Abstract
Purpose
Cancer in the head and neck area is commonly treated with radiotherapy. A key step for low-risk treatment is the accurate delineation of organs at risk in the planning imagery. The success of deep learning in image segmentation led to automated algorithms achieving human expert performance on certain datasets. However, such algorithms require large datasets for training and fail to segment previously unseen pathologies, where human experts still succeed. As pathologies are rare and large datasets costly to generate, we investigate the effect of: reduced training data, batch sizes and incorporation of prior knowledge.
Methods
The small data problem is studied by training a full-volume segmentation network with the reduced amount of data from the MICCAI 2015 head and neck segmentation challenge. To improve the segmentation, we evaluate the batch size as a hyper-parameter and first study and then incorporate a stacked autoencoder as shape prior into the training process.
Results
We found that using half of the training data (12 images of 25) results in an accuracy drop of only 3% for the segmentation of organs at risk. Also, the batch size turns out to be relevant for the quality of the segmentation when trained with less than half of the data. By applying PCA on the autoencoder’s latent space we achieve a compact and accurate shape model, which is used as a regularizer and significantly improves the segmentation results.
Conclusion
Small training data of up to 12 training images is enough to train accurate head and neck segmentation models. By using a shape prior for regularization, the performance of the segmentation can be improved significantly on the full dataset. When training on fewer than 12 images, the batch size is relevant and models have to be trained much longer until convergence.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Siegel RL, Miller KD, Jemal A (2018) Cancer statistics, 2018. CA Cancer J Clin 68:7–30. https://doi.org/10.3322/caac.21442
Nelms BE, Tomé WA, Wheeler G (2012) Variations in the contouring of organs at risk: test case from a patient with oropharyngeal cancer. Int J Radiat Oncol 82(1):368–378. https://doi.org/10.1016/j.ijrobp.2010.10.019
Raudaschl PF, Zaffino P, Sharp GC, Spadea MF, Chen A, Dawant BM, Albrecht T, Gass T, Langguth C, Lüthi M, Jung F, Knapp O, Wesarg S, Mannion-Haworth R, Bowes M, Ashman A, Guillard G, Brett A, Vincent G, Orbes-Arteaga M, Córdenas-Peña D, Castellanos-Dominguez G, Aghdasi N, Li Y, Berens A, Moe K, Hannaford B, Schubert R, Fritscher KD (2017) Evaluation of segmentation methods on head and neck CT: auto-segmentation challenge 2015. Med Phys 44(5):2020–2036. https://doi.org/10.1002/mp.12197
Ibragimov B, Xing L (2017) Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks. Med Phys 44(2):547–557. https://doi.org/10.1002/mp.12045
Fritscher K, Raudaschl P, Zaffino P, Spadea MF, Sharp GC, Schubert R (2016) Deep neural networks for fast segmentation of 3D Medical Images. In: Medical image computing and computer-assisted intervention, pp 158–165. https://doi.org/10.1007/978-3-319-46720-7
Ren X, Xiang L, Nie D, Shao Y, Zhang H, Shen D, Wang Q (2018) Interleaved 3D-CNN s for joint segmentation of small–volume structures in head and neck CT images. Med Phys 45(5):2063–2075. https://doi.org/10.1002/mp.12837
Kodym O, Španěl M, Herout A (2019) Segmentation of head and neck organs at risk using CNN with batch dice loss. In: German conference on pattern recognition, pp 105–114. https://doi.org/10.1007/978-3-030-12939-2_8
Yunhe G, Rui H, Ming C, Zhe W, Jincheng D, Yuanyuan C, Yiwei Y, Jie Z, Chanjuan T, Hongsheng L (2019) FocusNet: imbalanced large and small organ segmentation with an end-to-end deep neural network for head and neck CT images. In: Medical image computing and computer-assisted intervention, pp 829–838. https://doi.org/10.1007/978-3-030-32248-9
Oktay O, Ferrante E, Kamnitsas K, Heinrich M, Bai W, Caballero J, Cook SA, De Marvao A, Dawes T, O’Regan DP, Kainz B, Glocker B, Rueckert D (2018) Anatomically constrained neural networks (ACNN): application to cardiac image enhancement and segmentation. IEEE Trans Med Imaging 2(37):384–395. https://doi.org/10.1109/TMI.2017.2743464
