MICCAI 2025 Papers with AI Summaries
International Conference on Medical Image Computing and Computer-Assisted Intervention · 1027 papers
→ MICCAI 2025 papers with code (609)
Each paper below shows an AI-generated one-line summary. Get the full 6-part summary (innovation, method, data, results, limitations) and search all 1027 MICCAI 2025 papers by keyword, author or institution —
free trial on arXivSub.
3D Acetabular Surface Reconstruction from 2D Pre-operative X-ray Images using SRVF Elastic Registration and Deformation Graph
Zhang, Shuai (University College London), Mazomenos, Evangelos B. (University College London)
SegmentationOptimizationImageMeshComputed Tomography
🎯 What it does: Using SRVF elastic registration and embedded deformation maps, we reconstruct patient-specific 3D acetabular surfaces and predict suitable acetabular cup sizes based on only three 2D X-rays.
3D Dynamic Prediction of Missing Teeth in Diverse Patterns via Centroid-prompted Diffusion Model
Ji, Zongrui (Tongji University), Ma, Lei (Peking University)
GenerationData SynthesisDiffusion modelPoint CloudMeshComputed Tomography
🎯 What it does: A unified framework is proposed that utilizes a dynamic iterative generation strategy and centroid hints for teeth in a conditional diffusion model to achieve precise prediction of the 3D shapes and positions of multiple missing teeth.
4D CardioSynth: Synthesising Dynamic Virtual Heart Populations through Spatiotemporal Disentanglement
Dou, Haoran (University of Manchester), Frangi, Alejandro F. (University of Manchester)
GenerationData SynthesisGraph Neural NetworkAuto EncoderMeshTime SeriesBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A 4D CardioSynth framework is proposed to generate dynamic 3D virtual populations of hearts through separated spatial and temporal latent subspaces.
6D Object Pose Tracking for Orthopedic Surgical Training using Visual-Inertial Sensor Fusion
Hogenkamp, Maarten (ETH Zurich), Meboldt, Mirko (ETH Zurich)
Object TrackingPose EstimationSimultaneous Localization and MappingVideoMultimodality
🎯 What it does: In digital orthopedic surgery training, a visual-inertial 6D target pose tracking system utilizing dual cameras and embedded IMU is proposed, capable of real-time precise tracking of surgical tools and anatomical structures.
A Boundary-aware Cold-Diffusion Model for Electron Microscopy Segmentation
Qi, Muge (Peking University), Ma, Lei (Peking University)
SegmentationConvolutional Neural NetworkDiffusion modelImage
🎯 What it does: This paper proposes a boundary-aware model based on cold diffusion for semantic segmentation of electron microscope images.
A Causal-holistic Adaptive Intervention Network for Tailoring Automated Coronary Artery Disease Diagnosis to Individual Patients
Ma, Xinghua (Harbin Institute of Technology), Gao, Xin (Chinese Academy of Sciences)
ClassificationAnomaly DetectionTransformerBiomedical DataComputed Tomography
🎯 What it does: A Causal-Holistic Adaptive Intervention Network (CAIN) is proposed for personalized diagnosis of coronary artery disease (CAD).
A Causality-Inspired Model for Intima-Media Thickening Assessment in Ultrasound Videos
Gao, Shuo (Southeast University), Zhou, Guangquan (Southeast University)
ClassificationRecognitionContrastive LearningVideoTextUltrasound
🎯 What it does: A method for evaluating ultrasound video plaques based on causal models is proposed, eliminating style bias caused by changes in perspective and enhancing content relevance.
A Composite Alignment-Aware Framework for Myocardial Lesion Segmentation in Multi-sequence CMR Images
Gao, Yifan (University of Science and Technology of China), Wang, Xiaosong (Shanghai Artificial Intelligence Laboratory)
SegmentationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A multi-sequence CMR myocardial lesion segmentation framework CAA-Seg based on composite alignment is proposed.
A Curvature-Guided Diffeomorphic Mesh Deformation Framework for Lifespan Brain Cortical Surface Reconstruction
Teng, Lin (ShanghaiTech University), Shen, Dinggang (Shanghai United Imaging Intelligence Co., Ltd.)
Convolutional Neural NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A curvature-guided differential homeomorphic mesh deformation framework is proposed for lifelong cortical surface reconstruction.
A Diffusion-Driven Temporal Super-Resolution and Spatial Consistency Enhancement Framework for 4D MRI imaging
Zhou, Xuanru (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences), Wang, Shanshan (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences)
RestorationSuper ResolutionTransformerDiffusion modelBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Proposes the TSSC-Net framework to achieve spatiotemporal super-resolution and spatial consistency enhancement for 4D MRI.
A flexible deep learning framework for survival analysis with medical data
Campanella, Gabriele (Icahn School of Medicine at Mount Sinai), Fuchs, Thomas J. (University of Zurich)
ImageTabularBiomedical DataComputed TomographyElectronic Health Records
🎯 What it does: A medical survival analysis framework based on the Deep Conditional Transformation Model (DCTM) is proposed, which can directly handle non-tabular data such as images and electronic health records.
A Frequency-Aware Self-Supervised Learning for Ultra-Wide-Field Image Enhancement
Liao, Weicheng (Zhejiang University of Technology), Zhao, Yitian (Ningbo Institute of Materials Technology and Engineering)
RestorationImage
🎯 What it does: A frequency-aware self-supervised enhancement framework for UWF retinal images is proposed and implemented, which includes a deblurring module FRED and an illumination compensation module RICE, balancing detail preservation and color accuracy.
A Holistic Time-Aware Classification Model for Multimodal Longitudinal Patient Data
Susetzky, Tobias (Technical University of Munich), Rueckert, Daniel (Technical University of Munich)
ClassificationRecommendation SystemTransformerMultimodalityBiomedical DataElectronic Health Records
🎯 What it does: A time-aware multimodal Transformer encoder, TAMME, is proposed to integrate images, text, numerical, and categorical data in longitudinal EHRs, supporting uneven time sampling.
