Abstract
Semi-supervised learning algorithms make use of both labelled training data and unlabelled data. However, the visual domain gap between these sets poses a challenge which prevents deep learning models from obtaining the results they have achieved most especially in the field of medical imaging. Recently, self-training with deep learning has become a powerful approach to leverage labelled training and unlabelled data. However, a challenge of generating noisy pseudo-labels and placing over-confident labelling belief on incorrect classes leads to deviation from the solution. To solve this challenge, the study investigates a curriculum-styled approach for deep semi-supervised segmentation which relaxes and treats pseudo-labels as continuous hidden variables by developing an adaptive pseudo-label generation strategy to jointly optimized the pseudo-label generation and selection process. A regularization scheme is further proposed to smoothen the probability outputs and sharpen the less represented pseudo-label regions. The proposed method was evaluated on three publicly available Computer Tomography (CT) scan benchmarks and extensive experiments on all modules have demonstrated the efficacy of the proposed method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
We’re sorry, something doesn't seem to be working properly.
Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.
References
Anter, A.M., Hassanien, A.E., ElSoud, M.A.A., Tolba, M.F.: Neutrosophic sets and fuzzy c-means clustering for improving CT liver image segmentation. In: Kömer, P., Abraham, A., Snášel, V. (eds.) Proceedings of the Fifth International Conference on Innovations in Bio-Inspired Computing and Applications IBICA 2014. AISC, vol. 303, pp. 193–203. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-08156-4_20
Chung, M., Lee, J., Lee, J., Shin, Y.G.: Liver segmentation in abdominal CT images via auto-context neural network and self-supervised contour attention. ArXiv arXiv:2002.05895 (February 2020)
Devi, K.G., Radhakrishnan, R.: Automatic segmentation of colon in 3d CT images and removal of opacified fluid using cascade feed forward neural network. Comput. Math. Methods Med. 2015, 670739–670739 (2015)
Gibson, E., et al.: Automatic multi-organ segmentation on abdominal CT with dense v-networks. IEEE Trans. Med. Imaging 37(8), 1822–1834 (2018). https://doi.org/10.1109/TMI.2018.2806309
Gonzalez, Y., et al.: Semi-automatic sigmoid colon segmentation in CT for radiation therapy treatment planning via an iterative 2.5-d deep learning approach. Med. Image Anal. 68, 101896 (2021)
Hu, P., Wu, F., Peng, J., Bao, Y., Chen, F., Kong, D.: Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets. Int. J. Comput. Assist. Radiol. Surg. 12(3), 399–411 (2016). https://doi.org/10.1007/s11548-016-1501-5
Kalluri, T., Varma, G., Chandraker, M., Jawahar, C.: Universal semi-supervised semantic segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (October 2019)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Larsson, M., Zhang, Y., Kahl, F.: Robust abdominal organ segmentation using regional convolutional neural networks. In: Sharma, P., Bianchi, F.M. (eds.) SCIA 2017. LNCS, vol. 10270, pp. 41–52. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59129-2_4
Nartey, O., Yang, G., Wu, J., Asare, S.: Semi-supervised learning for fine-grained classification with self-training. IEEE Access 1 (December 2019).https://doi.org/10.1109/ACCESS.2019.2962258
Nartey, O., Yang, G., Wu, J., Asare, S., Frempong, L.N.: Robust semi-supervised traffic sign recognition via self-training and weakly-supervised learning. Sensors 20(9), 2684 (2020). https://doi.org/10.3390/s20092684
Peng, J., Estrada, G., Pedersoli, M., Desrosiers, C.: Deep co-training for semi-supervised image segmentation. Pattern Recogn. 107–269 (2020).https://doi.org/10.1016/j.patcog.2020.107269
