ABSTRACT
We present SIBIA (Scalable Integrated Biophysics-based Image Analysis), a framework for coupling biophysical models with medical image analysis. It provides solvers for an image-driven inverse brain tumor growth model and an image registration problem, the combination of which can eventually help in diagnosis and prognosis of brain tumors. The two main computational kernels of SIBIA are a Fast Fourier Transformation (FFT) implemented in the library AccFFT to discretize differential operators, and a cubic interpolation kernel for semi-Lagrangian based advection. We present efficiency and scalability results for the computational kernels, the inverse tumor solver and image registration on two x86 systems, Lonestar 5 at the Texas Advanced Computing Center and Hazel Hen at the Stuttgart High Performance Computing Center. We showcase results that demonstrate that our solver can be used to solve registration problems of unprecedented scale, 40963 resulting in ∼ 200 billion unknowns---a problem size that is 64X larger than the state-of-the-art. For problem sizes of clinical interest, SIBIA is about 8X faster than the state-of-the-art.
- E D Angelini, O Clatz, E Mandonnet, E Konukoglu, L Capelle, and H Duffau. 2007. Glioma dynamics and computational models: A review of segmentation, registation, in silico growth algorithms and their clinical applications. Curr Med Imaging Rev 3, 4 (2007), 262--276.Google ScholarCross Ref
- J. Ashburner and K. J. Friston. 2011. Diffeomorphic registration using geodesic shooting and Gauss-Newton optimisation. NeuroImage 55, 3 (2011), 954--967.Google ScholarCross Ref
- S. Balay, S. Abhyankar, M. F. Adams, J. Brown, P. Brune, K. Buschelman, L. Dalcin, V. Eijkhout, W. D. Gropp, D. Kaushik, M. G. Knepley, L. C. McInnes, K. Rupp, B. F. Smith, S. Zampini, and H. Zhang. 2016. PETSc users manual. Technical Report ANL-95/11 - Revision 3.7. Argonne National Laboratory.Google Scholar
- V. Barbu and G. Marinoschi. 2016. An optimal control approach to the optical flow problem. Systems & Control Letters 87 (2016), 1--9.Google ScholarCross Ref
- S. Bauer, R. Wiest, L.-P. Nolte, and M. Reyes. 2013. A survey of MRI-based medical image analysis for brain tumor studies. Physics in medicine and biology 58, 13 (2013), R97.Google Scholar
- M. F. Beg, M. I. Miller, A. Trouvé, and L. Younes. 2005. Computing large deformation metric mappings via geodesic flows of diffeomorphisms. International Journal of Computer Vision 61, 2 (2005), 139--157. Google ScholarDigital Library
- L. T. Biegler, O. Ghattas, M. Heinkenschloss, and B. van Bloemen Waanders. 2003. Large-scale PDE-constrained optimization. Springer.Google Scholar
- A. Borzì, K. Ito, and K. Kunisch. 2002. Optimal control formulation for determining optical flow. SIAM Journal on Scientific Computing 24, 3 (2002), 818--847. Google ScholarDigital Library
- A. Borzì and V. Schulz. 2012. Computational optimization of systems governed by partial differential equations. SIAM, Philadelphia, Pennsylvania, US. Google ScholarDigital Library
- K. Chen and D. A. Lorenz. 2011. Image sequence interpolation using optimal control. Journal of Mathematical Imaging and Vision 41 (2011), 222--238. Google ScholarDigital Library
- G. E. Christensen, X. Geng, J. G. Kuhl, J. Bruss, T. J. Grabowski, I. A. Pirwani, M. W. Vannier, J. S. Allen, and H. Damasio. 2006. Introduction to the non-rigid image registration evaluation project. In Proc Biomedical Image Registration, Vol. LNCS 4057. 128--135. Google ScholarDigital Library