A Hybrid Contrastive Ordinal Regression Method for Advancing Disease Severity Assessment in Imbalanced Medical Datasets
Saleem, Afsah (Edith Cowan University), Gilani, Syed Zulqarnain (University of Western Australia)
ClassificationSegmentationData-Centric LearningContrastive LearningImageBiomedical DataUltrasound
🎯 What it does: A hybrid contrastive learning ordinal regression framework is proposed to address the issues of class imbalance and ordinal relationships in medical images.
A Large-scale Neural Model Inversion Framework for Effective Connectivity Estimation
Li, Guoshi (University of North Carolina at Chapel Hill), Yap, Pew-Thian (University of North Carolina at Chapel Hill)
Biomedical DataMagnetic Resonance ImagingAlzheimer's Disease
🎯 What it does: Developed the LEMI framework, which utilizes a linear neural mass model and Kalman filtering gradient descent method to estimate effective connectivity (EC) and local excitation-inhibition (E-I) balance in large-scale brain networks.
A Learning Framework for Predicting CT-based PRM Biomarker from MRI Sequences in COPD
Xu, Yiling (University of Heidelberg), Weinheimer, Oliver (University of Heidelberg)
SegmentationData SynthesisConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: Using multi-sequence functional MRI combined with deep learning models to predict region-specific airway and alveolar lesion indicators based on PRM in CT scans of COPD patients.
A Model Order-Free Method for Stable States Extraction in Dynamic Functional Connectivity
Fang, Songke (Shanxi University), Du, Yuhui (Shanxi University)
Biomedical DataMagnetic Resonance Imaging
🎯 What it does: A model-free dynamic functional connectivity state extraction method is proposed, which constructs a similarity graph through stable clustering and multi-scale random walks to achieve the retention and stabilization of multi-scale state information.
A Multi-Branch Framework for Cross-Domain Vessel Segmentation via the Few-Shot Paradigm
Huang, Zihang (Huazhong University of Science and Technology), Yang, Xin (Shenzhen University)
SegmentationDomain AdaptationConvolutional Neural NetworkImage
🎯 What it does: A multi-branch few-shot cross-domain vascular segmentation framework is proposed, utilizing high-frequency auxiliary modality, dual-modal feature extraction and fusion, as well as a multi-branch feature extraction module to achieve cross-modal vascular segmentation.
A Multimodal Contrastive Learning for Detecting Aortic Dissection on 3D Non-Contrast CT with Anatomy Simplification
Zhang, Duoer (Zhejiang Lab), Zhu, Wentao (Westlake University)
ClassificationObject DetectionSegmentationConvolutional Neural NetworkSupervised Fine-TuningContrastive LearningImageMultimodalityComputed Tomography
🎯 What it does: Using multimodal contrastive learning to pre-train a 3D NC-CT encoder for aortic dissection detection and lumen segmentation.
A New Paradigm for Low-dose PET/CT Reconstruction with Mamba-powered Progressive Network and Physics-informed Consistency
Tang, Zixin (ShanghaiTech University), Shen, Dinggang (Shanghai United Imaging Intelligence Co., Ltd.)
RestorationSegmentationConvolutional Neural NetworkGenerative Adversarial NetworkBiomedical DataComputed TomographyPositron Emission Tomography
🎯 What it does: A collaborative reconstruction framework is proposed to achieve radiation dose reduction by jointly reconstructing AC SPET and SCT from the original NAC LPET and LCT in low-dose PET/CT scans.
A Non-contrast Head CT Foundation Model for Comprehensive Neuro-Trauma Triage
Yoo, Youngjin (Siemens Healthineers), Gibson, Eli (New York University)
Object DetectionSegmentationConvolutional Neural NetworkLarge Language ModelImageBiomedical DataComputed Tomography
🎯 What it does: A 3D foundational model specifically designed for head CT neurotrauma triage has been developed, capable of multi-label detection of 16 key traumas.
A Novel ED Triage Framework Using Conditional Imputation, Multi-Scale Semantic Learning, and Cross-Modal Fusion
Xiao, Yi (Southeast University), Wang, Chunyu (Peking University People's Hospital)
ClassificationRecurrent Neural NetworkTransformerAuto EncoderGenerative Adversarial NetworkMultimodalityTabularBiomedical DataElectronic Health Records
🎯 What it does: This paper proposes a multimodal learning framework for triage in the emergency department, addressing the issues of missing data and sparse features.
A novel Fourier Adjacency Transformer for advanced EEG emotion recognition
Wang, Jinfeng (Kunming University of Science and Technology), Ding, Jiaman (Kunming University of Science and Technology)
RecognitionTransformerTime SeriesBiomedical Data
🎯 What it does: This paper proposes a Transformer model that combines Fourier periodic features with graph structure attention—Fourier Adjacency Transformer—for EEG emotion recognition.
A Novel Framework for Integrating 3D Ultrasound into Percutaneous Liver Tumour Ablation
Xing, Shuwei (Western University), Fenster, Aaron (Western University)
Image TranslationSegmentationImageVideoBiomedical DataMagnetic Resonance ImagingComputed TomographyUltrasound
🎯 What it does: A set of integrated framework for percutaneous ablation of liver tumors based on 3D ultrasound has been proposed and validated, including the registration and multimodal visualization of 2D ultrasound with CT/MRI.
A Novel Streamline-based diffusion MRI Tractography Registration Method with Probabilistic Keypoint Detection
Wang, Junyi (University of Electronic Science and Technology of China), Zhang, Fan (Harvard Medical School and Brigham and Women's Hospital)
Graph Neural NetworkBiomedical DataMagnetic Resonance Imaging
🎯 What it does: An unsupervised anatomical keypoint detection and Thin-Plate Spline transformation method for dMRI trajectory registration based on streamlines is proposed.
A Prior-Driven Lightweight Network for Endoscopic Exposure Correction
Wu, Zhijian (Westlake University), Zheng, Yefeng (Westlake University)
RestorationTransformerImage
🎯 What it does: A lightweight endoscopic exposure correction network WTNet is designed, utilizing wavelet transform to separate low-frequency illumination information from high-frequency details, and modeling them through Transformer and depthwise convolution to achieve exposure correction and low-light enhancement.