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
Rosenberg, C., Hebert, M., Schneiderman, H.: Semi-supervised self-training of object detection models. In: 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION 2005), vol. 1, pp. 29–36 (2005)
Roth, H., et al.: Hierarchical 3d fully convolutional networks for multi-organ segmentation. CoRR (April 2017)
Shahzad, R., Gao, S., Tao, Q., Dzyubachyk, O., van der Geest, R.: Automated cardiovascular segmentation in patients with congenital heart disease from 3D CMR scans: combining multi-atlases and level-sets. In: Zuluaga, M.A., Bhatia, K., Kainz, B., Moghari, M.H., Pace, D.F. (eds.) RAMBO/HVSMR -2016. LNCS, vol. 10129, pp. 147–155. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-52280-7_15
Simpson, A.L., et al.: A large annotated medical image dataset for the development and evaluation of segmentation algorithms. CoRRabs arXiv:1902.09063 (2019)
Tsai, Y.H., Hung, W.C., Schulter, S., Sohn, K., Yang, M.H., Chandraker, M.: Learning to adapt structured output space for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (June 2018)
Tziritas, G.: Fully-automatic segmentation of cardiac images using 3-D MRF model optimization and substructures tracking. In: Zuluaga, M.A., Bhatia, K., Kainz, B., Moghari, M.H., Pace, D.F. (eds.) RAMBO/HVSMR -2016. LNCS, vol. 10129, pp. 129–136. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-52280-7_13
Vorontsov, E., Tang, A., Pal, C., Kadoury, S.: Liver lesion segmentation informed by joint liver segmentation. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), pp. 1332–1335 (2018)
Wang, X., Yang, J., Ai, D., Zheng, Y., Tang, S., Wang, Y.: Adaptive mesh expansion model (AMEM) for liver segmentation from CT image. PLoS ONE 10(3), e0118064 (2015). https://doi.org/10.1371/journal.pone.0118064
Wu, W., Wu, S., Zhou, Z., Zhang, R., Zhang, Y.: 3d liver tumor segmentation in CT-images using improved fuzzy c-means and graph cuts. Biomed. Res. Int. 2017, 5207685 (2017). https://doi.org/10.1155/2017/5207685
Xianling, D., et al.: Multi-view secondary input collaborative deep learning for lung nodule 3d segmentation. Cancer Imaging 20, 53 (2020). https://doi.org/10.1186/s40644-020-00331-0
Zeng, G., Zheng, G.: Holistic decomposition convolution for effective semantic segmentation of medical volume images. Med. Image Anal. 57, 149–164 (2019)
Zhang, Y., David, P., Gong, B.: Curriculum domain adaptation for semantic segmentation of urban scenes. In: The IEEE International Conference on Computer Vision (ICCV), vol. 2–5, p. 6 (October 2017)
Zhou, X., Ito, T., Takayama, R., Wang, S., Hara, T., Fujita, H.: Three-dimensional CT-image segmentation by combining 2d fully convolutional network with 3d majority voting. In: MICCAI Workshop Large-Scale Annotation Biomed. Data Expert Label Synth, pp. 111–120 (October 2016). https://doi.org/10.1007/978-3-319-46976-812
Zou, Y., Yu, Z., Vijaya Kumar, B., Wang, J.: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: The European Conference on Computer Vision (ECCV) (September 2018)
Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_49
Acknowledgements
This work was partially supported by the National Natural Science Foundation of China under Grant No. 61772006, Sub Project of Independent Scientific Research Project under Grant No. ZZKY-ZX-03-02-04, and the Special Fund for Bagui Scholars of Guangxi.
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
Nartey, O.T., Yang, G., Agyapong, D., Wu, J., Sarpong, A.K., Frempong, L.N. (2021). Adaptive Curriculum Learning for Semi-supervised Segmentation of 3D CT-Scans. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13108. Springer, Cham. https://doi.org/10.1007/978-3-030-92185-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-92185-9_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92184-2
Online ISBN: 978-3-030-92185-9
eBook Packages: Computer ScienceComputer Science (R0)