupervised Fine-TuningImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes two methods, FGG and HS, to efficiently generate and fuse models in medical imaging tasks, thereby enhancing model performance.
FM-ABS: Promptable Foundation Model Drives Active Barely Supervised Learning for 3D Medical Image Segmentation
Xu, Zhe (Chinese University of Hong Kong), Tong, Raymond Kai-yu (Chinese University of Hong Kong)
SegmentationPrompt EngineeringImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: By combining a pre-trained general segmentation model with active few-shot labeling, the FM-ABS learning framework is proposed, which allows for training a dedicated segmentation model with only three labeled slices in 3D medical image segmentation.
FM-OSD: Foundation Model-Enabled One-Shot Detection of Anatomical Landmarks
Miao, Juzheng (Chinese University of Hong Kong), Heng, Pheng-Ann (Chinese University of Hong Kong)
RecognitionObject DetectionConvolutional Neural NetworkContrastive LearningImageComputed Tomography
🎯 What it does: This paper proposes a framework FM-OSD for single image one-shot anatomical landmark point detection using a visual foundation model, which can achieve high-precision landmark localization with just one template image.
Follow Sonographers’ Visual Scan-path: Adjusting CNN Model for Diagnosing Gout from Musculoskeletal Ultrasound
Tang, Xin (Nanjing University of Aeronautics and Astronautics), Chen, Fang (Tsinghua University)
ClassificationConvolutional Neural NetworkSupervised Fine-TuningImageUltrasound
🎯 What it does: This paper proposes a scanning path-based fine-tuning mechanism (SFT) that enhances the feature attention and classification performance of CNNs in gout diagnosis by learning the eye movement scanning trajectories of ultrasound doctors.
Follow the Radiologist: Clinically Relevant Multi-View Cues for Breast Cancer Detection from Mammograms
Jain, Kshitiz (Indian Institute of Technology Delhi), Arora, Chetan (PGIMER Chandigarh)
Object DetectionConvolutional Neural NetworkContrastive LearningImageBiomedical Data
🎯 What it does: A tumor detection framework based on multi-view mammograms is proposed, focusing on the morphological similarity of ROIs rather than geometric alignment;
Force Sensing Guided Artery-Vein Segmentation via Sequential Ultrasound Images
Geng, Yimeng (Chinese Academy of Sciences), Liu, Hongbin (Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science Innovation, Chinese Academy of Sciences)
SegmentationConvolutional Neural NetworkImageBiomedical DataUltrasound
🎯 What it does: This paper proposes a force-aware continuous ultrasound image vascular segmentation framework, which utilizes compression force information to select key frames and integrates them into the segmentation network through an attention mechanism to achieve artery and vein segmentation.
Forecasting Disease Progression with Parallel Hyperplanes in Longitudinal Retinal OCT
Chakravarty, Arunava (Medical University of Vienna), Bogunović, Hrvoje (Medical University of Vienna)
ClassificationDomain AdaptationConvolutional Neural NetworkSupervised Fine-TuningImageBiomedical DataAlzheimer's Disease
🎯 What it does: This paper proposes a deep learning model based on Parallel Hyperplanes for predicting the risk of developing dry age-related macular degeneration (dAMD) and the cumulative distribution function (CDF) over continuous time from retinal OCT scans; it also utilizes unlabeled longitudinal image pairs for unsupervised fine-tuning to adapt to domain shifts from different scanners.
FRCNet: Frequency and Region Consistency for Semi-supervised Medical Image Segmentation
He, Along (Nankai University), Fu, Huazhu (Agency for Science, Technology and Research (A*STAR))
SegmentationTransformerImageBiomedical Data
🎯 What it does: Proposes FRCNet, which enhances semi-supervised medical image segmentation performance using frequency domain consistency and multi-scale region similarity.
Free-SurGS: SfM-Free 3D Gaussian Splatting for Surgical Scene Reconstruction
Guo, Jiaxin (Chinese University of Hong Kong), Liu, Yun-hui (Hong Kong Center for Logistics Robotics)
Depth EstimationOptimizationGaussian SplattingSimultaneous Localization and MappingOptical FlowVideo
🎯 What it does: This paper proposes Free‑SurGS, the first SfM-free 3D Gaussian Splatting method, which enables rapid reconstruction and real-time rendering of surgical scenes using monocular endoscopic video.