A Semi-Supervised Knowledge Distillation Framework for Left Ventricle Segmentation and Landmark Detection in Echocardiograms
Chen, Haoyuan (ShanghaiTech University), Shen, Dinggang (Shanghai United Imaging Intelligence Co., Ltd.)
SegmentationKnowledge DistillationConvolutional Neural NetworkSupervised Fine-TuningImageVideoUltrasound
🎯 What it does: A semi-supervised knowledge distillation framework is proposed, combining task-aware spatiotemporal networks (TSTNet) for left ventricle segmentation and landmark detection in echocardiography.
A Two-Stage Method for Specular Highlight Detection and Removal in Medical Images
Li, Zefeng (Sun Yat-sen University), Huang, Kai (City University of Macau)
RestorationSegmentationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A two-stage framework for metal highlight detection and removal has been designed and implemented, first using HFANet for highlight detection and rough removal, followed by the LaMa large mask filling model for detail restoration, in order to enhance the visual quality of medical images.
A Unified Continuous Staging Framework for Alzheimer’s Disease and Lewy Body Dementia via Hierarchical Anatomical Features
Chen, Tong (University of Sydney), Zhu, Dajiang (University of Georgia)
ClassificationGraph Neural NetworkBiomedical DataMagnetic Resonance ImagingDiffusion Tensor ImagingAlzheimer's Disease
🎯 What it does: A multi-scale hierarchical anatomical feature fusion framework is proposed, utilizing graph neural networks and tree embedding models to achieve continuous staging and four-class classification of Alzheimer's disease and Lewy body dementia.
A Unified Missing Modality Imputation Model with Inter-Modality Contrastive and Consistent Learning
Qi, Liangce, Jiang, Zhengang (Changchun University Of Science And Technology)
RestorationSegmentationTransformerContrastive LearningMultimodalityBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A unified missing modality completion model is proposed, which can generate missing modality images based on any subset of multimodal MRI.
A Uniform Multi-mode Fused Framework for Velocity Field Estimation in Ultrasound Imaging
Li, Hailong (Xiamen University), Chen, Yinran (Xiamen University)
Optical FlowImageBiomedical DataUltrasound
🎯 What it does: A unified multimodal fusion framework is proposed for velocity field estimation in ultrasound imaging, combining constraints such as multi-angle optical flow, Doppler, and coherence consistency, and adapting to different scanning modes including linear, phased, and matrix arrays.
A Virtual Domain Collaborative Learning Framework for Semi-supervised Microscopic Hyperspectral Image Segmentation
Qin, Geng, Guo, Yuxing
SegmentationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes a global-local segmentation framework that integrates cross-entropy, Dice, and boundary constraints, achieving finer foreground/background separation through adaptive weight adjustment.
Abnormality-Driven Representation Learning for Radiology Imaging
Ligero, Marta (EKFZ for Digital Health TU Dresden), Kather, Jakob Nikolas (EKFZ for Digital Health TU Dresden)
Anomaly DetectionRepresentation LearningConvolutional Neural NetworkTransformerContrastive LearningImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: The CLEAR framework is proposed, which achieves weakly supervised learning for 3D diagnostic tasks through frozen embeddings of 2D slices and attention aggregation, and based on this, the Lesion-enhanced Contrastive Learning (LeCL) method is developed.
Accelerated Free-Breathing 5D Multi-Echo Respiratory Motion-Resolved R2*, PDFF, and QSM Using Novel Composite Total Variation
Kang, MungSoo (Stony Brook University), Kee, Youngwook (Stony Brook University)
Biomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes a 5D compressed sensing reconstruction method with composite TV regularization in free breathing, multi-echo 3D gradient echo magnetic resonance imaging, achieving joint sparse modeling of respiratory motion and echo evolution.
Accurate and Efficient Fetal Birth Weight Estimation from 3D Ultrasound
Wang, Jian (Shenzhen University), Yang, Xin (Shenzhen University)
Convolutional Neural NetworkImageBiomedical DataUltrasound
🎯 What it does: This paper proposes a direct fetal birth weight prediction method based on 3D ultrasound volume, combining a multi-scale feature fusion network and a synthetic sample learning framework.
Accurate Boundary Alignment and Realism Enhancement for Colonoscopic Polyp Image-Mask Pair Generation
Qiu, Riyu (Xiamen University), Wang, Liansheng (Shanghai Changhai Hospital)
SegmentationGenerationData SynthesisDiffusion modelAuto EncoderImage
🎯 What it does: This study constructs Polyp-LDM, a latent diffusion model that combines latent space and authenticity enhancement, to generate realistic colonoscopic polyp images and corresponding masks.
Active Source-Free Cross-Domain and Cross-Modality Adaptation for Volumetric Medical Image Segmentation by Image Sensitivity and Organ Heterogeneity Sampling
Yang, Jin (Mallinckrodt Institute of Radiology, Washington University School of Medicine in St. Louis), Sotiras, Aristeidis (Institute for Informatics, Data Science and Biostatistics, Washington University School of Medicine in St. Louis)
SegmentationDomain AdaptationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: This paper proposes an active source-free cross-domain and cross-modal medical image segmentation framework, utilizing two active sampling strategies: Image Sensitivity Query (ISQ) and Organ Heterogeneity Query (OHQ). It dynamically fuses the scores of both strategies through a dynamic image-to-organ scaling mechanism, and then iteratively queries a small number of labeled samples in the target domain to fine-tune the model.
Ada-FCN: Adaptive Frequency-Coupled Network for fMRI-Based Brain Disorder Classification
Xun, Yue (Hong Kong Polytechnic University), Wang, Shujun (Hong Kong Polytechnic University)
ClassificationGraph Neural NetworkTime SeriesBiomedical DataMagnetic Resonance ImagingAlzheimer's Disease
🎯 What it does: Proposes the Ada-FCN framework, which utilizes adaptive cascade decomposition to learn task-related frequency bands, and constructs a unified brain functional network through frequency coupling connections, ultimately performing unified GCN for brain disease classification on this network.
