Abstract
An emerging trend in biomedical systems research is the development of models that take full advantage of the increasing available computational power to manage and analyze new biological data as well as to model complex biological processes. Such biomedical models require significant computational resources, since they process and analyze large amounts of data, such as medical image sequences. We present a family of advanced computational models for the prediction of the spatio-temporal evolution of glioma and their novel implementation in state-of-the-art FPGA devices. Glioma is a rapidly evolving type of brain cancer, well known for its aggressive and diffusive behavior. The developed system simulates the glioma tumor growth in the brain tissue, which consists of different anatomic structures, by utilizing MRI slices. The presented models have been proved highly accurate in predicting the growth of the tumor, whereas the developed innovative hardware system, when implemented on a low-end, low-cost FPGA, is up to 85% faster than a high-end server consisting of 20 physical cores (and 40 virtual ones) and more than 28× more energy-efficient than it; the energy efficiency grows up to 50× and the speedup up to 14× if the presented designs are implemented in a high-end FPGA. Moreover, the proposed reconfigurable system, when implemented in a large FPGA, is significantly faster than a high-end GPU (i.e., from 80% and up to 250% faster), for the majority of the models, while it is also significantly better (i.e., from 80% to over 1,600%) in terms of power efficiency, for all the implemented models.
- Alexander R. A. Anderson. 2005. A hybrid mathematical model of solid tumour invasion: The importance of cell adhesion. Math. Med. Biol.: J. IMA 22, 2 (06 2005), 163–186. DOI:DOI:https://doi.org/10.1093/imammb/dqi005Google Scholar
- A. R. A. Anderson, M. A. J. Chaplain, E. L. Newman, R. J. C. Steele, and A. M. Thompson. 1900. Mathematical modelling of tumour invasion and metastasis. J. Theor. Med. 2 (01 Jan. 1900), 490902. DOI:DOI:https://doi.org/10.1080/10273660008833042Google Scholar
- M. Birk, A. Guth, M. Zapf, M. Balzer, N. Ruiter, M. Hübner, and J. Becker. 2011. Acceleration of image reconstruction in 3D ultrasound computer tomography: An evaluation of CPU, GPU and FPGA computing. In Proceedings of the Conference on Design Architectures for Signal Image Processing (DASIP’11). 1–8. DOI:DOI:https://doi.org/10.1109/DASIP.2011.6136856Google Scholar
- Paul Commean. 2020. The Cancer Imaging Archive - RIDER NEURO MRI. Retrieved from https://wiki.cancerimagingarchive.net/display/Public/RIDER+NEURO+MRI.Google Scholar
- Omkar Dandekar, Carlos Castro-Pareja, and Raj Shekhar. 2007. FPGA-based real-time 3D image preprocessing for image-guided medical interventions. J. Real-Time Image Process. 1, 4 (01 July 2007), 285–301. DOI:DOI:https://doi.org/10.1007/s11554-007-0028-yGoogle Scholar
- N. Doulamis, M. Papadogiorgaki, and M. Zervakis. 2013. Texture driven mathematical modeling for brain tumor evolution. In Proceedings of the Conference on Pervasive Technologies Related to Assistive Environments (PETRA’13).Google Scholar
- A. Elazab, H. Bai, X. Zhang, and Q. Hu. 2017. Low grade glioma growth modeling considering chemotherapy and radiotherapy effects from magnetic resonance images. In Proceedings of the 39th International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’17). 3077–3080. DOI:DOI:https://doi.org/10.1109/EMBC.2017.8037507Google Scholar
- Jian Fang, Yvo T. B. Mulder, Jan Hidders, Jinho Lee, and H. Peter Hofstee. 2020. In-memory database acceleration on FPGAs: A survey. VLDB J. 29, 1 (01 Jan. 2020), 33–59. DOI:DOI:https://doi.org/10.1007/s00778-019-00581-wGoogle Scholar
- R. Gioiosa, S. A. McKee, and M. Valero. 2010. Designing OS for HPC applications: Scheduling. In Proceedings of the IEEE International Conference on Cluster Computing. 78–87.Google Scholar