From Pixel to Cancer: Cellular Automata in Computed Tomography
Lai, Yuxiang (John Hopkins University), Zhou, Zongwei (University of California, San Francisco)
SegmentationGenerationData SynthesisConvolutional Neural NetworkImageBiomedical DataComputed Tomography
🎯 What it does: This paper proposes the Pixel2Cancer method, which generates multi-stage, cross-organ synthetic tumors in computed tomography images based on three general rules of cellular automata (growth, invasion, death) without the need for manual annotation.
From Static to Dynamic Diagnostics: Boosting Medical Image Analysis via Motion-Informed Generative Videos
Li, Wuyang (Chinese University of Hong Kong), Yuan, Yixuan (Southern University of Science and Technology)
ClassificationGenerationData SynthesisKnowledge DistillationDiffusion modelImageVideoBiomedical Data
🎯 What it does: Utilizing video generation models to convert static medical images into medical videos with motion information, and jointly using image and video features in model training to enhance the performance of semi-supervised medical image classification.
fTSPL: Enhancing Brain Analysis with fMRI-Text Synergistic Prompt Learning
Wang, Pengyu (Chinese University of Hong Kong), Yuan, Yixuan (Southern University of Science and Technology)
ClassificationGraph Neural NetworkPrompt EngineeringVision Language ModelContrastive LearningMultimodalityBiomedical DataMagnetic Resonance ImagingAlzheimer's Disease
🎯 What it does: A framework for fMRI-Text Synergistic Prompt Learning (fTSPL) is proposed, which utilizes a pre-trained Vision-Language model to automatically generate instance-level text and construct multimodal functional connectivity graphs, thereby enhancing brain function analysis based on graph neural networks.
FUNAvg: Federated Uncertainty Weighted Averaging for Datasets with Diverse Labels
Tölle, Malte, Engelhardt, Sandy (Heidelberg University Hospital)
SegmentationFederated LearningImageBiomedical DataComputed Tomography
🎯 What it does: Train a shared backbone network under the federated learning framework, and learn a segmentation head separately for each client. After estimating uncertainty using MC Dropout, obtain the global segmentation result through uncertainty-weighted averaging.
Fundus2Video: Cross-Modal Angiography Video Generation from Static Fundus Photography with Clinical Knowledge Guidance
Zhang, Weiyi (Hong Kong Polytechnic University), He, Mingguang (Hong Kong Polytechnic University)
GenerationData SynthesisGenerative Adversarial NetworkImageVideo
🎯 What it does: A model based on autoregressive GAN (Fundus2Video) is proposed, capable of synthesizing dynamic fluorescein angiography (FFA) videos from a single color fundus photograph (CF).
Fuzzy Attention-based Border Rendering Network for Lung Organ Segmentation
Zhang, Sheng (Imperial College London), Yang, Guang (Sun Yat-sen University)
SegmentationTransformerImageBiomedical DataComputed Tomography
🎯 What it does: Designed and implemented a Transformer-like U-Net based on fuzzy attention and a global-local octree fusion module for lung organ CT image segmentation.
Gait Patterns as Biomarkers: A Video-Based Approach for Classifying Scoliosis
Zhou, Zirui (Southern University of Science and Technology), Yu, Shiqi (Southern University of Science and Technology)
ClassificationRecognitionConvolutional Neural NetworkVideoBenchmark
🎯 What it does: This paper constructs two deep models, ScoNet and ScoNet-MT, based on gait features in videos to classify adolescent scoliosis (scoliosis) and publicly releases a large-scale video dataset, Scoliosis1K, for the first time.
Gaussian Pancakes: Geometrically-Regularized 3D Gaussian Splatting for Realistic Endoscopic Reconstruction
Bonilla, Sierra (Wellcome/EPSRC Centre for Interventional and Surgical Sciences), Bano, Sophia (Wellcome/EPSRC Centre for Interventional and Surgical Sciences)
RestorationGenerationDepth EstimationRecurrent Neural NetworkGaussian SplattingSimultaneous Localization and MappingVideo
🎯 What it does: The paper introduces 'Gaussian Pancakes', which combines 3D Gaussian Splatting with an RNN-based SLAM system to achieve real-time and accurate 3D reconstruction and view synthesis in endoscopic videos.