ADA: An Adaptive Augmentation Framework for Single-Source Domain Generalization in Medical Image Segmentation
Huang, Runlin (Beijing Normal-Hong Kong Baptist University), Su, Weifeng (Beijing Normal-Hong Kong Baptist University)
SegmentationDomain AdaptationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: Proposes the Adaptive Augmentation Framework (ADA), which enhances the cross-domain generalization ability of single-source medical image segmentation through adaptive data augmentation.
Adaptation of Multi-modal Representation Models for Multi-task Surgical Computer Vision
Walimbe, Soham (University of Strasbourg), Padoy, Nicolas (University of Strasbourg, CNRS, INSERM, ICube, UMR7357)
RecognitionGraph Neural NetworkPrompt EngineeringContrastive LearningVideoMultimodality
🎯 What it does: A multimodal task-agnostic model MML-SurgAdapt based on CLIP is proposed, utilizing single-positive multi-label learning for phase recognition, CVS assessment, and action triplet recognition in surgical videos.
ADAptation: Reconstruction-based Unsupervised Active Learning for Breast Ultrasound Diagnosis
Duan, Yaofei (Macao Polytechnic University), Tan, Tao (Macao Polytechnic University)
Domain AdaptationDiffusion modelContrastive LearningImageBiomedical DataUltrasound
🎯 What it does: The ADAptation framework is proposed, utilizing unsupervised active learning to achieve cross-domain adaptation for breast ultrasound diagnosis, and automatically selecting the most informative target domain samples for labeling.
Adapting Foundation Model for Dental Caries Detection with Dual-View Co-Training
Luo, Tao (ShanghaiTech University), Cui, Zhiming (ShanghaiTech University)
Object DetectionTransformerSupervised Fine-TuningImageComputed TomographyBenchmark
🎯 What it does: A dual-view collaborative training framework for dental caries detection, DVCTNet, is proposed, utilizing two perspectives of panoramic X-rays and sectioned tooth images to simulate the clinical diagnosis process and improve detection accuracy.
Adapting Vision Foundation Models for Real-time Ultrasound Image Segmentation
Zhang, Xiaoran (Yale University), Sun, Shanhui (United Imaging Intelligence)
SegmentationImageBiomedical DataUltrasound
🎯 What it does: A real-time ultrasound image segmentation framework based on Hiera and DINOv2 is proposed.
Adaptive Adversarial Data Augmentation with Trajectory Constraint for Alzheimer’s Disease Conversion Prediction
Cho, Hyuna (Pohang University of Science and Technology), Kim, Won Hwa (Pohang University of Science and Technology)
ClassificationAdversarial AttackTransformerBiomedical DataPositron Emission TomographyAlzheimer's DiseaseOrdinary Differential Equation
🎯 What it does: Generate pMCI samples through adaptive adversarial attacks and trajectory constraints, and train classifiers to predict the risk of MCI patients converting to Alzheimer's disease based on this.
Adaptive Embedding for Long-Range High-Order Dependencies via Time-Varying Transformer on fMRI
Xue, Rundong (Xi'an Jiaotong University), Gao, Yue (Tsinghua University)
ClassificationTransformerTime SeriesBiomedical DataMagnetic Resonance ImagingAlzheimer's Disease
🎯 What it does: This paper proposes a long-range high-order dependency framework called LHDFormer, which integrates time-varying NeuroWalk kernels and dual-domain Transformers for dynamic functional brain network analysis and brain disease diagnosis.
Adaptive Frame Selection for Gestational Age Estimation from Blind Sweep Fetal Ultrasound Videos
Akumu, Tanya (Universitat de Barcelona), Lekadir, Karim (Institució Catalana de Recerca i Estudis Avançats)
Object DetectionOptimizationConvolutional Neural NetworkVideoBiomedical DataUltrasound
🎯 What it does: A framework named SelectGA has been developed, utilizing adaptive frame selection technology to process blind-scan fetal ultrasound videos for gestational age estimation.
Adaptive Graph Learning with Multi-Graph Convolutions for Brain Disorder Classification
Noman, Fuad (Monash University Malaysia), Ting, Chee-Ming (King Abdullah University of Science and Technology)
ClassificationGraph Neural NetworkMixture of ExpertsContrastive LearningGraphBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A brain network classification framework based on fMRI, AGMGC, has been constructed, which can dynamically learn brain graph structures and extract features through multi-graph convolution.
Adaptive Spatial Transcriptomics Interpolation via Cross-modal Cross-slice Modeling
Que, Ningfeng (University of Dundee), Li, Chao (University of Dundee)
Image TranslationRestorationData SynthesisGraph Neural NetworkImageBiomedical Data
🎯 What it does: A deep learning framework C2-STi is proposed for interpolating missing ST slices between continuous ST slices.
Adaptive Stain Normalization for Cross-Domain Medical Histology
Xu, Tianyue (Johns Hopkins University), Haeffele, Benjamin D. (University of Pennsylvania)
ClassificationObject DetectionDomain AdaptationConvolutional Neural NetworkGenerative Adversarial NetworkImageBiomedical Data
🎯 What it does: A trainable pigment decoupling network based on the Beer-Lambert law, named BeerLaNet, is proposed and integrated as a plug-in module into target detection and classification networks to achieve adaptive pigment normalization for cross-domain pathological images.
Adaptively Distilled ControlNet: Accelerated Training and Superior Sampling for Medical Image Synthesis
Qiu, Kunpeng (National University of Singapore), Guo, Yongxin (National University of Singapore)
SegmentationGenerationData SynthesisKnowledge DistillationDiffusion modelImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: This paper proposes Adaptively Distilled ControlNet, which uses a teacher-student dual-branch structure to perform adaptive distillation on a student model that only uses masks, guided by a teacher model that uses both images and masks during training. After training, only the student model is used to quickly generate accurately aligned medical images.
Addressing Label Scarcity and Domain Shift in Medical Image Segmentation
Kumari, Suruchi (Indian Institute of Technology Roorkee), Singh, Pravendra (Indian Institute of Technology Roorkee)
SegmentationDomain AdaptationImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: A unified framework is proposed to address the issues of label scarcity (semi-supervised learning) and domain shift (unsupervised domain adaptation) in medical image segmentation.
