mlsanityData to 7 Oct 2026

CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision

arXiv 2203.01475 ↗First posted 3 Mar 2022eess.IV cs.CVcited by 64

Not on the map. Why?

Abstract (arXiv)

Curating a large set of fully annotated training data can be costly, especially for the tasks of medical image segmentation. Scribble, a weaker form of annotation, is more obtainable in practice, but training segmentation models from limited supervision of scribbles is still challenging. To address the difficulties, we propose a new framework for scribble learning-based medical image segmentation, which is composed of mix augmentation and cycle consistency and thus is referred to as CycleMix. For augmentation of supervision, CycleMix adopts the mixup strategy with a dedicated design of random occlusion, to perform increments and decrements of scribbles. For regularization of supervision, CycleMix intensifies the training objective with consistency losses to penalize inconsistent segmentation, which results in significant improvement of segmentation performance. Results on two open datasets, i.e., ACDC and MSCMRseg, showed that the proposed method achieved exhilarating performance, demonstrating comparable or even better accuracy than the fully-supervised methods. The code and expert-made scribble annotations for MSCMRseg are publicly available at https://github.com/BWGZK/CycleMix.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). Builds on 31 of its 41 references that are in the map. First posted on arXiv 3 Mar 2022.

Builds on

31 of 41 references.

References · 31

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  8. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  9. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  10. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 375
  11. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  12. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 260
19 more
  1. 2019Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentationcited by 258
  2. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 226
  3. 2015Conditional Random Fields as Recurrent Neural Networkscited by 213
  4. 2019Semi-Supervised Semantic Segmentation with High- and Low-level Consistencycited by 147
  5. 2016Multivariate mixture model for myocardium segmentation combining multi-source imagescited by 133
  6. 2021Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversitycited by 127
  7. 2018On Regularized Losses for Weakly-supervised CNN Segmentationcited by 121
  8. 2018Normalized Cut Loss for Weakly-supervised CNN Segmentationcited by 112
  9. 2015Constrained Convolutional Neural Networks for Weakly Supervised Segmentationcited by 100
  10. 2015STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentationcited by 78
  11. 2020FocalMix: Semi-Supervised Learning for 3D Medical Image Detectioncited by 52
  12. 2018Learning to Segment Medical Images with Scribble-Supervision Alonecited by 48
  13. 2019Semi-Supervised and Task-Driven Data Augmentationcited by 40
  14. 2020Post-DAE: Anatomically Plausible Segmentation via Post-Processing with Denoising Autoencoderscited by 38
  15. 2017An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentationcited by 36
  16. 2019Scribble-based Hierarchical Weakly Supervised Learning for Brain Tumor Segmentationcited by 32
  17. 2019Cardiac Segmentation from LGE MRI Using Deep Neural Network Incorporating Shape and Spatial Priorscited by 27
  18. 2018Recurrent neural networks for aortic image sequence segmentation with sparse annotationscited by 25
  19. 2020ACCL: Adversarial constrained-CNN loss for weakly supervised medical image segmentationcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 13; 2024: 27; 2025: 14; 2026: 7.

64 papers.

Sort:

By area:

  1. 2022Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentationcited by 74
  2. 2025nnInteractive: Redefining 3D Promptable Segmentationcited by 39
  3. 2024ScribFormer: Transformer Makes CNN Work Better for Scribble-based Medical Image Segmentationcited by 24
  4. 2023ScribbleVC: Scribble-supervised Medical Image Segmentation with Vision-Class Embeddingcited by 23
  5. 2023Towards Segment Anything Model (SAM) for Medical Image Segmentation: A Surveycited by 21
  6. 2024A Survey on Mixup Augmentations and Beyondcited by 18
  7. 2022Scribble2D5: Weakly-Supervised Volumetric Image Segmentation via Scribble Annotationscited by 15
  8. 2023S2ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-supervised Polyp Segmentationcited by 15
  9. 2023Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directionscited by 14
  10. 2024MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidancecited by 11
  11. 2022Non-Iterative Scribble-Supervised Learning with Pacing Pseudo-Masks for Medical Image Segmentationcited by 9
  12. 2023Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Datacited by 9
38 more
  1. 2023ZScribbleSeg: Zen and the Art of Scribble Supervised Medical Image Segmentationcited by 8
  2. 2023Scribble-based 3D Multiple Abdominal Organ Segmentation via Triple-branch Multi-dilated Network with Pixel- and Class-wise Consistencycited by 7
  3. 2024Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentationcited by 7
  4. 2023Data efficient deep learning for medical image analysis: A surveycited by 6
  5. 20232D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentationcited by 6
  6. 2024FedLPPA: Learning Personalized Prompt and Aggregation for Federated Weakly-supervised Medical Image Segmentationcited by 6
  7. 2024LNQ 2023 challenge: Benchmark of weakly-supervised techniques for mediastinal lymph node quantificationcited by 6
  8. 2025From Gaze to Insight: Bridging Human Visual Attention and Vision Language Model Explanation for Weakly-Supervised Medical Image Segmentationcited by 5
  9. 2024Beyond Pixel-Wise Supervision for Medical Image Segmentation: From Traditional Models to Foundation Modelscited by 4
  10. 2024ProCNS: Progressive Prototype Calibration and Noise Suppression for Weakly-Supervised Medical Image Segmentationcited by 3
  11. 20243D Vascular Segmentation Supervised by 2D Annotation of Maximum Intensity Projectioncited by 3
  12. 2024PCLMix: Weakly Supervised Medical Image Segmentation via Pixel-Level Contrastive Learning and Dynamic Mix Augmentationcited by 3
  13. 2024ModelMix: A New Model-Mixup Strategy to Minimize Vicinal Risk across Tasks for Few-scribble based Cardiac Segmentationcited by 3
  14. 2024From Few to More: Scribble-based Medical Image Segmentation via Masked Context Modeling and Continuous Pseudo Labelscited by 3
  15. 2024SA-MixNet: Structure-aware Mixup and Invariance Learning for Scribble-supervised Road Extraction in Remote Sensing Imagescited by 2
  16. 2024HAGAN: Hybrid Augmented Generative Adversarial Network for Medical Image Synthesiscited by 2
  17. 2024A Point-Neighborhood Learning Framework for Nasal Endoscope Image Segmentationcited by 2
  18. 2024Segment Anything Model for automated image data annotation: empirical studies using text prompts from Grounding DINOcited by 2
  19. 2024ScribbleVS: Scribble-Supervised Medical Image Segmentation via Dynamic Competitive Pseudo Label Selectioncited by 2
  20. 2025SparseMamba-PCL: Scribble-Supervised Medical Image Segmentation via SAM-Guided Progressive Collaborative Learningcited by 2
  21. 2025Adaptive Frequency Domain Alignment Network for Medical image segmentationcited by 2
  22. 2023Volumetric Medical Image Segmentation via Scribble Annotations and Shape Priorscited by 1
  23. 2024Revisiting 3D Medical Scribble Supervision: Benchmarking Beyond Cardiac Segmentationcited by 1
  24. 2024Weakly-Supervised Learning via Multi-Lateral Decoder Branching for Tool Segmentation in Robot-Assisted Cardiovascular Catheterizationcited by 1
  25. 2024ToNNO: Tomographic Reconstruction of a Neural Network's Output for Weakly Supervised Segmentation of 3D Medical Imagescited by 1
  26. 2024DuEDL: Dual-Branch Evidential Deep Learning for Scribble-Supervised Medical Image Segmentationcited by 1
  27. 2024MambaEviScrib: Mamba and Evidence-Guided Consistency Enhance CNN Robustness for Scribble-Based Weakly Supervised Ultrasound Image Segmentationcited by 1
  28. 2025EAUWSeg: Eliminating annotation uncertainty in weakly-supervised medical image segmentationcited by 1
  29. 2025MedCL: Learning Consistent Anatomy Distribution for Scribble-supervised Medical Image Segmentationcited by 1
  30. 2023Efficient Subclass Segmentation in Medical Imagescited by 0
  31. 2023Clean Label Disentangling for Medical Image Segmentation with Noisy Labelscited by 0
  32. 2023AttenScribble: Attentive Similarity Learning for Scribble-Supervised Medical Image Segmentationcited by 0
  33. 2024Skeleton Supervised Airway Segmentationcited by 0
  34. 2024Task-Specific Adaptation of Segmentation Foundation Model via Prompt Learningcited by 0
  35. 2024Rethinking Barely-Supervised Volumetric Medical Image Segmentation from an Unsupervised Domain Adaptation Perspectivecited by 0
  36. 2024Size Aware Cross-shape Scribble Supervision for Medical Image Segmentationcited by 0
  37. 2024SP 3 : Superpixel-propagated pseudo-label learning for weakly semi-supervised medical image segmentationcited by 0
  38. 2025Multi-Disease-Aware Training Strategy for Cardiac MR Image Segmentationcited by 0

50 most cited of 64 All 64 (JSON)