Gaze-DETR: Using Expert Gaze to Reduce False Positives in Vulvovaginal Candidiasis Screening
Kong, Yan (Nanjing University), Wang, Qian (United Imaging Intelligence)
Object DetectionTransformerImage
🎯 What it does: This paper proposes a detection method using expert eye movement data to reduce false positives in vaginal candidiasis screening—Gaze-DETR;
Gaze-directed Vision GNN for Mitigating Shortcut Learning in Medical Image
Wu, Shaoxuan (Northwest University), Feng, Jun (Northwest University)
ClassificationConvolutional Neural NetworkGraph Neural NetworkImageBiomedical Data
🎯 What it does: This paper proposes a Vision GNN (GD-ViG) based on retinal eye movements, which guides the network to focus on lesion areas by generating pupil maps, thereby reducing shortcut learning in medical imaging.
GBT: Geometric-oriented Brain Transformer for Autism Diagnosis
Peng, Zhihao (Chinese University of Hong Kong), Yuan, Yixuan (Southern University of Science and Technology)
ClassificationGraph Neural NetworkTransformerBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes a Transformer-based brain network model GBT for autism diagnosis.
GCAN: Generative Counterfactual Attention-guided Network for Explainable Cognitive Decline Diagnostics based on fMRI Functional Connectivity
Shen, Xiongri (Harbin Institute of Technology (Shenzhen)), Zhang, Zhiguo (Harbin Institute of Technology)
ClassificationExplainability and InterpretabilityTransformerGenerative Adversarial NetworkBiomedical DataMagnetic Resonance ImagingAlzheimer's Disease
🎯 What it does: A Generative Adversarial Causal Attention Network (GCAN) is proposed to explain and enhance the diagnosis of mild cognitive impairment and subjective cognitive decline based on fMRI functional connectivity.
GEM: Context-Aware Gaze EstiMation with Visual Search Behavior Matching for Chest Radiograph
Liu, Shaonan, Shen, Linlin (Shenzhen University)
RecognitionPose EstimationGraph Neural NetworkTransformerContrastive LearningImageTextMultimodalityComputed Tomography
🎯 What it does: This paper proposes the GEM network, which implements context-based gaze estimation for medical images by utilizing fine-grained alignment between images and reports, as well as visual behavior graph matching, to predict the gaze points of radiologists on chest X-rays.
Generalized Robust Fundus Photography-based Vision Loss Estimation for High Myopia
Yan, Zipei, Liang, Dong (Chinese Academy of Sciences)
ClassificationDomain AdaptationAnomaly DetectionConvolutional Neural NetworkSupervised Fine-TuningImageBiomedical Data
🎯 What it does: A parameter-efficient RED framework is designed to estimate visual field loss in high myopia patients using fundus photographs.
Generalizing to Unseen Domains in Diabetic Retinopathy with Disentangled Representations
Xia, Peng (Monash University), Ge, Zongyuan (Melbourne University)
ClassificationDomain AdaptationConvolutional Neural NetworkContrastive LearningImage
🎯 What it does: This paper proposes the DECO framework, which achieves feature-level cross-domain data augmentation by decoupling retinal image features into DR-related semantic features and domain noise, and trains a DR grading model with better domain generalization capabilities based on this.
Generating Anatomically Accurate Heart Structures via Neural Implicit Fields
Yang, Jiancheng (Swiss Federal Institute of Technology Lausanne), Fua, Pascal (Stony Brook University)
SegmentationGenerationData-Centric LearningNeural Radiance FieldImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: ImHeart is designed, a neural implicit field model that utilizes learnable templates and a unified deformation field for accurate reconstruction of multi-structural cardiac geometry, and enhances cross-center MRI segmentation performance through data centering retraining.
