FCNN-based axon segmentation for convection-enhanced delivery optimization
- 40 Downloads
Glioblastoma multiforme treatment is a challenging task in clinical oncology. Convection- enhanced delivery (CED) is showing encouraging but still suboptimal results due to drug leakages. Numerical models can predict drug distribution within the brain, but require retrieving brain physical properties, such as the axon diameter distribution (ADD), through axon architecture analysis. The goal of this work was to provide an automatic, accurate and fast method for axon segmentation in electronic microscopy images based on fully convolutional neural network (FCNN) as to allow automatic ADD computation.
The segmentation was performed using a residual FCNN inspired by U-Net and Resnet. The FCNN training was performed exploiting mini-batch gradient descent and the Adam optimizer. The Dice coefficient was chosen as loss function.
The proposed segmentation method achieved results comparable with already existing methods for axon segmentation in terms of Information Theoretic Scoring (\(0.98\%\)) with a faster training (5 h on the deployed GPU) and without requiring heavy post-processing (testing time was 0.2 s with a non-optimized code). The ADDs computed from the segmented and ground-truth images were statistically equivalent.
The algorithm proposed in this work allowed fast and accurate axon segmentation and ADD computation, showing promising performance for brain microstructure analysis for CED delivery optimization.
KeywordsAxon segmentation Electron microscopy Deep learning Convection-enhanced delivery Glioblastoma
This work has received funding from the European Union’s Horizon 2020 research and innovation programme under Grant Agreement No 688279.
Compliance with ethical standards
Conflict of interest
The authors have no conflict of interest to disclose.
This article does not contain any studies with human participants. All applicable international, national and/or institutional guidelines for the care and use of animals were followed.
- 1.Andres B, Köthe U, Helmstaedter M, Denk W, Hamprecht FA (2008) Segmentation of SBFSEM volume data of neural tissue by hierarchical classification. In: Joint pattern recognition symposium, Springer, pp 142–152Google Scholar
- 2.Arganda-Carreras I, Turaga SC, Berger DR, Cireşan D, Giusti A, Gambardella LM, Schmidhuber J, Laptev D, Dwivedi S, Buhmann JM, Liu T, Seyedhosseini M, Tasdizen T, Kamentsky L, Burget R, Uher V, Tan X, Sun C, Pham TD, Bas E, Uzunbas MG, Cardona A, Schindelin J, Seung SH (2015) Crowdsourcing the creation of image segmentation algorithms for connectomics. Front Neuroanat 9:142CrossRefGoogle Scholar
- 4.Barua NU, Hopkins K, Woolley M, OSullivan S, Harrison R, Edwards RJ, Bienemann AS, Wyatt MJ, Arshad A, Gill SS (2016) A novel implantable catheter system with transcutaneous port for intermittent convection-enhanced delivery of carboplatin for recurrent glioblastoma. Drug Deliv 23(1):167–173CrossRefGoogle Scholar
- 7.Buckner JC, Brown PD, O’neill BP, Meyer FB, Wetmore CJ, Uhm JH (2007) Central nervous system tumors. In: Mayo clinic proceedings, Elsevier vol 82, pp 1271–1286Google Scholar
- 8.Cai D, Chen K, Qian Y, Kämäräinen JK (2017) Convolutional low-resolution fine-grained classification. Pattern Recognit Lett (in press)Google Scholar
- 9.Ciresan D, Giusti A, Gambardella LM, Schmidhuber J (2012) Deep neural networks segment neuronal membranes in electron microscopy images. In: Advances in neural information processing systems, pp 2843–2851Google Scholar
- 12.Ehlers W, Wagner A (2015) Multi-component modelling of human brain tissue: a contribution to the constitutive and computational description of deformation, flow and diffusion processes with application to the invasive drug-delivery problem. Comput Methods Biomech Biomed Eng 18(8):861–879CrossRefGoogle Scholar
- 15.Hanif F, Muzaffar K, Perveen K, Malhi SM, Simjee SU (2017) Glioblastoma multiforme: a review of its epidemiology and pathogenesis through clinical presentation and treatment. Asian Pac J Cancer Prev 18(1):3Google Scholar
- 16.He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, pp 770–778Google Scholar
- 17.Iacob G, Dinca EB (2009) Current data and strategy in glioblastoma multiforme. J Med Life 2(4):386Google Scholar
- 22.Kaynig V, Fuchs T, Buhmann JM (2010) Neuron geometry extraction by perceptual grouping in SSTEM images. In: IEEE conference on computer vision and pattern recognition, IEEE, pp 2902–2909Google Scholar
- 23.Kingma D, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
- 25.Laptev D, Vezhnevets A, Dwivedi S, Buhmann JM (2012) Anisotropic sstem image segmentation using dense correspondence across sections. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 323–330Google Scholar
- 27.Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JA, van Ginneken B, Sánchez CI (2017) A survey on deep learning in medical image analysis. arXiv preprint arXiv:1702.05747
- 28.Liu T, Jurrus E, Seyedhosseini M, Ellisman M, Tasdizen T (2012) Watershed merge tree classification for electron microscopy image segmentation. In: IEEE international conference on pattern recognition, IEEE, pp 133–137Google Scholar
- 33.Quan TM, Hildebrand DG, Jeong WK (2016) Fusionnet: A deep fully residual convolutional neural network for image segmentation in connectomics. arXiv preprint arXiv:1612.05360
- 37.Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 234–241Google Scholar
- 40.Tschopp F, Martel JN, Turaga SC, Cook M, Funke J (2016) Efficient convolutional neural networks for pixelwise classification on heterogeneous hardware systems. In: IEEE international symposium on biomedical imaging, IEEE, pp 1225–1228Google Scholar
- 43.Vidotto M, Dini D, De Momi E (2018a) Effective diffusion and tortuosity in brain white matter. In: International conference the IEEE engineering in medicine and biology societyGoogle Scholar
- 44.Vidotto M, Gazzara M, Botnariuc D, Bernardini A, Dini D, De Momi E (2018b) White matter hydraulic permeability from electron microscopy images. In: World congress of biomechanicsGoogle Scholar
- 46.Xiao C, Liu J, Chen X, Han H, Shu C, Xie Q (2018) Deep contextual residual network for electron microscopy image segmentation in connectomics. In: International symposium on biomedical imaging, IEEE, pp 378–381Google Scholar