mlsanityData to 7 Oct 2026

Recurrent Mask Refinement for Few-Shot Medical Image Segmentation

arXiv 2108.00622 ↗First posted 2 Aug 2021cs.CVcited by 63

Not on the map. Why?

Abstract (arXiv)

Although having achieved great success in medical image segmentation, deep convolutional neural networks usually require a large dataset with manual annotations for training and are difficult to generalize to unseen classes. Few-shot learning has the potential to address these challenges by learning new classes from only a few labeled examples. In this work, we propose a new framework for few-shot medical image segmentation based on prototypical networks. Our innovation lies in the design of two key modules: 1) a context relation encoder (CRE) that uses correlation to capture local relation features between foreground and background regions; and 2) a recurrent mask refinement module that repeatedly uses the CRE and a prototypical network to recapture the change of context relationship and refine the segmentation mask iteratively. Experiments on two abdomen CT datasets and an abdomen MRI dataset show the proposed method obtains substantial improvement over the state-of-the-art methods by an average of 16.32%, 8.45% and 6.24% in terms of DSC, respectively. Code is publicly available.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). Builds on 45 of its 71 references that are in the map. First posted on arXiv 2 Aug 2021.

Builds on

45 of 71 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  7. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  10. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  11. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  12. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 657
33 more
  1. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  2. 2017Deep Learning for Medical Image Analysiscited by 399
  3. 2017One-Shot Learning for Semantic Segmentationcited by 337
  4. 2020CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentationcited by 307
  5. 2018nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentationcited by 291
  6. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  7. 2016Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challengecited by 198
  8. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  9. 2018An Unsupervised Learning Model for Deformable Medical Image Registrationcited by 150
  10. 2019Data augmentation using learned transformations for one-shot medical image segmentationcited by 138
  11. 2015Brain Tumor Segmentation with Deep Neural Networkscited by 137
  12. 2019Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimationcited by 131
  13. 2020Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotationcited by 128
  14. 2020Deep Snake for Real-Time Instance Segmentationcited by 111
  15. 2019Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentationcited by 88
  16. 2018CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)cited by 81
  17. 2018Methods for Segmentation and Classification of Digital Microscopy Tissue Imagescited by 72
  18. 2019'Squeeze & Excite' Guided Few-Shot Segmentation of Volumetric Imagescited by 69
  19. 2018HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentationcited by 66
  20. 2019Closing the Gap between Deep and Conventional Image Registration using Probabilistic Dense Displacement Networkscited by 40
  21. 2018Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learningcited by 36
  22. 2017A deep learning model integrating FCNNs and CRFs for brain tumor segmentationcited by 35
  23. 2019Data Efficient Unsupervised Domain Adaptation for Cross-Modality Image Segmentationcited by 33
  24. 2019Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Imagescited by 28
  25. 2018Structure-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoisingcited by 22
  26. 2019NoduleNet: Decoupled False Positive Reductionfor Pulmonary Nodule Detection and Segmentationcited by 21
  27. 2020FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimationcited by 21
  28. 2017Liver lesion segmentation informed by joint liver segmentationcited by 18
  29. 2020Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentationcited by 16
  30. 2019Automatic Pulmonary Lobe Segmentation Using Deep Learningcited by 15
  31. 2019Automated pulmonary nodule detection using 3D deep convolutional neural networkscited by 7
  32. 2019An End-to-end Framework For Integrated Pulmonary Nodule Detection and False Positive Reductioncited by 5
  33. 2020AttentionAnatomy: A unified framework for whole-body organs at risk segmentation using multiple partially annotated datasetscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 16; 2023: 18; 2024: 8; 2025: 7; 2026: 8.

63 papers.

Sort:

By area:

  1. 2021Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformercited by 99
  2. 2023UniverSeg: Universal Medical Image Segmentationcited by 90
  3. 2021SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentationcited by 86
  4. 2021AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentationcited by 48
  5. 2024Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decodingcited by 48
  6. 2022Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flowcited by 38
  7. 2022Few-shot Medical Image Segmentation with Cycle-resemblance Attentioncited by 33
  8. 2023A Systematic Review of Few-Shot Learning in Medical Imagingcited by 28
  9. 2022Q-Net: Query-Informed Few-Shot Medical Image Segmentationcited by 24
  10. 2022Diffeomorphic Image Registration with Neural Velocity Fieldcited by 20
  11. 2023Few Shot Medical Image Segmentation with Cross Attention Transformercited by 19
  12. 2023Self-Sampling Meta SAM: Enhancing Few-shot Medical Image Segmentation with Meta-Learningcited by 18
38 more
  1. 2023Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentationcited by 17
  2. 2021Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learningcited by 14
  3. 2022Prototypical few-shot segmentation for cross-institution male pelvic structures with spatial registrationcited by 14
  4. 2024Prototype Correlation Matching and Class-Relation Reasoning for Few-Shot Medical Image Segmentationcited by 13
  5. 2022Recent Progress in Transformer-based Medical Image Analysiscited by 9
  6. 2023Partition-A-Medical-Image: Extracting Multiple Representative Sub-regions for Few-shot Medical Image Segmentationcited by 9
  7. 2021MEGAN: Memory Enhanced Graph Attention Network for Space-Time Video Super-Resolutioncited by 8
  8. 2025Recent Advances in Medical Imaging Segmentation: A Surveycited by 8
  9. 2022Unsupervised Visual Defect Detection with Score-Based Generative Modelcited by 7
  10. 2022Adversarially Robust Prototypical Few-shot Segmentation with Neural-ODEscited by 6
  11. 2023Data efficient deep learning for medical image analysis: A surveycited by 6
  12. 2022Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEscited by 5
  13. 2023Dense Affinity Matching for Few-Shot Segmentationcited by 5
  14. 2024SegICL: A Multimodal In-context Learning Framework for Enhanced Segmentation in Medical Imagingcited by 5
  15. 2022Enhancing Few-shot Image Classification with Cosine Transformercited by 4
  16. 2024Segmentation by registration-enabled SAM prompt engineering using five reference imagescited by 4
  17. 2025Rethinking Few-Shot Medical Image Segmentation by SAM2: A Training-Free Framework with Augmentative Prompting and Dynamic Matchingcited by 4
  18. 2023Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentationcited by 3
  19. 2024Few-Shot Learning for Annotation-Efficient Nucleus Instance Segmentationcited by 3
  20. 2022Exemplar Learning for Medical Image Segmentationcited by 2
  21. 2022CM-MLP: Cascade Multi-scale MLP with Axial Context Relation Encoder for Edge Segmentation of Medical Imagecited by 2
  22. 2023Meta-hallucinator: Towards Few-Shot Cross-Modality Cardiac Image Segmentationcited by 2
  23. 2023VesselShot: Few-shot learning for cerebral blood vessel segmentationcited by 2
  24. 2024Few-Shot 3D Volumetric Segmentation with Multi-Surrogate Fusioncited by 2
  25. 2021One-shot Weakly-Supervised Segmentation in Medical Imagescited by 1
  26. 2022Few-Shot Meta Learning for Recognizing Facial Phenotypes of Genetic Disorderscited by 1
  27. 2023Regional Deep Atrophy: a Self-Supervised Learning Method to Automatically Identify Regions Associated With Alzheimer's Disease Progression From Longitudinal MRIcited by 1
  28. 2023RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinementcited by 1
  29. 2024Adaptive Prompt Learning with SAM for Few-shot Scanning Probe Microscope Image Segmentationcited by 1
  30. 2025Contrastive Graph Modeling for Cross-Domain Few-Shot Medical Image Segmentationcited by 1
  31. 2026Focus on Background: Exploring SAM's Potential in Few-shot Medical Image Segmentation with Background-centric Promptingcited by 1
  32. 2026DyABD: The Abdominal Muscle Segmentation in Dynamic MRI Benchmarkcited by 1
  33. 2022TransFiner: A Full-Scale Refinement Approach for Multiple Object Trackingcited by 0
  34. 2022Coarse Retinal Lesion Annotations Refinement via Prototypical Learningcited by 0
  35. 2022Few-Shot Segmentation via Rich Prototype Generation and Recurrent Prediction Enhancementcited by 0
  36. 2023Few-shot Medical Image Segmentation via Cross-Reference Transformercited by 0
  37. 2023EqGAN: Feature Equalization Fusion for Few-shot Image Generationcited by 0
  38. 2023AdLER: Adversarial Training with Label Error Rectification for One-Shot Medical Image Segmentationcited by 0

50 most cited of 63 All 63 (JSON)