AdFair-CLIP: Adversarial Fair Contrastive Language-Image Pre-training for Chest X-rays
Yi, Chenlang (Texas Aamp University), Yang, Tianbao (University Of Iowa)
ClassificationRepresentation LearningAdversarial AttackConvolutional Neural NetworkContrastive LearningImageTextMultimodalityComputed Tomography
🎯 What it does: This paper proposes AdFair-CLIP, a language pre-training model for chest X-ray images that achieves fairness through adversarial feature intervention, aiming to eliminate racial and gender biases.
Advancing Medical Representation Learning Through High-Quality Data
Baghbanzadeh, Negin (York University), Dolatabadi, Elham (York University)
RetrievalRepresentation LearningTransformerVision Language ModelContrastive LearningImageTextMultimodalityBiomedical Data
🎯 What it does: A high-quality Open-PMC medical image-text dataset was constructed and a visual-language model was trained using contrastive learning.
AdvMIM: Adversarial Masked Image Modeling for Semi-Supervised Medical Image Segmentation
Zhu, Lei (Hong Kong University of Science and Technology), Liu, Yong (Beijing University of Posts and Telecommunications)
SegmentationDomain AdaptationConvolutional Neural NetworkTransformerGenerative Adversarial NetworkImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: Developed an Adversarial Masked Image Modeling (AdvMIM) method for semi-supervised medical image segmentation, which constructs a masked domain and uses adversarial training to reduce the gap between the original domain and the masked domain, thereby enhancing the performance of Transformers under limited labeled data.
AEM: Attention Entropy Maximization for Multiple Instance Learning based Whole Slide Image Classification
Zhang, Yunlong (Zhejiang University), Yang, Lin (Westlake University)
ClassificationTransformerImage
🎯 What it does: Proposes the Attention Entropy Maximization (AEM) regularization method to alleviate the overfitting problem caused by excessive attention concentration in multi-instance learning.
AffinityUMamba: Uncertainty-Aware Medical Image Segmentation via Probabilistic Weak Supervision Beyond Gold-Standard Annotations
Zhang, Yukun (Beijing University of Posts and Telecommunications), Cheng, Kun (Beijing University of Posts and Telecommunications)
SegmentationConvolutional Neural NetworkMultimodalityBiomedical DataMagnetic Resonance ImagingComputed TomographyUltrasound
🎯 What it does: This paper proposes AffinityUMamba, a weakly supervised medical image segmentation framework based on a dual-branch U-Net structure, aimed at handling label noise through probabilistic weak supervision and enhancing uncertainty calibration.
All-in-One Medical Image Restoration with Latent Diffusion-Enhanced Vector-Quantized Codebook Prior
Chen, Haowei (Beihang University), Xu, Yan (Beihang University)
RestorationSuper ResolutionMixture of ExpertsDiffusion modelImageBiomedical DataMagnetic Resonance ImagingComputed TomographyPositron Emission Tomography
🎯 What it does: The DiffCode framework is proposed to achieve full-task medical image restoration, capable of simultaneously handling MRI super-resolution, CT denoising, and PET synthesis.
Alzheimer’s Disease Recognition Based on Adaptive Graph Normalization Flow for Incomplete Multimodal Data Fusion
Li, Yaqin (Ningbo University), Gao, Linlin (Ningbo University)
RecognitionGraph Neural NetworkFlow-based ModelMultimodalityBiomedical DataMagnetic Resonance ImagingComputed TomographyPositron Emission TomographyAlzheimer's Disease
🎯 What it does: To address the issue of multimodal missing data in the diagnosis of Alzheimer's disease, the AGDiC model is proposed, achieving adaptive graph structure and consistent modality recovery and fusion with streaming distribution.
Ambiguous Medical Image Segmentation Using Diffusion Schrödinger Bridge
Baru, Lalith Bharadwaj (International Institute of Information Technology), Bapi, Raju S. (Alan Turing Institute and University College London)
SegmentationDiffusion modelScore-based ModelImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A Segmentation Schrödinger Bridge (SSB) framework is proposed to address the issue of ambiguous segmentation in medical imaging.
An Anatomical Significance-Aware Architecture for Explainable Myocardial Infarction Prediction via Multi-Task Learning
Peng, Jiachuan (University of Oxford), Grau, Vicente (University of Oxford)
ClassificationExplainability and InterpretabilityTransformerPoint Cloud
🎯 What it does: A dual-branch network based on Transformer has been constructed to achieve multi-task learning for myocardial infarction (MI) prediction and classification of cardiac substructures (left ventricular endocardium, epicardium, and right ventricular endocardium) on 3D cardiac point clouds.
Analysis of Image-and-Text Uncertainty Propagation in Multimodal Large Language Models with Cardiac MR-Based Applications
Tang, Yucheng (University College London), Hu, Yipeng (King's College London)
TransformerLarge Language ModelMultimodalityBiomedical DataMagnetic Resonance ImagingElectronic Health Records
🎯 What it does: A multi-modal uncertainty propagation model (MUPM) is proposed to quantify the uncertainty relationship between medical imaging and text inputs in multi-modal large language models, applied in cardiac MRI prediction tasks.
Anatomical Graph-based Multilevel Distillation for Robust Alzheimer’s Disease Diagnosis with Missing Modalities
Liu, Fei (Monash University Malaysia), Cheng, Jiayuan (Monash University Malaysia)
ClassificationKnowledge DistillationGraph Neural NetworkTransformerMultimodalityBiomedical DataMagnetic Resonance ImagingPositron Emission TomographyAlzheimer's Disease
🎯 What it does: A multi-layer distillation framework based on anatomical maps (AGMD) is proposed to achieve more robust early diagnosis of Alzheimer's disease (AD) using only MRI single-modal models in the absence of multimodal data such as PET.
Anatomical Structure Few-Shot Detection Utilizing Enhanced Human Anatomy Knowledge in Ultrasound Images
Zhu, Ying (Yunnan University), Pu, Bin (University of British Columbia)
Object DetectionConvolutional Neural NetworkImageBiomedical DataUltrasound
🎯 What it does: A few-shot ultrasound image structure detection framework TRR-CCM based on human anatomical knowledge is proposed, combining Circular Channel Mamba (CCM) and Topological Relationship Reasoning (TRR) to achieve multi-object detection;
Anatomy-Aware Frequency-Attention Transformer Networks for Liver Couinaud CT/MR Segmentation
Fan, Wenkang (Xiamen University), Luo, Xiongbiao (Xiamen University)
SegmentationTransformerImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: An anatomically aware frequency attention Transformer network (AFATN) is proposed for precise segmentation of liver Couinaud segments in CT/MR images.
Anatomy-Aware Low-Dose CT Denoising via Pretrained Vision Models and Semantic-Guided Contrastive Learning
Wang, Runze (Damo Academy Alibaba Group), Jin, Dakai (Alibaba Group)
RestorationSegmentationGenerative Adversarial NetworkContrastive LearningImageBiomedical DataComputed Tomography
🎯 What it does: A low-dose CT denoising framework called ALDEN is proposed, based on pre-trained visual models and semantically guided contrastive learning.
Anatomy-based Self-supervised Pre-training for Scale-robust Hierarchical Representations in Chest X-rays
Chu, Surong (Taiyuan University of Technology), Li, Shuo (Harbin Institute of Technology)
ClassificationSegmentationRepresentation LearningConvolutional Neural NetworkContrastive LearningImageBiomedical DataComputed Tomography
🎯 What it does: A scale-robust hierarchical anatomical representation framework (SRHRS) based on self-supervised learning is proposed, combining multi-scale input, location scale prediction (LSP), and decomposition prediction (DP) tasks to learn consistent and hierarchical anatomical representations of chest X-ray images.
Anatomy-Conserving Unpaired CBCT-to-CT Translation via Schrödinger Bridge
Shi, Ke (Wuhan University), Du, Bo (Wuhan University)
Image TranslationGenerationData SynthesisTransformerGenerative Adversarial NetworkContrastive LearningImageBiomedical DataComputed Tomography
🎯 What it does: A paired CBCT→CT translation framework based on the Schrödinger bridge, named ACSB, is proposed, which achieves high-quality synthetic CT while preserving anatomical structures.
Anatomy-Guided Multimodal Graph Networks for Alzheimer’s Disease: Integrative Analysis of Cross-Modal Brain Connectivity Signatures
Hu, Wenzheng (Shenzhen University), Lei, Baiying (Shenzhen University)
ClassificationConvolutional Neural NetworkGraph Neural NetworkMultimodalityBiomedical DataMagnetic Resonance ImagingPositron Emission TomographyAlzheimer's Disease
🎯 What it does: This paper proposes a multimodal graph network based on anatomical priors, using sMRI and PET data to construct brain region feature maps and predict the progression of Alzheimer's disease.
Anomaly Detection by Clustering DINO Embeddings using a Dirichlet Process Mixture
Schulthess, Nico (ETH Zurich), Konukoglu, Ender (ETH Zurich)
Anomaly DetectionContrastive LearningImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: Using the medical image patch embeddings extracted by DINOv2, a Dirichlet Process Mixture Model (DPMM) is employed to model the distribution of normal samples, and the anomaly score is calculated through the cosine similarity between the embeddings and the means of the nearest mixture components, achieving unsupervised anomaly detection and segmentation.
Aorta Multi-class Segmentation via Anatomically Constrained Plane Detection
An, Jonghoon (Soongsil University), Chung, Minyoung (Soongsil University)
SegmentationConvolutional Neural NetworkImageBiomedical DataComputed Tomography
🎯 What it does: A framework for plane detection based on anatomical constraints is proposed to address the accuracy challenges caused by boundary ambiguity and strong similarity in aortic multi-region segmentation, ultimately achieving end-to-end multi-class segmentation of the aorta.
Asymmetric Matching in Abdominal Lymph Nodes of Follow-up CT Scans
Mao, Yiji (Sichuan University), Zhang, Haixian (Sichuan University)
Graph Neural NetworkContrastive LearningImageBiomedical DataComputed Tomography
🎯 What it does: This study investigates the issue of asymmetric matching of abdominal lymph nodes in follow-up CT scans and proposes a framework that combines specificity extraction, correlation modeling, and attention fusion to achieve cross-scan lymph node correspondence.
Asynchronous Multi-Modal Learning for Dynamic Risk Monitoring of Acute Respiratory Distress Syndrome in Intensive Care Units
Feng, Yidan (Hong Kong Polytechnic University), Qin, Jing (Hong Kong Polytechnic University)
Anomaly DetectionConvolutional Neural NetworkTransformerSupervised Fine-TuningMultimodalityTabularBiomedical DataElectronic Health Records
🎯 What it does: Developed a continuous ARDS risk monitoring model based on asynchronous multimodal deep learning, achieving real-time risk prediction and urgency classification for ICU patients.
Attention-Based Multimodal Deep Learning Model for Post-Stroke Motor Impairment Prediction
Karakis, Rukiye (Sivas Cumhuriyet University), Boudrias, Marie-Hèléne (McGill University)
ClassificationConvolutional Neural NetworkMultimodalityBiomedical DataMagnetic Resonance ImagingDiffusion Tensor Imaging
🎯 What it does: A multimodal deep learning model based on attention mechanisms is proposed, utilizing whole-brain DTI microstructural indicators (FA, MD, RD, AD), structural MRI (WM, GM), and demographic features to classify upper limb motor function after stroke as good or poor.
Attention-Guided Vector Quantized Variational Autoencoder for Brain Tumor Segmentation
Ali, Danish (University of Western Australia), Hassan, Ghulam Mubashar (University of Western Australia)
SegmentationConvolutional Neural NetworkTransformerAuto EncoderImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A two-stage Attention-Guided Vector Quantized Variational Autoencoder (AG-VQ-VAE) model is proposed for brain tumor segmentation, focusing on improving the accuracy of tumor boundaries.
