Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Thyroid ultrasound diagnosis improvement via multi-view self-supervised learning and two-stage pre-training (2402.11497v1)

Published 18 Feb 2024 in cs.CV

Abstract: Thyroid nodule classification and segmentation in ultrasound images are crucial for computer-aided diagnosis; however, they face limitations owing to insufficient labeled data. In this study, we proposed a multi-view contrastive self-supervised method to improve thyroid nodule classification and segmentation performance with limited manual labels. Our method aligns the transverse and longitudinal views of the same nodule, thereby enabling the model to focus more on the nodule area. We designed an adaptive loss function that eliminates the limitations of the paired data. Additionally, we adopted a two-stage pre-training to exploit the pre-training on ImageNet and thyroid ultrasound images. Extensive experiments were conducted on a large-scale dataset collected from multiple centers. The results showed that the proposed method significantly improves nodule classification and segmentation performance with limited manual labels and outperforms state-of-the-art self-supervised methods. The two-stage pre-training also significantly exceeded ImageNet pre-training.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (58)
  1. Big self-supervised models advance medical image classification, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3478–3488.
  2. Unsupervised contrastive learning of image representations from ultrasound videos with hard negative mining, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part IV, Springer. pp. 423–433.
  3. Seer cancer stat facts thyroid cancer. National Cancer Institute.[(accessed on 10 May 2021)] .
  4. A review of thyroid gland segmentation and thyroid nodule segmentation methods for medical ultrasound images. Computer methods and programs in biomedicine 185, 105329.
  5. Self-supervised learning for medical image analysis using image context restoration. Medical image analysis 58, 101539.
  6. A simple framework for contrastive learning of visual representations, in: International conference on machine learning, PMLR. pp. 1597–1607.
  7. Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 .
  8. MMSelfSup: Openmmlab self-supervised learning toolbox and benchmark. https://github.com/open-mmlab/mmselfsup.
  9. Automatic classification of thyroid nodules in ultrasound images using a multi-task attention network guided by clinical knowledge. Computers in Biology and Medicine 150, 106172.
  10. Unsupervised visual representation learning by context prediction, in: Proceedings of the IEEE international conference on computer vision, pp. 1422–1430.
  11. Self-supervised multimodal domino: in search of biomarkers for alzheimer’s disease, in: 2021 IEEE 9th International Conference on Healthcare Informatics (ICHI), IEEE. pp. 23–30.
  12. On self-supervised multimodal representation learning: an application to alzheimer’s disease, in: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), IEEE. pp. 1548–1552.
  13. Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728 .
  14. Thyroid region prior guided attention for ultrasound segmentation of thyroid nodules. Computers in Biology and Medicine 155, 106389.
  15. Dira: discriminative, restorative, and adversarial learning for self-supervised medical image analysis, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 20824–20834.
  16. Contrastive multi-view representation learning on graphs, in: International conference on machine learning, PMLR. pp. 4116–4126.
  17. Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000–16009.
  18. Momentum contrast for unsupervised visual representation learning, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 9729–9738.
  19. Deep residual learning for image recognition, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770–778.
  20. Self-supervised multimodal reconstruction pre-training for retinal computer-aided diagnosis. Expert Systems with Applications 185, 115598.
  21. Self-supervised multimodal reconstruction of retinal images over paired datasets. Expert Systems with Applications 161, 113674.
  22. Personalized diagnostic tool for thyroid cancer classification using multi-view ultrasound, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part III, Springer. pp. 665–674.
  23. Thyroid nodule segmentation and classification in ultrasound images through intra-and inter-task consistent learning. Medical image analysis 79, 102443.
  24. Emotion-aware multi-view contrastive learning for facial emotion recognition, in: European Conference on Computer Vision, Springer. pp. 178–195.
  25. Similarity of neural network representations revisited, in: International Conference on Machine Learning, PMLR. pp. 3519–3529.
  26. Self-supervised feature learning via exploiting multi-modal data for retinal disease diagnosis. IEEE Transactions on Medical Imaging 39, 4023–4033.