- O. Clatz, M. Sermesant, P. Y. Bondiau, H. Delingette, S. K. Warfield, G. Malandain, and N. Ayache. 2005. Realistic simulation of the 3D growth of brain tumors in MR images coupling diffusion with biomechanical deformation. IEEE Transactions on Medical Imaging 24, 10 (2005), 1334--1346.Google ScholarCross Ref
- V. Collins. 1998. Gliomas. Cancer Survey, vol. 32, pp. 37--51 (1998).Google Scholar
- K.D. Costa, J.W. Holmes, and A.D. McCulloch. 2001. Modeling cardiac mechanical properties in three dimensions. Philosophical Transactions of the Royal Society A 359 (2001), 1233--1250.Google ScholarCross Ref
- Cotin, S. and Delingette, H. and Ayache, N. 1999. Real-time elastic deformations of soft tissues for surgery simulation. IEEE Transactions On Visualization And Computer Graphics 5, 1 (1999), 62--73. Google ScholarDigital Library
- K. Czechowski, C. Battaglino, C. McClanahan, K. Iyer, P.-K. Yeung, and R. Vuduc. 2012. On the communication complexity of 3D FFTs and its implications for exascale. In Proc ACM/IEEE Conference on Supercomputing. 205--214. Google ScholarDigital Library
- S. C. Eisentat and H. F. Walker. 1996. Choosing the forcing terms in an inexact Newton method. SIAM Journal on Scientiic Computing 17, 1 (1996), 16--32. Google ScholarDigital Library
- M. Falcone and R. Ferretti. 1998. Convergence analysis for a class of high-order semi-Lagrangian advection schemes. SIAM J. Numer. Anal. 35, 3 (1998), 909--940. Google ScholarDigital Library
- Ferrant, M. and Nabavi, A. and Macq, B. and Jolesz, F.A. and Kikinis, R. and Warfield, S.K. 2001. Registration of 3-D intraoperative MR images of the brain using a finite-element biomechanical model. IEEE Transactions On Medical Imaging 20, 12 (2001), 1384--1397.Google ScholarCross Ref
- B. Fischer and J. Modersitzki. 2008. Ill-posed medicine --- an introduction to image registration. Inverse Problems 24, 3 (2008), 1--16.Google ScholarCross Ref
- D.T. Gering, A. Nabavi, R. Kikinis, N. Hata, L.J. Donnell, and W.E. Grimson. 2001. An integrated visualization system for surgical planning and guidance using image fusion and an open MR. Journal of Magnetic Resonance Imaging 13, 6 (2001), 967--975.Google ScholarCross Ref
- A. Gholami. 2017. Fast Algorithms for Biophysically-Constrained Inverse Problems in Medical imaging. Ph.D. Dissertation. The University of Texas at Austin.Google Scholar
- A. Gholami and G. Biros. 2017. AccFFT. (2017). https://github.com/amirgholami/accfftGoogle Scholar
- A. Gholami, J. Hill, D. Malhotra, and G. Biros. 2016. AccFFT: A library for distributed-memory FFT on CPU and GPU architectures. arXiv e-prints (2016). in review (arXiv preprint: http://arxiv.org/abs/1506.07933);.Google Scholar
- A. Gholami, A. Mang, and G. Biros. 2016. An inverse problem formulation for parameter estimation of a reaction-diffusion model of low grade gliomas. Journal of Mathematical Biology 72, 1 (2016), 409--433.Google ScholarCross Ref
- A. Gooya, K.M. Pohl, M. Bilello, G. Biros, and C. Davatzikos. 2011. Joint Segmentation and Deformable Registration of Brain Scans Guided by a Tumor Growth Model. In Medical Image Computing and Computer-Assisted Intervention - MICCAI 2011. Lecture Notes in Computer Science, Vol. 6892. Springer Berlin Heidelberg, 532--540. Google ScholarDigital Library
- A. Gooya, K. M. Pohl, M. Bilello, L. Cirillo, G. Biros, E. R. Melhem, and C. Davatzikos. 2013. GLISTR: Glioma image segmentation and registration. Medical Imaging, IEEE Transactions on 31, 10 (2013), 1941--1954.Google ScholarCross Ref
