Multi-modal Brain Tumor Segmentation Using Stacked Denoising Autoencoders

详细信息    查看全文

• 关键词：Gliomas ; MRI ; SDAE ; Unsupervised learning ; Supervised learning
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9556
• 期：1
• 页码：181-194
• 全文大小：3,038 KB
• 参考文献：1.Tustison, N., Gee, J.: Introducing Dice, Jaccard, and Other Label Overlap Measures To ITK (December 2009)
  2.Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., Bengio, Y.: Theano: A CPU and GPU math expression compiler. In: Proceedings of the Python for Scientific Computing Conference, SciPy 2010, Austin, TX, June 30 - July 3 (2010)
  3.Davy, A., Havaei, M., Warde-Farley, D., Biard, A., Tran, L., Jon, P., Courville, A., Larochelle, H., Pal, C., Bengio, Y.: Brain tumor segmentation with deep neural networks. In: Proceedings of the MICCAI-BRATS (2014)
  4.Durst, C., Tustison, N., Wintermark, M., Avants, B.: Ants and arboles (2013)
  5.Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: International Conference on Artificial Intelligence and Statistics, pp. 315–323 (2011)
  6.Gotz, M., Weber, C., Blocher, J., Stieltjes, B., Meinzer, H.P., Maier-Hein, K.: Extremely randomized trees based brain tumor segmentation. In: Proceedings of the BRATS Challenge-MICCAI (2014)
  7.Havaei, M., Davy, A., Warde-Farley, D., Biard, A., Courville, A.C., Bengio, Y., Pal, C., Jon, P., Larochelle, H.: Brain tumor segmentation with deep neural networks. CoRR abs/1505.03540 (2015). http://​arxiv.​org/​abs/​1505.​03540
  8.Hinton, G., Srivastava, N., Swersky, K.: Neural networks for machine learning lecture 6e rmsprop : divide the gradient by a running average of its recent magnitude
  9.Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.R.: Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint (2012). arXiv:​1207.​0580
  10.Khotanlou, H., Colliot, O., Atif, J., Bloch, I.: 3d brain tumor segmentation in mri using fuzzy classification, symmetry analysis and spatially constrained deformable models. Fuzzy Sets Syst. 160(10), 1457–1473 (2009)MathSciNet CrossRef
  11.Kleesiek, J., Biller, A., Urban, G., Köthe, U., Bendszus, M., Hamprecht, F.A.: ilastik for multi-modal brain tumor segmentation
  12.Liu, S., Liu, S., Cai, W., Pujol, S., Kikinis, R., Feng, D.: Early diagnosis of alzheimer’s disease with deep learning. In: 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI), pp. 1015–1018, April 2014
  13.Meier, R., Bauer, S., Slotboom, J., Wiest, R., Reyes, M.: Appearance-and context-sensitive features for brain tumor segmentation
  14.Menze, B., Reyes, M., Van Leemput, K.: The multimodal brain tumor image segmentation benchmark (brats). IEEE Trans. Med. Imaging 34(10), 1993–2024 (2014)CrossRef
  15.Popuri, K., Cobzas, D., Murtha, A., Jägersand, M.: 3d variational brain tumor segmentation using dirichlet priors on a clustered feature set. Int. J. Comput. Assist. Radiol. Surg. 7(4), 493–506 (2012)CrossRef
  16.Sheet, D., Karri, S.P.K., Katouzian, A., Navab, N., Ray, A.K., Chatterjee, J.: Deep learning of tissue specific speckle representations in optical coherence tomography and deeper exploration for in situ histology, pp. 777–780 (2015)
  17.Shin, H.C., Orton, M., Collins, D., Doran, S., Leach, M.: Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4d patient data. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1930–1943 (2013)CrossRef
  18.Stupp, R., Brada, M., van den Bent, M., Tonn, J.C., Pentheroudakis, G., Group, E.G.W., et al.: High-grade glioma: esmo clinical practice guidelines for diagnosis, treatment and follow-up. Ann. Oncol. 25(3), iii93–iii101 (2014)CrossRef
  19.Urban, G., Bendszus, M., Hamprecht, F., Kleesiek, J.: Multi-modal brain tumor segmentation using deep convolutional neural networks. In: MICCAI BraTS (Brain Tumor Segmentation) Challenge. Proceedings, Winning Contribution, pp. 31–35 (2014)
  20.Vaidya, S., Chunduru, A., Muthuganapathy, R., Krishnamurthi, G.: Longitudinal multiple sclerosis lesion segmentation using 3d convolutional neural networks
  21.Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371–3408 (2010)MathSciNet MATH
  22.Wang, N., Yeung, D.Y.: Learning a deep compact image representation for visual tracking. In: Advances in Neural Information Processing Systems, pp. 809–817 (2013)
  23.Zikic, D., Ioannou, Y., Brown, M., Criminisi, A.: Segmentation of brain tumor tissues with convolutional neural networks. In: Proceedings MICCAI-BRATS 2014, pp. 36–39 (2014)
  
• 作者单位：Kiran Vaidhya (18)
  Subramaniam Thirunavukkarasu (18)
  Varghese Alex (18)
  Ganapathy Krishnamurthi (18)
  
  18. Indian Institute of Technology Madras, Chennai, India
  
• 丛书名：Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries
• ISBN：978-3-319-30858-6
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

Accurate Segmentation of Gliomas from Magnetic Resonance Images (MRI) is required for treatment planning and monitoring disease progression. As manual segmentation is time consuming, an automated method can be useful, especially in large clinical studies. Since Gliomas have variable shape and texture, automated segmentation is a challenging task and a number of techniques based on machine learning algorithms have been proposed. In the recent past, deep learning methods have been tested on various image processing tasks and found to outperform state of the art techniques. In our work, we consider stacked denoising autoencoder (SDAE), a deep neural network that reconstructs its input. We trained a three layer SDAE where the input layer was a concatenation of fixed size 3D patches (11\(\,\times \,\)11\(\,\times \,\)3 voxels/neurons) from multiple MRI sequences. The 2nd, 3rd and 4th layers had 3000, 1000 and 500 neurons respectively. Two different networks were trained one with high grade glioma (HGG) data and other with a combination of high grade and low grade gliomas (LGG). Each network was trained with 35 patients for pre-training and 21 patients for fine tuning. The predictions from the two networks were combined based on maximum posterior probability. For HGG data, the whole tumor dice score was .81, tumor core was .68 and active tumor was .64 (\(n=220\) patients). For LGG data, the whole tumor dice score was .72, tumor core was .42 and active tumor was .29 (\(n=54\) patients).