Generating Progressive Images from Pathological Transitions via Diffusion Model
Liu, Zeyu (Beihang University), Zhang, Guanglei (Beihang University)
GenerationData SynthesisDiffusion modelImageBiomedical Data
🎯 What it does: An Adaptive Deep Control Diffusion Network (ADD) is proposed, capable of generating progressive samples of pathological images under very few sample conditions, for data augmentation and improving downstream classification performance.
Genomics-guided Representation Learning for Pathologic Pan-cancer Tumor Microenvironment Subtype Prediction
Meng, Fangliangzi (Tongji University), Liu, Qi (Tongji University)
Domain AdaptationRepresentation LearningContrastive LearningImageBiomedical Data
🎯 What it does: A gene-guided Siamese representation learning framework called PathoTME is proposed, which uses panoramic whole slide images (WSI) of all cancer types to predict tumor microenvironment (TME) subtypes;
Geometric Transformation Uncertainty for Improving 3D Fetal Brain Pose Prediction from Freehand 2D Ultrasound Videos
Ramesh, Jayroop (University of Oxford), Namburete, Ana I. L. (University of Oxford)
Pose EstimationConvolutional Neural NetworkSupervised Fine-TuningImageVideoBiomedical DataUltrasound
🎯 What it does: A deep learning model based on multi-head geometric transformations and uncertainty estimation is proposed to predict the 3D fetal brain plane posture in freehand 2D ultrasound images.
Glioblastoma segmentation from early post-operative MRI: challenges and clinical impact
Holden Helland, Ragnhild (SINTEF Digital), Reinertsen, Ingerid (SINTEF Digital)
SegmentationConvolutional Neural NetworkImageMagnetic Resonance Imaging
🎯 What it does: This study investigates an automatic segmentation method for residual glioblastoma in early postoperative magnetic resonance imaging (EPMR), proposing improved sampling strategies and network structures to enhance segmentation and classification performance, and comparing it with manual annotations.
GMM-CoRegNet: A Multimodal Groupwise Registration Framework Based on Gaussian Mixture Model
Li, Zhenyu, Qian, Zhen (United Imaging Intelligence Co Ltd)
Mixture of ExpertsMultimodalityBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A multimodal intra-registration framework GMM-CoRegNet based on weakly supervised Gaussian mixture models is proposed, which constructs GMM using reference image labels and designs a similarity measure to achieve simultaneous registration of any number of modalities.
GMoD: Graph-driven Momentum Distillation Framework with Active Perception of Disease Severity for Radiology Report Generation
Xiang, ZhiPeng, Zhang, Liqiang (Huazhong University Of Science And Technology)
GenerationKnowledge DistillationGraph Neural NetworkTransformerImageTextBiomedical Data
🎯 What it does: This paper proposes a graph-driven momentum distillation framework GMoD, which achieves active perception of disease severity in X-ray images through graph attention and momentum distillation, thereby generating more accurate and semantically consistent radiology reports.
Goal-conditioned reinforcement learning for ultrasound navigation guidance
Amadou, Abdoul Aziz (King's College London), Rhode, Kawal (King's College London)
Pose EstimationConvolutional Neural NetworkReinforcement LearningContrastive LearningImageBiomedical DataComputed TomographyUltrasound
🎯 What it does: A target-conditioned reinforcement learning-based ultrasound guidance model is proposed, capable of training in a simulated environment to enable the probe to achieve localization and pose control under any given target image.
Gradient Guided Co-Retention Feature Pyramid Network for LDCT Image Denoising
Zhou, Li (University of Massachusetts Lowell), Yu, Hengyong (University of Massachusetts Lowell)
RestorationConvolutional Neural NetworkImageComputed Tomography
🎯 What it does: A gradient-guided co-retention feature pyramid network (G2CR-FPN) is proposed for low-dose CT image denoising, which integrates multi-scale features and gradient enhancement to improve noise suppression and detail preservation.
