Multi-organ segmentation of the head and neck area: an efficient hierarchical neural networks approach
- 78 Downloads
In radiation therapy, a key step for a successful cancer treatment is image-based treatment planning. One objective of the planning phase is the fast and accurate segmentation of organs at risk and target structures from medical images. However, manual delineation of organs, which is still the gold standard in many clinical environments, is time-consuming and prone to inter-observer variations. Consequently, many automated segmentation methods have been developed.
In this work, we train two hierarchical 3D neural networks to segment multiple organs at risk in the head and neck area. First, we train a coarse network on size-reduced medical images to locate the organs of interest. Second, a subsequent fine network on full-resolution images is trained for a final accurate segmentation. The proposed method is purely deep learning based; accordingly, no pre-registration or post-processing is required.
The approach has been applied on a publicly available computed tomography dataset, created for the MICCAI 2015 Auto-Segmentation challenge. In an extensive evaluation process, the best configurations for the trained networks have been determined. Compared to the existing methods, the presented approach shows state-of-the-art performance for the segmentation of seven different structures in the head and neck area.
We conclude that 3D neural networks outperform the most existing model- and atlas-based methods for the segmentation of organs at risk in the head and neck area. The ease of use, high accuracy and the test time efficiency of the method make it promising for image-based treatment planning in clinical practice.
KeywordsMulti-organ segmentation Neural network Head and neck Radiotherapy
Compliance with ethical standards
Conflict of interest
Elias Tappeiner, Samuel Pröll, Markus Hönig, Patrick F. Raudaschl, Paolo Zaffino, Maria F. Spadea, Gregory C. Sharp, Rainer Schubert, Karl Fritscher declare to have no conflict of interest.
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.
- 2.Raudaschl PF, Zaffino P, Sharp GC, Spadea MF, Chen A, Dawant BM, Albrecht T, Gass T, Langguth C, Lthi 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 CrossRefGoogle Scholar
- 5.Fritscher K, Raudaschl P, Zaffino P, Spadea MF, Sharp GC, Schubert R (2016) Deep neural networks for fast segmentation of 3D medical images. Med Image Comput Comput Assist Interv 158165. https://doi.org/10.1007/978-3-319-46720-7
- 7.Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotation. Med Image Comput Comput Assist Interv 424–432(1606):06650Google Scholar
- 8.Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. Med Image Comput Comput Assist Interv 234241. https://doi.org/10.1007/978-3-319-24574-4_28
- 10.He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. Comput Vis Pattern Recognit 770778. https://doi.org/10.3389/fpsyg.2013.00124
- 11.Sudre CH, Li W, Vercauteren T, Ourselin S, Cardoso MJ (2017) Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support 240–248. https://doi.org/10.1007/978-3-319-67558-9_28
- 12.Brosch T, Yoo Y, Tang LY, Li DK, Traboulsee A, Tam R (2015) Deep convolutional encoder networks for multiple sclerosis lesion segmentation. Med Image Comput Comput Assist Interv 3–11. https://doi.org/10.1007/978-3-319-24574-4_1
- 14.Li W, Wang G, Fidon L, Ourselin S, Cardoso MJ, Vercauteren T (2017) On the compactness, efficiency, and representation of 3D convolutional networks: brain parcellation as a pretext task. Inf Process Med Imaging 348–360. https://doi.org/10.1007/978-3-319-59050-9_28
- 15.Tappeiner E, Pröll S, Hönig M, Raudaschl FP, Zaffino P, Spadea FM, Sharp CG, Schubert R, Fritscher K (2018) Efficient multi-organ segmentation of the head and neck area using hierarchical neural networks. In: Computer assisted radiology and surgery proceedings of the 32nd international congress, pp 37–38. https://doi.org/10.1007/s11548-018-1766-y
- 16.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. arXiv preprint. arXiv:1606.00915
- 17.Gibson E, Giganti F, Hu Y, Bonmati E, Bandula S, Gurusamy K, Davidson RB, Pereira PS, Clarkson JM, Barratt DC (2017) Towards image-guided pancreas and biliary endoscopy: automatic multi-organ segmentation on abdominal CT with dense dilated networks. Med Image Comput Comput Assist Interv 728–736. https://doi.org/10.1007/978-3-319-66182-7_83
- 18.Roth HR, Oda H, Hayashi Y, Oda M, Shimizu N, Fujiwara, M, Misawa K, Mori K (2017) Hierarchical 3D fully convolutional networks for multi-organ segmentation. arXiv preprint. arXiv:1704.06382
- 19.Gibson E, Li W, Sudre C, Fidon L, Shakir ID, Wang G, Eaton-Rosen Z, Gray R, Doel T, Hu Y, Whyntie T, Nachev P, Modat M, Barratt CD, Ourselin S, Cardoso MJ, Vercauteren T (2017) NiftyNet: a deep-learning platform for medical imaging. arXiv preprint. arXiv:1709.03485
- 20.Luo W, Li Y, Urtasun R, Zemel R (2017) Understanding the effective receptive field in deep convolutional neural networks. Adv Neural Inf Process Syst 4898–4906(1701):04128Google Scholar
- 22.Kingma D, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint. arXiv:1412.6980
- 25.Jung F, Knapp O, Wesarg S (2015) CoSMo—coupled shape model segmentation. Head and neck auto-segmentation challenge MICCAI Munich. http://midasjournal.org/browse/publication/970
- 26.Mannion-Haworth R, Bowes M, Ashman A, Guillard G, Brett A, Vincent G (2015) Fully automatic segmentation of head and neck organs using active appearance models. Head and neck auto-segmentation challenge MICCAI Munich. http://midasjournal.org/browse/publication/967
- 27.Albrecht T, Gass T, Langguth C, Lüthi M (2015) Multi atlas segmentation with active shape model refinement for multiorgan segmentation in head and neck cancer radiotherapy planning. Head and neck auto-segmentation challenge MICCAI Munich. http://midasjournal.org/browse/publication/968
- 28.Orbes-Arteaga M, Córdenas-Peña D, Castellanos-Dominguez G (2015) Head and neck auto segmentation challenge based on non-local generative models. Head and neck auto-segmentation challenge MICCAI Munich. http://midasjournal.org/browse/publication/965
- 29.Aghdasi N, Li Y, Berens A, Moe K, Hannaford B (2015) Head and neck segmentation based on anatomical knowledge. Head and neck auto-segmentation challenge MICCAI Munich. http://midasjournal.org/browse/publication/971
- 30.Chen A, Dawant BM (2015) A multi-atlas approach for the automatic segmentation of multiple structures in head and neck CT images. Head and neck auto-segmentation challenge MICCAI Munich. http://midasjournal.org/browse/publication/964