LeCun Y, Bengio Y, Bengio G (2015) Deep learning. Nature 521(7553):436–444. https://doi.org/10.1038/nature14539
Tappeiner E, Pröll S, Hönig M, Raudaschl PF, Zaffino P, Spadea MF, Fritscher K. (2019) Multi-organ segmentation of the head and neck area: an efficient hierarchical neural networks approach. Int J Comput Assist Radiol Surg. https://doi.org/10.1007/s11548-019-01922-4
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431–3440. https://doi.org/10.1109/CVPR.2015.7298965
Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2016) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFS. Preprint arXiv:1606.00915
Li W, Wang G, Fidon L, Ourselin S, Cardoso M J, Vercauteren T (2017) On the compactness, efficiency, and representation of 3D convolutional networks: Brain parcellation as a pretext task. In: Information processing in medical imaging, pp 348–360. https://doi.org/10.1007/978-3-319-59050-9_28
He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. In: Computer vision and pattern recognition, pp 770–778. https://doi.org/10.3389/fpsyg.2013.00124
Milletari F, Navab N, Ahmadi SA (2016) V-Net: Fully convolutional neural networks for volumetric medical image segmentation. In: 3D vision, pp 565–571. https://doi.org/10.1109/3DV.2016.79
Crum WR, Camara O, Hill DLG (2006) Generalized overlap measures for evaluation and validation in medical image analysis. Trans Med Imaging 25(11):1451–1461. https://doi.org/10.1109/TMI.2006.880587
Zhu W, Huang Y, Zeng L, Chen X, Liu Y, Qian Z, Nan Du, Fan W, Xie X (2018) AnatomyNet: deep learning for fast and fully automated whole-volume segmentation of head and neck anatomy. Med Phys 46(2):1–13. https://doi.org/10.1002/mp.13300
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Computer vision and pattern recognition, pp 7132–7141. https://doi.org/10.1109/CVPR.2018.00745
Gao Y, Huang R, Chen M, Wang Z, Deng J, Chen Y, Yang Y, Zhang J, Tao C, Li H (2019) FocusNet: imbalanced Large and small organ segmentation with an end-to-end deep neural network for head and neck CT images. preprint arXiv:1907.12056
Nikolov S, Blackwell S, Mendes R, De Fauw J, Meyer C, Hughes C, Askham H, Romera-Paredes B, Karthikesalingam A, Chu C, Carnell D, Boon C, D’Souza D, Moinuddin S A, Sullivan K, Montgomery H, Rees G, Sharma R, Suleyman M, Back T, Ledsam J R, Ronneberger O (2018) Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy. preprint arXiv:1809.04430
Cootes TF, Taylor CJ (1995) Combining point distribution models with shape models based on finite element analysis. Image Vis Comput 13(5):403–409. https://doi.org/10.1016/0262-8856(95)99727-I
Masci J, Meier U, Ciresan D, Schmidhuber J (2011). Stacked convolu- tional auto-encoders for hierarchical feature extraction.In: Conference on artificial neural networks, pp 52–59. https://doi.org/10.1007/978-3-642-21735-7_7
Tong N, Gou S, Yang S, Ruan D, Sheng K (2018) Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks. Med Phys 45(10):4558–4558. https://doi.org/10.1002/mp.13147
Dice LR (1945) Measures of the amount of ecologic association between species. Ecology 26(3):297–302. https://doi.org/10.2307/1932409
Huttenlocher DP, Klanderman GA, Rucklidge WJ (1993) Comparing images using the Hausdorff distance. IEEE Trans Pattern Anal Mach Intell 15(9):850–863. https://doi.org/10.1109/34.232073
Kingma D, Ba J (2014) Adam: A method for stochastic optimization.preprint arXiv:1412.6980
Plaut E (2018) from principal subspaces to principal components with linear autoencoders. preprint arXiv:1804.10253
Wilcoxon F (1945) Individual Comparisons by Ranking Methods. Biom Bull 1(6):80–83. https://doi.org/10.2307/3001968
Masters D, Carlo L (2018) Revisiting small batch training for deep neural networks. preprint arXiv:1804.07612
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
Elias Tappeiner, Samuel Pröll, Karl Fritscher, Martin Welk, Rainer Schubert declare to have no conflict of interest.
Ethical approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Tappeiner, E., Pröll, S., Fritscher, K. et al. Training of head and neck segmentation networks with shape prior on small datasets. Int J CARS 15, 1417–1425 (2020). https://doi.org/10.1007/s11548-020-02175-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-020-02175-2