  27. A survey of multi-view representation learning. IEEE transactions on knowledge and data engineering 31, 1863–1883.
  28. Covid-19 lung infection segmentation with a novel two-stage cross-domain transfer learning framework. Medical image analysis 74, 102205.
  29. Tl-med: A two-stage transfer learning recognition model for medical images of covid-19. Biocybernetics and Biomedical Engineering 42, 842–855.
  30. What is being transferred in transfer learning? Advances in neural information processing systems 33, 512–523.
  31. Unsupervised learning of visual representations by solving jigsaw puzzles, in: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VI, Springer. pp. 69–84.
  32. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 .
  33. Context encoders: Feature learning by inpainting, in: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2536–2544.
  34. Bt-unet: A self-supervised learning framework for biomedical image segmentation using barlow twins with u-net models. Machine Learning , 1–16.
  35. Transfusion: Understanding transfer learning for medical imaging. Advances in neural information processing systems 32.
  36. 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, Springer. pp. 234–241.
  37. Self-supervised contrastive learning of multi-view facial expressions, in: Proceedings of the 2021 International Conference on Multimodal Interaction, pp. 253–257.
  38. Multi-view action recognition using contrastive learning, in: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 3381–3391.
  39. Deep learning on ultrasound images of thyroid nodules. Biocybernetics and Biomedical Engineering 41, 636–655.
  40. Self-supervised learning methods and applications in medical imaging analysis: A survey. PeerJ Computer Science 8, e1045.
  41. Use of diagnostic imaging studies and associated radiation exposure for patients enrolled in large integrated health care systems, 1996-2010. Jama 307, 2400–2409.
  42. Classification for thyroid nodule using vit with contrastive learning in ultrasound images. Computers in Biology and Medicine 152, 106444.
  43. Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: a cancer journal for clinicians 71, 209–249.
  44. Caid: Context-aware instance discrimination for self-supervised learning in medical imaging, in: International Conference on Medical Imaging with Deep Learning, PMLR. pp. 535–551.
  45. Convolutional neural networks for medical image analysis: Full training or fine tuning? IEEE transactions on medical imaging 35, 1299–1312.
  46. Self-supervised learning for medical images by solving multimodal jigsaw puzzles. Ieee Transactions on Medical Imaging 12729, 661–673.
  47. Can we adopt self-supervised pretraining for chest x-rays? arXiv preprint arXiv:2211.12931 .
  48. Auto-weighting for breast cancer classification in multimodal ultrasound, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part VI 23, Springer. pp. 190–199.
  49. Multi-view multi-behavior contrastive learning in recommendation, in: International Conference on Database Systems for Advanced Applications, Springer. pp. 166–182.
  50. Self-supervised multi-modal fusion network for multi-modal thyroid ultrasound image diagnosis. Computers in Biology and Medicine 150, 106164.
  51. A two-stage deep transfer learning model and its application for medical image processing in traditional chinese medicine. Knowledge-Based Systems 239, 108060.
  52. Bi-rads classification of calcification on mammograms, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part VII 24, Springer. pp. 119–128.
  53. Preservational learning improves self-supervised medical image models by reconstructing diverse contexts, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3499–3509.
  54. Comparing to learn: Surpassing imagenet pretraining on radiographs by comparing image representations, in: Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part I 23, Springer. pp. 398–407.
  55. Multi-task learning for segmentation and classification of tumors in 3d automated breast ultrasound images. Medical Image Analysis 70, 101918.
  56. Models genesis. Medical image analysis 67, 101840.
  57. Rubik’s cube+: A self-supervised feature learning framework for 3d medical image analysis. Medical image analysis 64, 101746.
  58. Unpaired image-to-image translation using cycle-consistent adversarial networks, in: Proceedings of the IEEE international conference on computer vision, pp. 2223–2232.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (12)
  1. Jian Wang (969 papers)
  2. Xin Yang (320 papers)
  3. Xiaohong Jia (12 papers)
  4. Wufeng Xue (23 papers)
  5. Rusi Chen (6 papers)
  6. Yanlin Chen (20 papers)
  7. Xiliang Zhu (7 papers)
  8. Lian Liu (26 papers)
  9. Yan Cao (50 papers)
  10. Jianqiao Zhou (6 papers)
  11. Dong Ni (94 papers)
  12. Ning Gu (40 papers)
Citations (2)
View on Semantic Scholar

Summary

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

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