Abstract
We revisit Auto-Context Forests for brain tumour segmentation in multi-channel magnetic resonance images, where semantic context is progressively built and refined via successive layers of Decision Forests (DFs). Specifically, we make the following contributions: (1) improved generalization via an efficient node-splitting criterion based on hold-out estimates, (2) increased compactness at a tree-level, thereby yielding shallow discriminative ensembles trained orders of magnitude faster, and (3) guided semantic bagging that exposes latent data-space semantics captured by forest pathways. The proposed framework is practical: the per-layer training is fast, modular and robust. It was a top performer in the MICCAI 2016 BRATS (Brain Tumour Segmentation) challenge, and this paper aims to discuss and provide details about the challenge entry.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
As an illustration on WT layers. The 4 (WT) clusters are obtained from (the single DF of) the first WT layer. The second and third WT layers each consist of 4 distinct (50-tree) DFs, each of which is trained on cluster-specific data. At test time, voxels \(\varvec{\mathrm {x}}\) pass through the first WT layer and are assigned a cluster \(k_{\varvec{\mathrm {x}}}\!\in \!\{1\cdots 4\}\). Then for the second and third layers, they are sent through the DF specific to the \(k_{\varvec{\mathrm {x}}}\)-th cluster. The same process is followed for TC and ET layers.
References
Amit, Y., Geman, D.: Shape quantization and recognition with randomized trees. Neural Comput. 9(7), 1545–1588 (1997)
Archambeau, C., Verleysen, M.: Robust Bayesian clustering. Neural Netw. 20(1), 129–138 (2007)
Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)
Cordier, N., Delingette, H., Ayache, N.: A patch-based approach for the segmentation of pathologies: application to glioma labelling. IEEE Trans. Med. Imaging 35(4), 1066–1076 (2015)
Criminisi, A., Robertson, D., Konukoglu, E., Shotton, J., Pathak, S., White, S., Siddiqui, K.: Regression forests for efficient anatomy detection and localization in computed tomography scans. Med. Image Anal. 17(8), 1293–1303 (2013)
Geremia, E., Menze, B.H., Ayache, N.: Spatially adaptive random forests. In: 2013 IEEE 10th International Symposium on Biomedical Imaging, pp. 1344–1347. IEEE (2013)
Ho, T.K.: The random subspace method for constructing decision forests. IEEE Trans. Pattern Anal. Mach. Intell. 20(8), 832–844 (1998)
Kamnitsas, K., Ledig, C., Newcombe, V.F.J., Simpson, J.P., Kane, A.D., Menon, D.K., Rueckert, D., Glocker, B.: Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med. Image Anal. 36, 61–78 (2017). Elsevier
Menze, B., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., Burren, Y., Porz, N., Slotboom, J., Wiest, R., et al.: The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2015)
Menze, B.H., Leemput, K., Lashkari, D., Weber, M.-A., Ayache, N., Golland, P.: A generative model for brain tumor segmentation in multi-modal images. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6362, pp. 151–159. Springer, Heidelberg (2010). doi:10.1007/978-3-642-15745-5_19
Pereira, S., Pinto, A., Alves, V., Silva, C.A.: Deep convolutional neural networks for the segmentation of gliomas in multi-sequence MRI. In: Crimi, A., Menze, B., Maier, O., Reyes, M., Handels, H. (eds.) BrainLes 2015. LNCS, vol. 9556, pp. 131–143. Springer, Cham (2016). doi:10.1007/978-3-319-30858-6_12
Quinlan, J.R.: Simplifying decision trees. Int. J. Man. Mach. Stud. 27(3), 221–234 (1987)
Shotton, J., Johnson, M., Cipolla, R.: Semantic texton forests for image categorization and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–8. IEEE (2008)