Augmented Reality-based Guidance with Deformable Registration in Head and Neck Tumor Resection
Yang, Qingyun (Vanderbilt University), Wu, Jie Ying (Florida International University)
SegmentationPose EstimationSimultaneous Localization and MappingPoint CloudMesh
🎯 What it does: A deformable registration framework combining pre-resection surface and post-resection cavity is proposed for the re-localization of positive margins after head and neck tumor resection, and it is integrated into an augmented reality (AR) guidance system.
Automated Auditing of Upper Endoscopy Procedure Times: A Temporal Multiclass Analysis
Bravo, Diego (Universidad Nacional de Colombia), Romero, Eduardo (Universidad Nacional de Colombia)
ClassificationRecognitionTransformerVideoBiomedical Data
🎯 What it does: A multi-scale video sequence model MSSI based on Transformer is proposed for automatically auditing the organ and gastric region dwell time during gastroscopy.
Automated Characterization of Myocardial Scar Topological Patterns for Ventricular Tachycardia Screening
Sheng, Xicheng (Fudan University), Zhuang, Xiahai (Fudan University)
ClassificationSegmentationConvolutional Neural NetworkImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: An end-to-end framework named PolarNet is proposed for the automated segmentation of myocardial scars and characterization of their topological subtypes in polar coordinates, assisting in the screening of ventricular tachycardia (VT).
Automated Detection of Abnormalities in Zebrafish Development
Sivaprasad, Sarath (CISPA Helmholtz Center for Information Security), Fritz, Mario (Helmholtz Institute for Pharmaceutical Research Saarland)
Anomaly DetectionTransformerImageTime Series
🎯 What it does: A large-scale high-resolution zebrafish embryo development image sequence dataset is proposed, and a Transformer-based spatiotemporal model is trained to achieve early detection of embryonic development abnormalities.
Automated Detection of BK Virus in H&E Whole-Slide Images Using Weakly-Supervised Deep Learning and Interpretable Morphological Biomarkers
Sahai, Sharifa (Harvard Medical School), Mahmood, Faisal (Harvard Medical School)
ClassificationObject DetectionSegmentationExplainability and InterpretabilityConvolutional Neural NetworkImageBiomedical Data
🎯 What it does: This study developed a weakly supervised deep learning model called BKVision, which automatically detects BK virus infection in kidney transplant biopsies using H&E slides and extracts interpretable nuclear morphological features through post-analysis.
Automated Integration of Surgical Implants into Digital Twins for Trauma Surgery
Stauffer, Tobias (ETH Zürich), Lohmeyer, Quentin (ETH Zürich)
Object DetectionPose EstimationRecurrent Neural NetworkBiomedical Data
🎯 What it does: This paper proposes an automatic method based on surgical tracking data to dynamically integrate implants such as screws and plates into a digital twin during the fracture reduction process.
Automatic dataset shift identification to support safe deployment of medical imaging AI
Roschewitz, Mélanie (Imperial College London), Glocker, Ben (Imperial College London)
Domain AdaptationAnomaly DetectionImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes an unsupervised dataset shift detection framework that can automatically distinguish between prevalence shift (label shift), covariate shift, and mixed shift during the deployment of medical imaging.
Automatic Deep Deformable Registration using Domain Adaptation and Run-Time Optimisation
Gadoux, Emilien (Institut Pascal), Bartoli, Adrien (University Hospital of Clermont Ferrand)
SegmentationDomain AdaptationOptimizationConvolutional Neural NetworkTransformerAuto EncoderImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A fully automated 3D-2D liver registration method has been developed, which first uses a deep network to segment anatomical landmarks in intraoperative images, and then accurately aligns the preoperative 3D model to the surgical images through a two-step neural network (affine estimation + latent space-based deformation optimization).
Autoregressive Medical Image Segmentation via Next-Scale Mask Prediction
Chen, Tao (Eindhoven University of Technology), Shan, Hongming (Fudan University)
SegmentationTransformerImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: This paper proposes an autoregressive-based medical image segmentation framework called AR-Seg, which can predict segmentation masks at multiple scales, achieving a segmentation process from coarse to fine.
AVDM: Controllable Adversarial Diffusion Model for Vessel-to-Volume Synthesis
Dai, Jian (Fudan University), Geng, Daoying (Fudan University)
SegmentationGenerationData SynthesisDiffusion modelImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper proposes a controllable adversarial diffusion model (AVDM) for generating volumes from vascular structures, addressing the issue of poor alignment of vascular structures in existing methods.
Aβ-PET Pattern Prediction via Graph Reconstruction-Aware Fusion (GRAF) of Functional and Structural Networks
Yuan, Haoyue (ShanghaiTech University), Shen, Dinggang (Shanghai United Imaging Intelligence Co., Ltd.)
Graph Neural NetworkMultimodalityBiomedical DataMagnetic Resonance ImagingPositron Emission TomographyAlzheimer's Disease
🎯 What it does: This paper proposes a graph self-supervised reconstruction fusion framework called GRAF, which jointly predicts early brain Aβ PET uptake maps in Alzheimer's disease using functional (rs-fMRI) and structural (dMRI) neural networks.
Background-Invariant Independence-Guided Multi-head Attention Network for Skin Lesion Classification
Roy, Debasmit (Jadavpur University), Sarkar, Ram (Jadavpur University)
ClassificationConvolutional Neural NetworkImage
🎯 What it does: Designed and implemented BIIGMA-Net, a network that enhances the robustness of skin lesion classification through multi-head independent guided channel attention and background-invariant vector sampling.
BaMCo: Balanced Multimodal Contrastive Learning for Knowledge-Driven Medical VQA
Yazıcı, Ziya Ata (Istanbul Technical University), Ekenel, Hazım Kemal (Istanbul Technical University)
ClassificationRecognitionRetrievalTransformerLarge Language ModelContrastive LearningMultimodalityBiomedical Data
🎯 What it does: This paper proposes a knowledge space pre-training method based on balanced multimodal contrastive learning (BaMCo) and integrates it into large language models (LLM) to achieve medical visual question answering (Medical VQA).