Groupwise Deformable Registration of Diffusion Tensor Cardiovascular Magnetic Resonance: Disentangling Diffusion Contrast, Respiratory and Cardiac Motions
Wang, Fanwen (Imperial College London), Yang, Guang (Sun Yat-sen University)
SegmentationGenerationOptimizationDiffusion modelImageBiomedical DataMagnetic Resonance ImagingDiffusion Tensor Imaging
🎯 What it does: To address the registration challenges of cardiac diffusion tensor CMR images under respiratory and cardiac motion as well as low signal-to-noise ratio conditions, an inter-group deformation registration framework based on implicit templates is proposed. Motion correction and text feature preservation are achieved through tensor embedding to generate pseudo-images and a differentiable mutual information loss.
Gyri vs. Sulci: Core-Periphery Organization in Functional Brain Networks
Yu, Xiaowei (University of Texas at Arlington), Zhu, Dajiang (University of Georgia)
TransformerBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper uses the Twin-Transformer framework to spatially-temporally decouple fMRI data from the HCP task, revealing the functional core-periphery structure of cortical gyri and sulci.
H2ASeg: Hierarchical Adaptive Interaction and Weighting Network for Tumor Segmentation in PET/CT Images
Lu, Jinpeng (Harbin Institute of Technology (Shenzhen)), Zhang, Yongbing (Harbin Institute of Technology Shenzhen)
SegmentationConvolutional Neural NetworkTransformerImageMultimodalityBiomedical DataComputed TomographyPositron Emission Tomography
🎯 What it does: A new hierarchical adaptive interaction and weighting network H2ASeg is proposed for tumor segmentation in PET/CT images.
Hallucinated Style Distillation for Single Domain Generalization in Medical Image Segmentation
Yi, Jingjun (Tencent Jarvis Lab), Huang, Feiyue (Guangxi Medical University)
SegmentationDomain AdaptationKnowledge DistillationTransformerContrastive LearningImageBiomedical Data
🎯 What it does: This paper proposes a single-domain general medical image segmentation framework—Hallucinated Style Distillation (HSD), which learns style-invariant features through style hallucination, representation expansion, and cross-style distillation on a single source domain, thereby enhancing the model's generalization performance on unseen target domains.
Hallucination Index: An Image Quality Metric for Generative Reconstruction Models
Tivnan, Matthew (Massachusetts General Hospital and Harvard Medical School), Li, Quanzheng (Massachusetts General Hospital and Harvard Medical School)
RestorationGenerationDiffusion modelScore-based ModelImageBiomedical Data
🎯 What it does: This paper proposes and validates a new image quality metric—Hallucination Index—to quantify hallucinations in generative medical image reconstruction models, and experiments were conducted on electron microscope images.
HAMIL-QA: Hierarchical Approach to Multiple Instance Learning for Atrial LGE MRI Quality Assessment
Sultan, K. M. Arefeen (University of Utah), Elhabian, Shireen Y. (University of Utah)
ClassificationExplainability and InterpretabilityComputational EfficiencyKnowledge DistillationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A hierarchical multi-instance learning framework named HAMIL-QA has been developed for the automatic assessment of the diagnostic quality of left atrial Late Gadolinium Enhancement (LGE) MRI scans.
Hard Negative Sample Mining for Whole Slide Image Classification
Huang, Wentao (Stony Brook University), Chen, Chao (Harvard Medical School)
ClassificationConvolutional Neural NetworkContrastive LearningImage
🎯 What it does: This paper proposes a framework that combines hard negative sample mining with multi-instance ranking loss to improve the classification of whole slide images (WSI).
Harnessing Temporal Information for Precise Frame-Level Predictions in Endoscopy Videos
Mobadersany, Pooya (Janssen Research and Development, LLC), Standish, Kristopher (Johnson & Johnson Innovative Medicine)
ClassificationTransformerContrastive LearningVideo
🎯 What it does: The study utilizes temporal information to achieve precise frame-level predictions and proposes EndoFormer for anatomical segment classification in colonoscopy videos.
HATs: Hierarchical Adaptive Taxonomy Segmentation for Panoramic Pathology Image Analysis
Deng, Ruining, Huo, Yuankai (Vanderbilt University Medical Center)
SegmentationTransformerBiomedical Data
🎯 What it does: A panoramic kidney tissue segmentation method based on hierarchical adaptive taxonomy, HATs, is proposed, capable of segmenting 15 structures from regional to cellular levels simultaneously.