Tu, Z.: Auto-context and its application to high-level vision tasks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–8. IEEE (2008)
Tu, Z., Bai, X.: Auto-context and its application to high-level vision tasks and 3D brain image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 32(10), 1744–1757 (2010)
Tustison, N., Gee, J.: N4ITK: Nicks N3 ITK implementation for MRI bias field correction. Insight J. (2009). http://hdl.handle.net/10380/3053
Tustison, N.J., Shrinidhi, K., Wintermark, M., Durst, C.R., Kandel, B.M., Gee, J.C., Grossman, M.C., Avants, B.B.: Optimal symmetric multimodal templates and concatenated random forests for supervised brain tumor segmentation (simplified) with ANTsR. Neuroinformatics 13(2), 209–225 (2015)
Tustison, N., Wintermark, M., Durst, C., Avants, B.: Ants and arboles. Multimodal Brain Tumor Segmentation, p. 47 (2013)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, p. I-511. IEEE (2001)
Zhang, Y., Brady, M., Smith, S.: Segmentation of brain MR images through a hidden Markov Random Field model and the Expectation-Maximization algorithm. IEEE Trans. Med. Imaging 20(1), 45–57 (2001)
Zikic, D., et al.: Decision forests for tissue-specific segmentation of high-grade gliomas in multi-channel MR. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012. LNCS, vol. 7512, pp. 369–376. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33454-2_46
Acknowledgment
The authors would like to thank the Microsoft–Inria Joint Centre for partially funding this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
A BRATS 2015 Dataset: Training IDs
A BRATS 2015 Dataset: Training IDs
For completeness, the identifiers of images from the BRATS 2015 dataset that were used for training (Sect. 6.1) are listed below.
2013_pat0001_1, 2013_pat0002_1, 2013_pat0003_1, 2013_pat0004_1, 2013_pat0005_1,
2013_pat0006_1, 2013_pat0007_1, 2013_pat0008_1, 2013_pat0009_1, 2013_pat0010_1,
2013_pat0011_1, 2013_pat0012_1, 2013_pat0013_1, 2013_pat0014_1, 2013_pat0015_1,
2013_pat0022_1, 2013_pat0024_1, 2013_pat0025_1, 2013_pat0026_1, 2013_pat0027_1,
tcia_pat105_0001, tcia_pat117_0001, tcia_pat124_0003, tcia_pat133_0001, tcia_pat149_0001,
tcia_pat153_0181, tcia_pat165_0001, tcia_pat170_0002, tcia_pat260_0129, tcia_pat260_0244,
tcia_pat260_0317, tcia_pat265_0001, tcia_pat290_0580, tcia_pat296_0001, tcia_pat300_0001,
tcia_pat314_0001, tcia_pat319_0001, tcia_pat370_0001, tcia_pat372_0001, tcia_pat375_0001,
tcia_pat377_0001, tcia_pat396_0139, tcia_pat396_0176, tcia_pat401_0001, tcia_pat430_0001,
tcia_pat491_0001, 2013_pat0001_1, 2013_pat0004_1, 2013_pat0006_1, 2013_pat0008_1,
2013_pat0011_1, 2013_pat0012_1, 2013_pat0013_1, 2013_pat0014_1, 2013_pat0015_1,
tcia_pat101_0001, tcia_pat109_0001, tcia_pat141_0001, tcia_pat241_0001, tcia_pat249_0001,
tcia_pat298_0001, tcia_pat307_0001, tcia_pat325_0001, tcia_pat346_0001, tcia_pat354_0001,
tcia_pat393_0001, tcia_pat402_0001, tcia_pat408_0001, tcia_pat413_0001, tcia_pat442_0001,
tcia_pat449_0001,
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Le Folgoc, L., Nori, A.V., Ancha, S., Criminisi, A. (2016). Lifted Auto-Context Forests for Brain Tumour Segmentation. In: Crimi, A., Menze, B., Maier, O., Reyes, M., Winzeck, S., Handels, H. (eds) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2016. Lecture Notes in Computer Science(), vol 10154. Springer, Cham. https://doi.org/10.1007/978-3-319-55524-9_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-55524-9_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-55523-2
Online ISBN: 978-3-319-55524-9
eBook Packages: Computer ScienceComputer Science (R0)