/CVPR-MIA

Papers of Medical Image Analysis on CVPR

CVPR-MIA

Recent papers about medical images published on CVPR. [Github]

To complement or correct it, please contact me at 1729766533 [at] qq [dot] com or send a pull request .

Last updated: 2024/03/21

CVPR2024

Image Reconstruction (图像重建)

  • QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction. [Paper][Code][Project]
  • Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRI. [Paper][Code]
  • Structure-Aware Sparse-View X-ray 3D Reconstruction.[Paper][Code]
  • Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI. [Paper][Code]

Image Resolution (图像超分)

  • Learning Large-Factor EM Image Super-Resolution with Generative Priors. [Paper][Code]

Image Registration (图像配准)

  • Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration. [Paper]
  • Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration. [Paper][Code]

Image Segmentation (图像分割)

  • PrPSeg: Universal Proposition Learning for Panoramic Renal Pathology Segmentation. [Paper]
  • Versatile Medical Image Segmentation Learned from Multi-Source Datasets via Model Self-Disambiguation. [Paper]
  • Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation. [Paper][Code]
  • One-Prompt to Segment All Medical Images. [Paper][Code]
  • Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention. [Paper][Code][Project]
  • Diversified and Personalized Multi-rater Medical Image Segmentation. [Paper][Code]
  • MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling. [Paper][Code]
  • Adaptive Bidirectional Displacement for Semi-Supervised Medical Image Segmentation. [Paper][Code]
  • Cross-dimension Affinity Distillation for 3D EM Neuron Segmentation. [Paper][Code]
  • ToNNO: Tomographic Reconstruction of a Neural Network’s Output for Weakly Supervised Segmentation of 3D Medical Images.[Paper][Code]
  • Versatile Medical Image Segmentation Learned from Multi-Source Datasets via Model Self-Disambiguation. [Paper][Code]
  • Teeth-SEG: An Efficient Instance Segmentation Framework for Orthodontic Treatment based on Anthropic Prior Knowledge. [Paper][Code]
  • Tyche: Stochastic in Context Learning for Universal Medical Image Segmentation. [Paper][Code]
  • Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation. [Paper][Code]
  • S2VNet: Universal Multi-Class Medical Image Segmentation via Clustering-based Slice-to-Volume Propagation. [Paper][Code]
  • EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation.[Paper][Code]
  • Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation.[Paper][Code]

Image Generation (图像生成)

  • Learned representation-guided diffusion models for large-image generation. [Paper]
  • MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariant. [Paper]
  • Towards Generalizable Tumor Synthesis. [Paper][Code]
  • Data-Efficient Unsupervised Interpolation Without Any Intermediate Frame for 4D Medical Images. [Paper][Code]

Image Classification (图像分类)

  • Systematic comparison of semi-supervised and self-supervised learning for medical image classification. [Paper][Code]
  • PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection. [Paper][Code]
  • Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images. [Paper][Code]

Federated Learning（联邦学习）

  • Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts. [Paper]

Medical Pre-training (预训练)

  • VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis. [Paper][Code]
  • MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning. [Paper]
  • Continual Self-supervised Learning: Towards Universal Multi-modal Medical Data Representation Learning. [Paper][Code]
  • Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models. [Paper][Code]
  • Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding. [Paper][Code]

Vision-Language Models (视觉-语言)

  • PairAug: What Can Augmented Image-Text Pairs Do for Radiology? [Paper][Code]
  • Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Matching Framework. [Paper][Code]
  • Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images. [Paper][Code]
  • OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM. [Paper][Code]
  • CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification. [Paper][Code]

Foundation Models (基础模型)

  • Low-Rank Knowledge Decomposition for Medical Foundation Models. [Paper][Code]

Computational Pathology (计算病理)

  • Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction. [Paper]
  • Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology. [Paper][Code]
  • PrPSeg: Universal Proposition Learning for Panoramic Renal Pathology Segmentation. [Paper]
  • ChAda-ViT: Channel Adaptive Attention for Joint Representation Learning of Heterogeneous Microscopy Images. [Paper][Code]
  • SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology. [Paper][Code]

Others

  • Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling. [Paper]
  • FocusMAE: Gallbladder Cancer Detection from Ultrasound Videos with Focused Masked Autoencoders. [Paper][Code]