Abstract
Learning from external data is an effective and efficient way of training deep networks, which can substantially alleviate the burden on collecting training data and annotations. It is of great significance in improving the performance of CT image segmentation tasks, where collecting a large amount of voxel-wise annotations is expensive or even impractical. In this paper, we propose a generic selective learning method to maximize the performance gains of harnessing external data in CT image segmentation. The key idea is to learn a weight for each external data such that ‘good’ data can have large weights and thus contribute more to the training loss, thereby implicitly encouraging the network to mine more valuable knowledge from informative external data while suppressing to memorize irrelevant patterns from ‘useless’ or even ‘harmful’ data. Particularly, we formulate our idea as a constrained non-linear programming problem, solved by an iterative solution that alternatively conducts weights estimating and network updating. Extensive experiments on abdominal multi-organ CT segmentation datasets show the efficacy and performance gains of our method against existing methods. The code is publicly available (Released at https://github.com/YouyiSong/Codes-for-Selective-Learning).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Available on https://zenodo.org/record/1169361#.XSFOm-gzYuU.
References
Litjens, G., Kooi, T., Bejnordi, B., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017)
Shen, D., Wu, G., Suk, H.: Deep learning in medical image analysis. Ann. Rev. Biomed. Eng. 19, 221–248 (2017)
Kakeya, H., Okada, T., Oshiro, Y.: 3D U-JAPA-Net: mixture of convolutional networks for abdominal multi-organ CT segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 426–433 (2018)
Song, Y., Yu, Z., Zhou, T., et al.: Learning 3D features with 2D CNNs via surface projection for CT volume segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 176–186 (2020)
Huang, R., Zheng, Y., Hu, Z., et al.: Multi-organ segmentation via co-training weight-averaged models from few-organ datasets. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 146–155 (2020)
Isensee, F., Jaeger, P., Kohl, S., et al.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18, 1–9 (2020)
Mansour, Y., Mohri, M., Suresh, A., et al.: A theory of multiple-source adaptation with limited target labeled data. arXiv preprint arXiv:2007.09762 (2020)
Cortes, C., Mohri, M., Suresh, A., et al.: Multiple-source adaptation with domain classifiers. arXiv preprint arXiv:2008.11036 (2020)
Konstantinov, N., Frantar, E., Alistarh, D., et al.: On the sample complexity of adversarial multi-source PAC learning. In: International Conference on Machine Learning, pp. 5416–5425 (2020)
Charikar, M., Steinhardt, J., Valiant, G.: Learning from untrusted data. In: Proceedings of 49th Annual ACM SIGACT Symposium on Theory of Computing, pp. 47–60 (2017)
Qiao, M., Valiant, G.: Learning discrete distributions from untrusted batches. arXiv preprint arXiv:1711.08113 (2017)
Awasthi, P., Blum, A., Haghtalab, N., et al.: Efficient PAC learning from the crowd. In: International Conference on Learning Theory, pp. 127–150 (2017)
Hendrycks, D., Mazeika, M., Wilson, D., et al.: Using trusted data to train deep networks on labels corrupted by severe noise. arXiv:1802.05300 (2018)
Han, B., Yao, Q., Yu, X., et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. In: Advances in Neural Information Processing Systems, pp. 8536–8546 (2018)
Ghadikolaei, H., Ghauch, H., Fischione, C., et al.: Learning and data selection in big datasets. In: International Conference on Machine Learning, pp. 2191–2200 (2019)
Jain, A., Orlitsky, A.: A general method for robust learning from batches. arXiv preprint arXiv:2002.11099 (2020)
Zhang, C., Yao, Y., Liu, H., et al.: Web-supervised network with softly update-drop training for fine-grained visual classification. In: AAAI Conference on Artificial Intelligence, pp. 12781–12788 (2020)
Zhang, C., Yao, Y., Shu, X., et al.: Data-driven meta-set based fine-grained visual classification. arXiv preprint arXiv:2008.02438 (2020)
Bugallo, M., Elvira, V., Martino, L., et al.: Adaptive importance sampling: the past, the present, and the future. IEEE Signal Process. Mag. 34(4), 60–79 (2017)
Katharopoulos, A., Fleuret, F.: Not all samples are created equal: deep learning with importance sampling. In: International Conference on Machine Learning, pp. 2525–2534 (2018)
Sun, Y., Kamel, M., Wong, A., et al.: Cost-sensitive boosting for classification of imbalanced data. Pattern Recogn. 40(12), 3358–3378 (2007)
Liu, Q., Ihler, A., Fisher, J.: Boosting crowdsourcing with expert labels: local vs. global effect. In: International Conference on Information Fusion, pp. 9–14 (2015)
Malisiewicz, T., Gupta, A., Efros, A.: Ensemble of exemplar-svms for object detection and beyond. In: International Conference on Computer Vision, pp. 89–96 (2011)
Dumitrache, A., Aroyo, L., Welty, C.: Crowdsourcing ground truth for medical relation extractio. arXiv preprint arXiv:1701.02185 (2017)
Yan, K., Cai, J., Zheng, Y., et al.: Learning from multiple datasets with heterogeneous and partial labels for universal lesion detection in CT. IEEE Trans. Med. Imaging (2020)
Luo, L., Yu, L., Chen, H., et al.: Deep mining external imperfect data for chest X-ray disease screening. IEEE Trans. Med. Imaging 39(11), 3583–3594 (2020)
Ren, M., Zeng, W., Yang, B., et al.: Learning to reweight examples for robust deep learning. In: International Conference on Machine Learning, pp. 4334–4343 (2018)
Konstantinov, N., Lampert, C.: Robust learning from untrusted sources. In: International Conference on Machine Learning, pp. 3488–3498 (2019)
Lin, T., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Song, H., Kim, M., Lee, J.: Selfie: refurbishing unclean samples for robust deep learning. In: International Conference on Machine Learning, pp. 5907–5915 (2019)
Nandwani, Y., Pathak, A., Singla, P.: A primal dual formulation for deep learning with constraints. In: Advances in Neural Information Processing Systems, pp. 1–9 (2019)
Gibson, E., Giganti, F., Hu, Y., et al.: Automatic multi-organ segmentation on abdominal CT with dense v-networks. IEEE Trans. Med. Imaging 37(8), 1822–1834 (2018)
Landman, B., Xu, Z., Eugenio, I., et al.: MICCAI multi-atlas labeling beyond the cranial vault-workshop and challenge (2015)
Roth, H., Farag, A., Turkbey, E., et al.: Data from pancreas-CT. Cancer Imaging Arch. (2015)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)
Xu, B., Wang, N., Chen, T., et al.: Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015)
Srivastava, N., Hinton, G., Krizhevsky, A., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Kingma, D., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Acknowledgement
The work described in this paper is supported by two grants from the Hong Kong Research Grants Council under General Research Fund scheme (Project No. PolyU 152035/17E and 15205919), and a grant from HKU Startup Fund and HKU Seed Fund for Basic Research (Project No. 202009185079).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Song, Y., Yu, L., Lei, B., Choi, KS., Qin, J. (2021). Selective Learning from External Data for CT Image Segmentation. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12901. Springer, Cham. https://doi.org/10.1007/978-3-030-87193-2_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-87193-2_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87192-5
Online ISBN: 978-3-030-87193-2
eBook Packages: Computer ScienceComputer Science (R0)