Bayesian Transformers and Higher-Order Graph Matching for Cell Tracking in Serial Tissue Sections
Karami, Mostafa (University of Connecticut), Nabavi, Sheida (University of Connecticut)
Object TrackingSegmentationTransformerContrastive LearningMultimodalityBiomedical Data
🎯 What it does: A novel unsupervised Bayesian Transformer combined with higher-order graph matching is proposed for cell tracking, aimed at achieving 3D tissue reconstruction in multi-channel sequential slices.
BayeSMM: Robust Deep Combined Computing Tackling Heavy-tailed Distribution in Medical Images
Liu, Yuanye (Fudan University), Zhuang, Xiahai (Fudan University)
SegmentationAnomaly DetectionConvolutional Neural NetworkMultimodalityBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A BayeSMM framework based on a Student's t-distribution mixture model is proposed for the joint registration and segmentation of multimodal medical images.
BCRNet: Enhancing Landmark Detection in Laparoscopic Liver Surgery via Bezier Curve Refinement
Li, Qian (National University of Singapore), Jin, Yueming (University of Oxford)
Object DetectionSegmentationTransformerSupervised Fine-TuningImageMultimodality
🎯 What it does: This paper proposes BCRNet, which achieves precise detection of key points in laparoscopic liver structures through Bezier curve prediction.
BenchReAD: A systematic benchmark for retinal anomaly detection
Lian, Chenyu (Hong Kong Polytechnic University), Qin, Jing (Hong Kong Polytechnic University)
Anomaly DetectionContrastive LearningImageMultimodalityBenchmark
🎯 What it does: A systematic retinal anomaly detection benchmark named BenchReAD has been established, which integrates multimodal data and conducts graded comparisons of methods, proposing an improved scheme called NFM-DRA based on normal feature memory.
Beyond Shadows: Learning Physics-inspired Ultrasound Confidence Maps from Sparse Annotations
Ronchetti, Matteo (ImFusion GmbH), Navab, Nassir (Technische Universität München)
SegmentationDomain AdaptationConvolutional Neural NetworkSupervised Fine-TuningImageBiomedical DataUltrasound
🎯 What it does: A probabilistic graphical model based on sparse 'good/bad' annotations and physical insights is proposed to train CNNs for real-time generation of confidence maps for ultrasound images.
Bias and Generalizability of Foundation Models across Datasets in Breast Mammography
Germani, Elodie (University Hospital Bonn), Albarqouni, Shadi (University Hospital Bonn)
ClassificationDomain AdaptationTransformerMixture of ExpertsVision Language ModelImageBiomedical DataMagnetic Resonance Imaging
🎯 What it does: This paper evaluates the bias and generalization ability of baseline models in breast cancer diagnosis and breast density classification tasks by collecting and aggregating mammography datasets from various regions around the world, and explores various bias mitigation and domain adaptation strategies.
BiasICL: In-Context Learning and Demographic Biases of Vision Language Models
Xu, Sonnet (Virginia Mason), Daneshjou, Roxana (Stanford University)
TransformerLarge Language ModelVision Language ModelImageTextMultimodalityMagnetic Resonance Imaging
🎯 What it does: A systematic evaluation of the impact of in-context learning (ICL) using visual language models on the predictive fairness for demographic subgroups such as race and gender in medical image diagnosis.
BiMSRec: A Progressive Image Reconstruction Framework for Medical Image Fusion Guided by Multi-Scale Deformation Fields
Long, Nuoer (Macao Polytechnic University), Sun, Yue (Jinan University)
Image TranslationRestorationImageBiomedical DataMagnetic Resonance ImagingComputed TomographyPositron Emission Tomography
🎯 What it does: This paper proposes the BiMSRec framework, which implements a hierarchical, multi-scale deformation field-based joint registration and reconstruction for multi-modal medical image fusion.
Bio2Vol: Adapting 2D Biomedical Foundation Models for Volumetric Medical Image Segmentation
Zhuang, Jiaxin (Hong Kong University of Science and Technology), Chen, Hao (Harvard Medical School)
SegmentationTransformerPrompt EngineeringBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: This work proposes the Bio2Vol framework, which transfers pre-trained 2D text-prompted foundational models (such as BiomedParse) to 3D medical image segmentation tasks, supporting volume-level text-prompted segmentation.
BioD2C: A Dual-level Semantic Consistency Constraint Framework for Biomedical VQA
Ji, Zhengyang (Shandong University), Yue, Yutao (Hong Kong University of Science and Technology (Guangzhou))
RecognitionRetrievalData-Centric LearningDrug DiscoveryTransformerLarge Language ModelVision Language ModelImageTextMultimodalityBiomedical Data
🎯 What it does: The BioD2C framework is proposed, achieving dual-layer semantic consistency constraints in biomedical visual question answering.
Bipartite Patient-Modality Graph Learning with Event-Conditional Modelling of Censoring for Cancer Survival Prediction
Yue, Hailin (Central South University), Wang, Jianxin (Institute of Guizhou Aerospace Measuring and Testing Technology)
Graph Neural NetworkMultimodalityBiomedical Data
🎯 What it does: A bipartite graph (patient-modal) was constructed and event conditional censoring modeling (ECMC) was incorporated to integrate pathological images, genomic, and clinical data to predict the survival risk of cancer patients.
BiSCoT: Behavior-Informed Subgroup-Consistent Connectome Template for Interpretable Brain Network Analysis
Chen, Zijian (Boston University), Venkataraman, Archana (Boston University)
CompressionExplainability and InterpretabilityGraph Neural NetworkAuto EncoderBiomedical DataMagnetic Resonance Imaging
🎯 What it does: A behavior information-based subgroup consistency brain network template (BISCoT) is proposed to compress the rs-fMRI connectivity matrix and extract interpretable sparse subnetworks.
Blaze3DM: Integrating Triplane Representation with Diffusion for Solving 3D Inverse Problems in Medical Imaging
He, Jia (University of Chinese Academy of Sciences), Liu, Ziwen (University of Chinese Academy of Sciences)
RestorationComputational EfficiencyDiffusion modelImageBiomedical DataMagnetic Resonance ImagingComputed Tomography
🎯 What it does: Developed the Blaze3DM model, using a three-plane neural field and diffusion model to solve 3D medical image inverse problems.