Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
149 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

ASLseg: Adapting SAM in the Loop for Semi-supervised Liver Tumor Segmentation (2312.07969v2)

Published 13 Dec 2023 in cs.CV

Abstract: Liver tumor segmentation is essential for computer-aided diagnosis, surgical planning, and prognosis evaluation. However, obtaining and maintaining a large-scale dataset with dense annotations is challenging. Semi-Supervised Learning (SSL) is a common technique to address these challenges. Recently, Segment Anything Model (SAM) has shown promising performance in some medical image segmentation tasks, but it performs poorly for liver tumor segmentation. In this paper, we propose a novel semi-supervised framework, named ASLseg, which can effectively adapt the SAM to the SSL setting and combine both domain-specific and general knowledge of liver tumors. Specifically, the segmentation model trained with a specific SSL paradigm provides the generated pseudo-labels as prompts to the fine-tuned SAM. An adaptation network is then used to refine the SAM-predictions and generate higher-quality pseudo-labels. Finally, the reliable pseudo-labels are selected to expand the labeled set for iterative training. Extensive experiments on the LiTS dataset demonstrate overwhelming performance of our ASLseg.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (21)
  1. Yue Zhang et al., “Deep learning and unsupervised fuzzy c-means based level-set segmentation for liver tumor,” in International Symposium on Biomedical Imaging (ISBI). IEEE, 2020, pp. 1193–1196.
  2. Li Lin et al., “Yolocurvseg: You only label one noisy skeleton for vessel-style curvilinear structure segmentation,” Medical Image Analysis (MedIA), vol. 90, pp. 102937, 2023.
  3. Yijin Huang et al., “Lesion-based contrastive learning for diabetic retinopathy grading from fundus images,” in International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer, 2021, pp. 113–123.
  4. Bilic et al., “The liver tumor segmentation benchmark (lits),” Medical Image Analysis (MedIA), vol. 84, pp. 102680, 2023.
  5. Dong Wang et al., “Focalmix: Semi-supervised learning for 3d medical image detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 3951–3960.
  6. Xiangde Luo et al., “Efficient semi-supervised gross target volume of nasopharyngeal carcinoma segmentation via uncertainty rectified pyramid consistency,” in International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer, 2021, pp. 318–329.
  7. Simon Reiß et al., “Every annotation counts: Multi-label deep supervision for medical image segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 9532–9542.
  8. Xiaokang Chen et al., “Semi-supervised semantic segmentation with cross pseudo supervision,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 2613–2622.
  9. Kirillov et al., “Segment anything,” arXiv preprint arXiv:2304.02643, 2023.
  10. Junlong Cheng et al., “Sam-med2d,” arXiv preprint arXiv:2308.16184, 2023.
  11. Jun Ma and Bo Wang, “Segment anything in medical images,” arXiv preprint arXiv:2304.12306, 2023.
  12. Junde Wu et al., “Medical sam adapter: Adapting segment anything model for medical image segmentation,” arXiv preprint arXiv:2304.12620, 2023.
  13. Lijun Wu et al., “R-drop: Regularized dropout for neural networks,” Advances in Neural Information Processing Systems (NeurIPS), vol. 34, pp. 10890–10905, 2021.
  14. “U-net: Convolutional networks for biomedical image segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer, 2015, pp. 234–241.
  15. Fabian Isensee et al., “nnu-net: a self-configuring method for deep learning-based biomedical image segmentation,” Nature methods, vol. 18, no. 2, pp. 203–211, 2021.
  16. “Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results,” Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017.
  17. Lequan Yu et al., “Uncertainty-aware self-ensembling model for semi-supervised 3d left atrium segmentation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer, 2019, pp. 605–613.
  18. Siyuan Qiao et al., “Deep co-training for semi-supervised image recognition,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 135–152.
  19. “Semi-supervised semantic segmentation with cross-consistency training,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 12674–12684.
  20. Tuan-Hung Vu et al., “Advent: Adversarial entropy minimization for domain adaptation in semantic segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 2517–2526.
  21. Verma et al., “Interpolation consistency training for semi-supervised learning,” Neural Networks, vol. 145, pp. 90–106, 2022.
Citations (3)
View on Semantic Scholar

Summary

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

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