HDilemma: Are Open-Source Hausdorff Distance Implementations Equivalent?
Podobnik, Gašper, Vrtovec, Tomaž (University of Ljubljana)
SegmentationImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: A systematic evaluation of five open-source Hausdorff distance implementations is conducted, comparing their differences with a grid reference and discussing the impact of implementation differences on the results.
HeartBeat: Towards Controllable Echocardiography Video Synthesis with Multimodal Conditions-Guided Diffusion Models
Zhou, Xinrui (Shenzhen University), Ni, Dong (People's Hospital of Guangxi Zhuang Autonomous Region)
GenerationData SynthesisDiffusion modelOptical FlowVideoMultimodalityBiomedical DataMagnetic Resonance ImagingUltrasound
🎯 What it does: The HeartBeat framework is proposed, which implements controllable cardiac ultrasound (ECHO) video synthesis using a multimodal condition-driven diffusion model.
HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition
Yuan, Kun (University of Strasbourg), Padoy, Nicolas (University of Strasbourg, CNRS, INSERM, ICube, UMR7357)
RecognitionContrastive LearningVideoTextMultimodality
🎯 What it does: This paper proposes HecVL, a model that utilizes hierarchical video-text pairs for video-language pre-training, aimed at zero-shot surgical phase recognition.
Hemodynamic-Driven Multi-Prototypes Learning for One-Shot Segmentation in Breast Cancer DCE-MRI
Pan, Xiang (Hangzhou Dianzi University), Li, Lihua (Jiangnan University)
SegmentationRecurrent Neural NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A multi-prototype network driven by hemodynamics (HDMPNet) is proposed to achieve single-instance segmentation of breast DCE-MRI tumors, capable of handling diverse tumor sizes, shapes, and multi-connected regions.
Heteroscedastic Uncertainty Estimation Framework for Unsupervised Registration
Zhang, Xiaoran (Yale University), Duncan, James S. (Yale University)
Image TranslationSegmentationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes a heteroscedastic uncertainty estimation framework for unsupervised image registration.
HF-ResDiff: High-Frequency-guided Residual Diffusion for Multi-dose PET Reconstruction
Tang, Zixin (ShanghaiTech University), Shen, Dinggang (Shanghai United Imaging Intelligence Co., Ltd.)
RestorationConvolutional Neural NetworkDiffusion modelImagePositron Emission Tomography
🎯 What it does: This paper proposes a high-frequency guided residual diffusion model HF-ResDiff for multi-dose PET image reconstruction.
HiA: Towards Chinese Multimodal LLMs for Comparative High-Resolution Joint Diagnosis
Ding, Xinpeng (Hong Kong University of Science and Technology), Li, Xiaomeng (Southern Medical University)
RecognitionSegmentationData-Centric LearningTransformerLarge Language ModelSupervised Fine-TuningVision Language ModelMultimodalityBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: This paper proposes a high-resolution instruction-aware adapter HiA and a local Chinese medical multimodal dataset Chili-Joint, addressing the limitations of existing Chinese medical MLLMs in terms of single images, low resolution, and translation biases.
Hierarchical Graph Learning with Small-World Brain Connectomes for Cognitive Prediction
Jiang, Yu (Chinese University of Hong Kong), Yuan, Yixuan (Southern University of Science and Technology)
Graph Neural NetworkBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This study investigates cognitive score prediction based on functional MRI and proposes the SW-HGL framework, which includes hierarchical graph learning and small-world brain connectivity graphs.
Hierarchical multiple instance learning for COPD grading with relatively specific similarity
Zhang, Hao (Nanjing Forestry University), Zhou, S. Kevin (Hohai University)
ClassificationConvolutional Neural NetworkImageBiomedical DataComputed Tomography
🎯 What it does: A hierarchical multi-instance learning (H-MIL) framework is proposed, incorporating relative specific similarity (RSS) loss in COPD grading to achieve more refined classification of lung diseases.
Hierarchical Symmetric Normalization Registration using Deformation-Inverse Network
Sha, Qingrui (ShanghaiTech), Shen, Dinggang (Shanghai United Imaging Intelligence Co., Ltd.)
Image TranslationSegmentationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: A hierarchical symmetric normalization registration framework (HSyN) is proposed, which estimates bidirectional half displacement fields through a symmetric normalization network and learns the inverse displacement using a deformation inverse network, achieving high-precision medical image registration under large deformations.
Hierarchical Text-to-Vision Self Supervised Alignment for Improved Histopathology Representation Learning
Watawana, Hasindri (Mohamed Bin Zayed University of Artificial Intelligence), Khan, Fahad Shahbaz (Mohamed Bin Zayed University of Artificial Intelligence)
ClassificationRepresentation LearningConvolutional Neural NetworkLarge Language ModelVision Language ModelContrastive LearningImageBiomedical Data
🎯 What it does: By combining automatically generated hierarchical natural language descriptions with visual hierarchies, a Hierarchical Language-tied Self-Supervision (HLSS) framework is proposed to achieve hierarchical alignment in self-supervised learning of medical images (histology).
High-resolution Medical Image Translation via Patch Alignment-Based Bidirectional Contrastive Learning
Zhang, Wei (City University of Hong Kong), Li, Xinyue (City University of Hong Kong)
Image TranslationGenerationData SynthesisGenerative Adversarial NetworkContrastive LearningImageBiomedical Data
🎯 What it does: A bidirectional contrastive learning model based on Patch alignment (PPT) is proposed, which can quickly generate corresponding IHC stained images from H&E stained images in seconds.
HistGen: Histopathology Report Generation via Local-Global Feature Encoding and Cross-modal Context Interaction
Guo, Zhengrui (Hong Kong University of Science and Technology), Chen, Hao (Harvard Medical School)
GenerationTransformerImageTextMultimodality
🎯 What it does: This paper presents HistGen, a panoramic slice report generation framework based on multi-instance learning, capable of automatically generating high-quality pathology reports.
HistoSyn: Histomorphology-Focused Pathology Image Synthesis
Yin, Chong (Hong Kong Baptist University), Yuen, Pong C. (Chinese University of Hong Kong)
SegmentationGenerationData SynthesisSupervised Fine-TuningDiffusion modelAuto EncoderImageBiomedical Data
🎯 What it does: A text prompt based on spatial and morphological attributes is proposed to guide diffusion models in generating high-quality pathological images with diagnostic features, and to achieve a quantitative assessment of the quality of synthetic images.
HoG-Net: Hierarchical Multi-Organ Graph Network for Head and Neck Cancer Recurrence Prediction from CT Images
Bae, Joseph (Stony Brook University), Prasanna, Prateek (Stony Brook University)
ClassificationGraph Neural NetworkImageBiomedical DataComputed Tomography
🎯 What it does: A hierarchical multi-organ graph network (HoG-Net) was constructed to transform the primary tumors and organs at risk (OAR) annotated by doctors in CT images into a graph structure, and to predict local recurrence in patients with head and neck squamous cell carcinoma (HNSCC) using a graph attention network.
HRDecoder: High-Resolution Decoder Network for Fundus Image Lesion Segmentation
Ding, Ziyuan (Central South University), Liu, Qing (University of Oulu)
SegmentationConvolutional Neural NetworkImage
🎯 What it does: The HRDecoder network is proposed, which simulates high-resolution feature learning through the HRL module and achieves high-resolution fundus image lesion segmentation using the HFF module.
HuLP: Human-in-the-Loop for Prognosis
Ridzuan, Muhammad (Mohamed Bin Zayed University of Artificial Intelligence), Yaqub, Mohammad (Mohamed bin Zayed University of Artificial Intelligence)
ClassificationExplainability and InterpretabilityConvolutional Neural NetworkTransformerBiomedical DataComputed TomographyElectronic Health Records
🎯 What it does: The HuLP (Human-in-the-Loop for Prognosis) model is proposed and implemented, supporting clinical doctors in manually intervening in model predictions during the inference phase, while learning from imaging data to fill in missing clinical variables and complete survival time predictions.
