Abstract
Most deep neural networks (DNNs) based ultrasound (US) medical image analysis models use pretrained backbones (e.g., ImageNet) for better model generalization. However, the domain gap between natural and medical images causes an inevitable performance bottleneck. To alleviate this problem, an US dataset named US-4 is constructed for direct pretraining on the same domain. It contains over 23,000 images from four US video sub-datasets. To learn robust features from US-4, we propose an US semi-supervised contrastive learning method, named USCL, for pretraining. In order to avoid high similarities between negative pairs as well as mine abundant visual features from limited US videos, USCL adopts a sample pair generation method to enrich the feature involved in a single step of contrastive optimization. Extensive experiments on several downstream tasks show the superiority of USCL pretraining against ImageNet pretraining and other state-of-the-art (SOTA) pretraining approaches. In particular, USCL pretrained backbone achieves fine-tuning accuracy of over 94% on POCUS dataset, which is 10% higher than 84% of the ImageNet pretrained model. The source codes of this work are available at https://github.com/983632847/USCL.
Y. Chen and C. Zhang—Contributed equally. This work was done at Shenzhen Research Institute of Big Data (SRIBD).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
For more details of PPG module, see the Supplementary Material Sect. 2.
References
Butterfly videos. https://www.butterflynetwork.com/index.html. Accessed 20 Sept 2020
Born, J., et al.: Accelerating detection of lung pathologies with explainable ultrasound image analysis. Appl. Sci. 11(2), 672 (2021)
Celebi, M. Emre., Aydin, Kemal (eds.): Unsupervised Learning Algorithms. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-24211-8
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. arXiv:2002.05709 (2020)
Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv:2003.04297 (2020)
Gao, L., et al.: Multi-modal active learning for automatic liver fibrosis diagnosis based on ultrasound shear wave elastography. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 410–414. IEEE (2021)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9729–9738 (2020)
He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. IEEE TPAMI 42(2), 386–397 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 4700–4708 (2017)
Jiao, Jianbo, Cai, Yifan, Alsharid, Mohammad, Drukker, Lior, Papageorghiou, Aris T., Noble, J. Alison.: Self-supervised contrastive video-speech representation learning for ultrasound. In: Martel, Anne L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 534–543. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59716-0_51
Ke, A., Ellsworth, W., Banerjee, O., Ng, A.Y., Rajpurkar, P.: Chextransfer: Performance and parameter efficiency of ImageNet models for chest X-ray interpretation. arXiv:2101.06871 (2021)
Kwitt, R., Vasconcelos, N., Razzaque, S., Aylward, S.: Localizing target structures in ultrasound video-a phantom study. Med. Image Anal. 17(7), 712–722 (2013)
Li, X., Jia, M., Islam, M.T., Yu, L., Xing, L.: Self-supervised feature learning via exploiting multi-modal data for retinal disease diagnosis. IEEE TMI 39(12), 4023–4033 (2020)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117–2125 (2017)
Lin, Tsung-Yi., et al.: Microsoft COCO: common objects in context. In: Fleet, David, Pajdla, Tomas, Schiele, Bernt, Tuytelaars, Tinne (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, L., Lei, W., Wan, X., Liu, L., Luo, Y., Feng, C.: Semi-supervised active learning for Covid-19 lung ultrasound multi-symptom classification. In: 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI), pp. 1268–1273. IEEE (2020)
Liu, T., Zhang, H.J., Qi, F.: A novel video key-frame-extraction algorithm based on perceived motion energy model. IEEE TCSVT 13(10), 1006–1013 (2003)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211–252 (2015)
Samuli, L., Timo, A.: Temporal ensembling for semi-supervised learning. In: International Conference on Learning Representations (ICLR), vol. 4, p. 6 (2017)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: ICCV, pp. 618–626 (2017)
Sohn, K.: Improved deep metric learning with multi-class N-pair loss objective. In: NeurIPS, pp. 1857–1865 (2016)
Sohn, K., et al.: FixMatch: simplifying semi-supervised learning with consistency and confidence. arXiv:2001.07685 (2020)
Somphone, O., Allaire, S., Mory, B., Dufour, C.: Live feature tracking in ultrasound liver sequences with sparse demons. In: MICCAI Workshop, pp. 53–60 (2014)
Vu, Y.N.T., Wang, R., Balachandar, N., Liu, C., Ng, A.Y., Rajpurkar, P.: MedAug: contrastive learning leveraging patient metadata improves representations for chest X-ray interpretation. arXiv:2102.10663 (2021)
Yap, M.H., et al.: Automated breast ultrasound lesions detection using convolutional neural networks. IEEE J. Biomed. Health Inform. 22(4), 1218–1226 (2017)
Acknowledgement
This work is supported by the Key-Area Research and Development Program of Guangdong Province (2020B0101350001); the GuangDong Basic and Applied Basic Research Foundation (No. 2020A1515110376); Guangdong Provincial Key Laboratory of Big Data Computation Theories and Methods, The Chinese University of Hong Kong (Shenzhen).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, Y. et al. (2021). USCL: Pretraining Deep Ultrasound Image Diagnosis Model Through Video Contrastive Representation Learning. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12908. Springer, Cham. https://doi.org/10.1007/978-3-030-87237-3_60
Download citation
DOI: https://doi.org/10.1007/978-3-030-87237-3_60
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87236-6
Online ISBN: 978-3-030-87237-3
eBook Packages: Computer ScienceComputer Science (R0)