- H. P. Greenspan. 1972. Models for the growth of a solid tumor by diffusion. Stud. Appl. Math. 51, 4 (1972), 317–340. DOI:DOI:https://doi.org/10.1002/sapm1972514317Google Scholar
Cross Ref
- Hana L.P. Harpold, Ellsworth C. Alvord Jr., and Kristin R. Swanson. 2007. The evolution of mathematical modeling of glioma proliferation and invasion. J. Neuropathol. Experim. Neurol. 66, 1 (01 2007), 1–9. DOI:DOI:https://doi.org/10.1097/nen.0b013e31802d9000Google Scholar
- Sami Hasan, Said Boussakta, and Alex Yakovlev. 2012. FPGA-based architecture for a generalized parallel 2-D MRI filtering algorithm. Amer. J. Eng. Appl. Sci. 4, 4 (Feb. 2012), 566–575. DOI:DOI:https://doi.org/10.3844/ajeassp.2011.566.575Google Scholar
- Haralambos Hatzikirou and Andreas Deutsch. 2008. Cellular automata as microscopic models of cell migration in heterogeneous environments. In Multiscale Modeling of Developmental Systems, Santiago Schnell, Philip K. Maini, Stuart A. Newman, and Timothy J. Newman (Eds.) (Current Topics in Developmental Biology, Vol. 81). Academic Press, 401–434. DOI:DOI:https://doi.org/10.1016/S0070-2153(07)81014-3Google Scholar
- M. Horowitz. 2014. 1.1 Computing’s energy problem (and what we can do about it). In Proceedings of the IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC’14). 10–14. DOI:DOI:https://doi.org/10.1109/ISSCC.2014.6757323Google Scholar
Cross Ref
- R. M. Jiang and D. Crookes. 2007. FPGA implementation of 3D discrete wavelet transform for real-time medical imaging. In Proceedings of the 18th European Conference on Circuit Theory and Design. 519–522. DOI:DOI:https://doi.org/10.1109/ECCTD.2007.4529647Google Scholar
- Kanchi Lakshmi Kiran, Devaraj Jayachandran, and S. Lakshminarayanan. 2009. Mathematical modelling of avascular tumour growth based on diffusion of nutrients and its validation. Canadian J. Chem. Eng. 87, 5 (2009), 732–740. DOI:DOI:https://doi.org/10.1002/cjce.20204Google Scholar
- Adrian KÅ.usek, Marcin Å.oÅ., Maciej PaszyÅ.ski, and Witold Dzwinel. 2019. Efficient model of tumor dynamics simulated in multi-GPU environment. Int. J. High Perform. Comput. Applic. 33, 3 (2019), 489–506. DOI:DOI:https://doi.org/10.1177/1094342018816772Google Scholar
- Ruoshi Li, Hongjing Huang, Zeke Wang, Zhiyuan Shao, Xiaofei Liao, and Hai Jin. 2020. Optimizing Memory Performance of Xilinx FPGAs under Vitis. arxiv:cs.DC/2010.08916Google Scholar
- Gülnihal Meral and Christina Surulescu. 2013. Mathematical modelling, analysis and numerical simulations for the influence of heat shock proteins on tumour invasion. J. Math. Anal. Appl. 408, 2 (2013), 597–614. DOI:DOI:https://doi.org/10.1016/j.jmaa.2013.06.017Google Scholar
- Daniele Jahier Pagliari, Mario R. Casu, and Luca P. Carloni. 2017. Accelerators for breast cancer detection. ACM Trans. Embed. Comput. Syst. 16, 380 (March 2017). DOI:DOI:https://doi.org/10.1145/2983630Google Scholar
- Maria Papadogiorgaki, Panagiotis Koliou, Xenofon Kotsiakis, and Michalis E. Zervakis. 2013. Mathematical modelling of spatio-temporal glioma evolution. Theor. Biol. Med. Modell. 10, 1 (24 July 2013), 47. DOI:DOI:https://doi.org/10.1186/1742-4682-10-47Google Scholar
- Maria Papadogiorgaki, Panagiotis Koliou, and Michalis E. Zervakis. 2018. Glioma growth modeling based on the effect of vital nutrients and metabolic products. Med. Biol. Eng. Comput. 56, 9 (01 Sep. 2018), 1683–1697. DOI:DOI:https://doi.org/10.1007/s11517-018-1809-0Google Scholar
- Emanuele Pezzotti, Alex Iacobucci, Gregory Nash, Umer Cheema, Paolo Vinella, and Rashid Ansari. 2017. FPGA-based hardware accelerator for image reconstruction in magnetic resonance imaging (abstract only). In Proceedings of the ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA’17). Association for Computing Machinery, New York, NY, 293. DOI:DOI:https://doi.org/10.1145/3020078.3021793Google Scholar
- G. Ramya and S. Bhuvaneshwari. 2015. FPGA based implementation of edge and corner detection in MRI brain tumor image. https://www.semanticscholar.org/paper/FPGA-Based-Implementation-of-Edge-and-Corner-in-MRI-Ramya-Bhuvaneshwari/8a51b82bf87285fc7d81e8491f3b8378fe1d66ef.Google Scholar