HUP-3D: A 3D multi-view synthetic dataset for assisted-egocentric hand-ultrasound-probe pose estimation
Birlo, Manuel (University College London), Stoyanov, Danail (University College London)
Data SynthesisPose EstimationConvolutional Neural NetworkGenerative Adversarial NetworkImageMultimodalityUltrasound
🎯 What it does: A multi-view synthetic dataset HUP-3D has been constructed and released for estimating the pose of handheld probes in obstetric ultrasound, and its effectiveness for 3D arm and tool pose estimation has been validated.
Hybrid-Structure-Oriented Transformer for Arm Musculoskeletal Ultrasound Segmentation
Chen, Lingyu (Nanjing University of Aeronautics and Astronautics), Chen, Fang (Tsinghua University)
SegmentationTransformerImageUltrasound
🎯 What it does: The paper proposes a hybrid structure Transformer model HSformer for musculoskeletal ultrasound images of the arm, achieving simultaneous segmentation of skin, subcutaneous fat, muscle, and bone.
HyperSpace: Hypernetworks for spacing-adaptive image segmentation
Joutard, Samuel (ImFusion), Prevost, Raphael (ImFusion)
SegmentationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A spatial resolution adaptive U-Net based on hypernetworks is proposed, which works directly at native resolution without the need for resampling during medical image segmentation.
HySparK: Hybrid Sparse Masking for Large Scale Medical Image Pre-Training
Tang, Fenghe (University of Science and Technology of China), Zhou, S. Kevin (Hohai University)
SegmentationGenerationConvolutional Neural NetworkTransformerContrastive LearningImageBiomedical DataComputed Tomography
🎯 What it does: A generative self-supervised pre-training method called HySparK based on a hybrid CNN-Transformer architecture has been developed, implementing self-supervised learning for 3D medical images using a bottom-up sparse mask and hierarchical decoding.
I2Net: Exploiting Misaligned Contexts Orthogonally with Implicit-Parameterized Implicit Functions for Medical Image Segmentation
Yu, Jiahao (Tsinghua University), Chen, Li (Tsinghua University)
SegmentationConvolutional Neural NetworkTransformerImageBiomedical DataComputed Tomography
🎯 What it does: This paper proposes I Net, which utilizes implicitly parameterized INR to dynamically generate model parameters, better addressing the contextual alignment inconsistency problem in medical image segmentation.
IarCAC: Instance-aware Representation for Coronary Artery Calcification Segmentation in Cardiac CT angiography
Jiang, Weili (Sichuan University), Chen, Mao (Sichuan University)
SegmentationConvolutional Neural NetworkTransformerImageBiomedical DataComputed Tomography
🎯 What it does: The IarCAC model is proposed, utilizing instance-aware sparse attention Transformer and Fourier domain guidance module to achieve coronary artery calcification segmentation.
IHCSurv: Effective Immunohistochemistry Priors for Cancer Survival Analysis in Gigapixel Multi-stain Whole Slide Images
Zhang, Yejia (DAMO Academy, Alibaba Group), Jiang, Hui (DAMO Academy, Alibaba Group)
ClassificationTransformerImageBiomedical Data
🎯 What it does: A framework called IHCSurv is proposed for cancer survival prediction using immunohistochemistry (IHC) specific priors, and the discriminative ability for panoramic images is enhanced through spatially constrained spectral clustering and regional Transformers.
IHRRB-DINO: Identifying High-Risk Regions of Breast Masses in Mammogram Images Using Data-Driven Instance Noise (DINO)
Kasem, Mahmoud SalahEldin (Assiut University), El-Baz, Ayman (University of Louisville)
Object DetectionTransformerContrastive LearningImage
🎯 What it does: A Transformer-based model for breast X-ray image detection and localization of breast masses, named IHRRB-DINO, has been developed, which enhances localization accuracy through data-driven instance noise.
IM-MoCo: Self-supervised MRI Motion Correction using Motion-Guided Implicit Neural Representations
Al-Haj Hemidi, Ziad (Universität zu Lübeck), Heinrich, Mattias P. (Universität zu Lübeck)
ClassificationRestorationImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes an instantiation motion correction pipeline (IM-MoCo) based on motion-guided implicit neural representation (INR), which effectively suppresses MRI motion artifacts while preserving anatomical structures.