Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
194 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Predictive Accuracy-Based Active Learning for Medical Image Segmentation (2405.00452v2)

Published 1 May 2024 in cs.CV

Abstract: Active learning is considered a viable solution to alleviate the contradiction between the high dependency of deep learning-based segmentation methods on annotated data and the expensive pixel-level annotation cost of medical images. However, most existing methods suffer from unreliable uncertainty assessment and the struggle to balance diversity and informativeness, leading to poor performance in segmentation tasks. In response, we propose an efficient Predictive Accuracy-based Active Learning (PAAL) method for medical image segmentation, first introducing predictive accuracy to define uncertainty. Specifically, PAAL mainly consists of an Accuracy Predictor (AP) and a Weighted Polling Strategy (WPS). The former is an attached learnable module that can accurately predict the segmentation accuracy of unlabeled samples relative to the target model with the predicted posterior probability. The latter provides an efficient hybrid querying scheme by combining predicted accuracy and feature representation, aiming to ensure the uncertainty and diversity of the acquired samples. Extensive experiment results on multiple datasets demonstrate the superiority of PAAL. PAAL achieves comparable accuracy to fully annotated data while reducing annotation costs by approximately 50% to 80%, showcasing significant potential in clinical applications. The code is available at https://github.com/shijun18/PAAL-MedSeg.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. The medical segmentation decathlon. Nature communications, 13(1):4128, 2022.
  2. Deep batch active learning by diverse, uncertain gradient lower bounds. In International Conference on Learning Representations, 2019.
  3. The power of ensembles for active learning in image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 9368–9377, 2018.
  4. Deep learning techniques for automatic mri cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE transactions on medical imaging, 37(11):2514–2525, 2018.
  5. Cost-effective active learning for melanoma segmentation. In 31st Conference on Machine Learning for Health: Workshop at NIPS 2017 (ML4H 2017), pages 1–5, 2017.
  6. Active learning with clustering. In Active Learning and Experimental Design workshop In conjunction with AISTATS 2010, pages 127–139. JMLR Workshop and Conference Proceedings, 2011.
  7. Klaus Brinker. Incorporating diversity in active learning with support vector machines. In Proceedings of the 20th international conference on machine learning (ICML-03), pages 59–66, 2003.
  8. Revisiting superpixels for active learning in semantic segmentation with realistic annotation costs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10988–10997, 2021.
  9. Interactive few-shot learning: Limited supervision, better medical image segmentation. IEEE Transactions on Medical Imaging, 40(10):2575–2588, 2021.
  10. Deep bayesian active learning with image data. In International conference on machine learning, pages 1183–1192. PMLR, 2017.
  11. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  12. Learning with limited annotations: a survey on deep semi-supervised learning for medical image segmentation. Computers in Biology and Medicine, page 107840, 2023.
  13. Multi-class active learning for image classification. In 2009 ieee conference on computer vision and pattern recognition, pages 2372–2379. IEEE, 2009.
  14. Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pages 1–9, 2016.
  15. What uncertainties do we need in bayesian deep learning for computer vision? Advances in neural information processing systems, 30, 2017.
  16. Active learning in brain tumor segmentation with uncertainty sampling, annotation redundancy restriction, and data initialization. arXiv preprint arXiv:2302.10185, 2023.
  17. Segthor: Segmentation of thoracic organs at risk in ct images. In 2020 Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA), pages 1–6. IEEE, 2020.
  18. Adaptive active learning for image classification. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 859–866, 2013.
  19. Attention, suggestion and annotation: a deep active learning framework for biomedical image segmentation. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part I 23, pages 3–13. Springer, 2020.
  20. Sgdr: Stochastic gradient descent with warm restarts. In International Conference on Learning Representations, 2016.
  21. Decoupled weight decay regularization. In International Conference on Learning Representations, 2018.
  22. A survey of deep active learning. ACM computing surveys (CSUR), 54(9):1–40, 2021.
  23. Biosegment: Active learning segmentation for 3d electron microscopy imaging. 2022.
  24. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pages 234–241. Springer, 2015.
  25. Medical image analysis with semantic segmentation and active learning. Studia Universitatis Babeș-Bolyai Informatica, 64(1):26–38, 2019.
  26. Active learning with bayesian unet for efficient semantic image segmentation. Journal of Imaging, 7(2):37, 2021.
  27. Active learning for convolutional neural networks: A core-set approach. In International Conference on Learning Representations, 2018.
  28. Rethinking automatic segmentation of gross target volume from a decoupling perspective. Computerized Medical Imaging and Graphics, page 102323, 2023.
  29. Deep active learning: Unified and principled method for query and training. In International Conference on Artificial Intelligence and Statistics, pages 1308–1318. PMLR, 2020.
  30. A review on deep learning in medical image analysis. International Journal of Multimedia Information Retrieval, 11(1):19–38, 2022.
  31. Dan Wang and Yi Shang. A new active labeling method for deep learning. In 2014 International joint conference on neural networks (IJCNN), pages 112–119. IEEE, 2014.
  32. Suggestive annotation: A deep active learning framework for biomedical image segmentation. In Medical Image Computing and Computer Assisted Intervention- MICCAI 2017: 20th International Conference, Quebec City, QC, Canada, September 11-13, 2017, Proceedings, Part III 20, pages 399–407. Springer, 2017.
  33. Deep similarity-based batch mode active learning with exploration-exploitation. In 2017 IEEE International Conference on Data Mining (ICDM), pages 575–584. IEEE, 2017.
  34. Learning loss for active learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 93–102, 2019.
  35. Netzer Yuval. Reading digits in natural images with unsupervised feature learning. In Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2011.
  36. A comparative survey of deep active learning. arXiv preprint arXiv:2203.13450, 2022.
  37. Dive into the details of self-supervised learning for medical image analysis. Medical Image Analysis, 89:102879, 2023.
  38. Dsal: Deeply supervised active learning from strong and weak labelers for biomedical image segmentation. IEEE journal of biomedical and health informatics, 25(10):3744–3751, 2021.
  39. Fine-tuning convolutional neural networks for biomedical image analysis: actively and incrementally. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7340–7351, 2017.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets