医学影像论文趋势 2023–2026

主要结论

• 医学影像论文从 2023 年的 45 篇增长到 2026 年的 132 篇，三年间扩大到约 2.9 倍。
• CVPR 是发医学影像论文最多的会议，2023–2026 年共 149 篇，占四个会议总量的 43%。
• 交叉方向里涨得最快的是驾驶仿真：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 13 篇。
• 在「健康与生命科学」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的临床 NLP是 3.2 倍，医学影像是 2.9 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI Evaluations
• ICML 2026Bayesian model selection and misspecification testing in imaging inverse problems only from noisy and partial measurements
• ICLR 2026COMPASS: Robust Feature Conformal Prediction for Medical Segmentation Metrics
• CVPR 2026CG-Reasoner Centroid-Guided Positional Reasoning Segmentation for Medical Imaging with a
• NeurIPS 2025Adaptive Latent-Space Constraints in Personalized Federated Learning
• ICML 2025TinyMIG: Transferring Generalization from Vision Foundation Models to Single-Domain Medical Imaging
• ICLR 2025Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging
• CVPR 2025Active Hyperspectral Imaging Using an Event Camera
• NeurIPS 2024CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
• ICML 2024Auto-Linear Phenomenon in Subsurface Imaging
• ICLR 2024FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
• CVPR 2024Data-Efficient Unsupervised Interpolation Without Any Intermediate Frame for 4D Medical Images
• NeurIPS 2023A case for reframing automated medical image classification as segmentation
• ICML 2023A Conditional Normalizing Flow for Accelerated Multi-Coil MR Imaging
• ICLR 20233D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation
• CVPR 2023A Unified HDR Imaging Method With Pixel and Patch Level
• NeurIPS 2026Coherent Hierarchical Multi-Label Learning to Defer for Medical Imaging
• ICML 2026Spatially-Adaptive Gradient Re-parameterization for 3D Large Kernel Optimization
• ICLR 2026MedGMAE: Gaussian Masked Autoencoders for Medical Volumetric Representation Learning
• CVPR 2026Coded-E2LF Coded Aperture Light Field Imaging from Events

全部医学影像论文

共 98 篇，第 2 / 2 页

51. ICML 2025iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detection
52. ICML 2025LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation
53. ICML 2025Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing
54. ICML 2025Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation Models
55. ICML 2025Stochastic Deep Restoration Priors for Imaging Inverse Problems
56. ICML 2025TinyMIG: Transferring Generalization from Vision Foundation Models to Single-Domain Medical Imaging
57. NeurIPS 2025Adaptive Latent-Space Constraints in Personalized Federated Learning
58. NeurIPS 2025Adversarial generalization of unfolding (model-based) networks
59. NeurIPS 2025Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process
60. NeurIPS 2025AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretation
61. NeurIPS 2025Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging
62. NeurIPS 2025Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search
63. NeurIPS 2025D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction
64. NeurIPS 2025DIsoN: Decentralized Isolation Networks for Out-of-Distribution Detection in Medical Imaging
65. NeurIPS 2025DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?
66. NeurIPS 2025Dual-Comb Ghost Imaging with Transformer-Based Reconstruction for Optical Fiber Endomicroscopy
67. NeurIPS 2025ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models
68. NeurIPS 2025Fast MRI for All: Bridging Access Gaps by Training without Raw Data
69. NeurIPS 2025From Human Attention to Diagnosis: Semantic Patch-Level Integration of Vision-Language Models in Medical Imaging
70. NeurIPS 2025From Pretraining to Pathology: How Noise Leads to Catastrophic Inheritance in Medical Models
71. NeurIPS 2025Gate to the Vessel: Residual Experts Restore What SAM Overlooks
72. NeurIPS 2025High Dynamic Range Imaging with Time-Encoding Spike Camera
73. NeurIPS 2025Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing
74. NeurIPS 2025Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Imaging Inverse Problems
75. NeurIPS 2025Learning to Zoom with Anatomical Relations for Medical Structure Detection
76. NeurIPS 2025Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation
77. NeurIPS 2025MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation
78. NeurIPS 2025MedicalNarratives: Connecting Medical Vision and Language with Localized Narratives
79. NeurIPS 2025Non-Line-of-Sight 3D Reconstruction with Radar
80. NeurIPS 2025NOVA: A Benchmark for Rare Anomaly Localization and Clinical Reasoning in Brain MRI
81. NeurIPS 2025NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems
82. NeurIPS 2025OCTDiff: Bridged Diffusion Model for Portable OCT Super-Resolution and Enhancement
83. NeurIPS 2025Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies
84. NeurIPS 2025Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains
85. NeurIPS 2025RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis
86. NeurIPS 2025Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2
87. NeurIPS 2025Segment Anything Model Meets Semi-supervised Medical Image Segmentation: A Novel Perspective
88. NeurIPS 2025Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation
89. NeurIPS 2025SHF: Symmetrical Hierarchical Forest with Pretrained Vision Transformer Encoder for High-Resolution Medical Segmentation
90. NeurIPS 2025SMMILE: An expert-driven benchmark for multimodal medical in-context learning
91. NeurIPS 2025Spectral Compressive Imaging via Chromaticity-Intensity Decomposition
92. NeurIPS 2025The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective
93. NeurIPS 2025Time-Embedded Algorithm Unrolling for Computational MRI
94. NeurIPS 2025Toward a Vision-Language Foundation Model for Medical Data: Multimodal Dataset and Benchmarks for Vietnamese PET/CT Report Generation
95. NeurIPS 2025Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysis
96. NeurIPS 2025Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal Transport
97. NeurIPS 2025UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights
98. NeurIPS 2025Whitened Score Diffusion: A Structured Prior for Imaging Inverse Problems

常见问题

2023–2026 年四大会议一共有多少篇医学影像论文？

共 346 篇，按年份分别是 2023 年 45 篇、2024 年 71 篇、2025 年 98 篇、2026 年 132 篇。

NeurIPS 2026 有多少篇医学影像论文？

NeurIPS 2026 有 39 篇医学影像论文，上一届是 42 篇。

ICLR 2026 有多少篇医学影像论文？

ICLR 2026 有 27 篇医学影像论文，上一届是 10 篇。

ICML 2026 有多少篇医学影像论文？

ICML 2026 有 11 篇医学影像论文，上一届是 8 篇。

CVPR 2026 有多少篇医学影像论文？

CVPR 2026 有 55 篇医学影像论文，上一届是 38 篇。

哪个会议的医学影像论文最多？

CVPR，2023–2026 年共 149 篇。