- Katarzyna A. Rejniak and Alexander R. A. Anderson. 2011. Hybrid models of tumor growth. WIREs Syst. Biol. Med. 3, 1 (2011), 115–125. DOI:DOI:https://doi.org/10.1002/wsbm.102Google Scholar
- Torsten Rohlfing, Natalie M. Zahr, Edith V. Sullivan, and Adolf Pfefferbaum. 2010. The SRI24 multichannel atlas of normal adult human brain structure. Hum. Brain Map. 31, 5 (2010), 798–819. DOI:DOI:https://doi.org/10.1002/hbm.20906Google Scholar
Cross Ref
- A. Roniotis, G. C. Manikis, V. Sakkalis, M. E. Zervakis, I. Karatzanis, and K. Marias. 2012. High-grade glioma diffusive modeling using statistical tissue information and diffusion tensors extracted from atlases. IEEE Trans. Inf. Technol. Biomed. 16, 2 (2012), 255–263. DOI:DOI:https://doi.org/10.1109/TITB.2011.2171190Google Scholar
Digital Library
- Tiina Roose, S. Jonathan Chapman, and Philip K. Maini. 2007. Mathematical models of avascular tumor growth. SIAM Rev. 49, 2 (2007), 179–208. DOI:DOI:https://doi.org/10.1137/S0036144504446291arXiv:https://doi.org/10.1137/S0036144504446291Google Scholar
Digital Library
- Kieran Smallbone, Robert A. Gatenby, and Philip K. Maini. 2008. Mathematical modelling of tumour acidity. J. Theor. Biol. 255, 1 (2008), 106–112. DOI:DOI:https://doi.org/10.1016/j.jtbi.2008.08.002Google Scholar
Cross Ref
- Kristin R. Swanson, Carly Bridge, J. D. Murray, and Ellsworth C. Alvord. 2003. Virtual and real brain tumors: Using mathematical modeling to quantify glioma growth and invasion. J. Neurol. Sci. 216, 1 (2003), 1–10. DOI:DOI:https://doi.org/10.1016/j.jns.2003.06.001Google Scholar
Cross Ref
- Kristin R. Swanson, Russell C. Rockne, Jonathan Claridge, Mark A. Chaplain, Ellsworth C. Alvord, and Alexander R.A. Anderson. 2011. Quantifying the role of angiogenesis in malignant progression of gliomas: In silico modeling integrates imaging and histology. Cancer Res. 71, 24 (2011), 7366–7375. DOI:DOI:https://doi.org/10.1158/0008-5472.CAN-11-1399Google Scholar
- Mindy D. Szeto, Gargi Chakraborty, Jennifer Hadley, Russ Rockne, Mark Muzi, Ellsworth C. Alvord, Kenneth A. Krohn, Alexander M. Spence, and Kristin R. Swanson. 2009. Quantitative metrics of net proliferation and invasion link biological aggressiveness assessed by MRI with hypoxia assessed by FMISO-PET in newly diagnosed glioblastomas. Cancer Res. 69, 10 (2009), 4502–4509. DOI:DOI:https://doi.org/10.1158/0008-5472.CAN-08-3884Google Scholar
Cross Ref
- E. Tzamali, R. Favicchio, A. Roniotis, G. Tzedakis, G. Grekas, J. Ripoll, K. Marias, G. Zacharakis, and V. Sakkalis. 2013. Employing in-vivo molecular imaging in simulating and validating tumor growth. In Proceedings of the 35th International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’13). 5533–5536. DOI:DOI:https://doi.org/10.1109/EMBC.2013.6610803Google Scholar
- Wikipedia contributors. 2021. Dell DRAC — Wikipedia, The Free Encyclopedia. Retrieved from https://en.wikipedia.org/w/index.php?title=Dell_DRAC&oldid=1002380717.Google Scholar
Index Terms
Novel Reconfigurable Hardware Systems for Tumor Growth Prediction
Recommendations
A novel FPGA-based system for tumor growth prediction
DATE '20: Proceedings of the 23rd Conference on Design, Automation and Test in EuropeAn emerging trend in the biomedical community is to create models that take advantage of the increasing available computational power, in order to manage and analyze new biological data as well as to model complex biological processes. Such biomedical ...
A CNN accelerator on embedded FPGA using dynamic reconfigurable coprocessor
AIIPCC '19: Proceedings of the International Conference on Artificial Intelligence, Information Processing and Cloud ComputingConvolutional neural network (CNN) has been widely deployed in deep learning networks at present. However, numerous convolution operations are computing intensive and often require powerful accelerator such as FPGA. The existed accelerators usually as ...






Comments