- A. Grama, A. Gupta, G. Karypis, and V. Kumar. 2003. An Introduction to parallel computing: Design and analysis of algorithms (second ed.). Addison Wesley.Google Scholar
- Per Christian Hansen. 2010. Discrete inverse problems: Insight and algorithms. SIAM. Google ScholarDigital Library
- G. L. Hart, C. Zach, and M. Niethammer. 2009. An optimal control approach for deformable registration. In Proc IEEE Conference on Computer Vision and Pattern Recognition. 9--16.Google Scholar
- A. Hawkins-Daarud, R. C. Rockne, A. R. A. Anderson, and K. R. Swanson. 2013. Modeling tumor-associated edema in gliomas during anti-angiogenic therapy and its imapct on imageable tumor. Front Oncol 3, 66 (2013).Google Scholar
- J. Hinkle, P. T. Fletcher, B. Wang, B. Salter, and S. Joshi. 2009. 4D MAP image reconstruction incorporating organ motion. In Proc Information Processing in Medical Imaging. 676--687. Google ScholarDigital Library
- M. Hinze, R. Pinnau, M. Ulbrich, and S. Ulbrich. 2009. Optimization with PDE constraints. Springer, Berlin, DE.Google Scholar
- C.S. Hogea, F. Abraham, G. Biros, and C. Davatzikos. 2006. A Framework for Soft Tissue Simulations with Applications to Modeling Brain Tumor Mass-Effect in 3D Images. In Medical Image Computing and Computer-Assisted Intervention Workshop on Biomechanics. Copenhagen.Google Scholar
- C. Hogea, C. Davatzikos, and G. Biros. 2008. Brain-tumor interaction biophysical models for medical image registration. SIAM J Imag Sci 30, 6 (2008), 3050--3072. Google ScholarDigital Library
- S. Ivkovic, C. Beadle, S. Noticewala, S.C. Massey, K.R. Swanson, L.N. Toro, A.R. Bresnick, P. Canoll, and S.S. Rosenfeld. 2012. Direct inhibition of myosin II effectively blocks glioma invasion in the presence of multiple motogens. Molecular biology of the cell 23, 4 (2012), 533--542.Google Scholar
- A. Kirsch. 2011. An introduction to the mathematical theory of inverse problems. Springer. Google ScholarDigital Library
- E. Konukoglu, O. Clatz, P. Y. Bondiau, H. Delingette, and N. Ayache. 2010. Extrapolating glioma invasion margin in brain magnetic resonance images: Suggesting new irradiation margins. Medical Image Analysis 14, 2 (2010), 111--125.Google ScholarCross Ref
- E. Konukoglu, O. Clatz, B. H. Menze, M. A. Weber, B. Stieltjes, E. Mandonnet, H. Delingette, and N. Ayache. 2010. Image guided personalization of reaction-diffusion type tumor growth models using modified anisotropic eikonal equations. IEEE Trans Med Imaging 29, 1 (2010), 77--95.Google ScholarCross Ref
- K. S. Kutten, N. Charon, M. I. Miller, J. T. Ratnanather, K. Deisseroth, L. Ye, and J. T. Vogelstein. 2016. A diffeomorphic approach to multimodal registration with mutual information: Applications to CLARITY mouse brain images. ArXiv e-prints (2016).Google Scholar
- E. Lee and M. Gunzburger. 2010. An optimal control formulation of an image registration problem. Journal of Mathematical Imaging and Vision 36, 1 (2010), 69--80. Google ScholarDigital Library
- J. L. Lions. 1971. Optimal control of systems governed by partial differential equations. Springer.Google Scholar
- X. Ma, H. Gao, B.E. Griffith, C. Berry, and X. Luo. 2013. Image-based fluid-structure interaction model of the human mitral valve. Computers & Fluids 71 (2013), 417--425.Google ScholarCross Ref
- A. Mang and G. Biros. 2015. An inexact Newton-Krylov algorithm for constrained diffeomorphic image registration. SIAM Journal on Imaging Sciences 8, 2 (2015), 1030--1069.Google ScholarDigital Library
- A. Mang and G. Biros. 2016. Constrained H1-regularization schemes for diffeomorphic image registration. SIAM Journal on Imaging Sciences 9, 3 (2016), 1154--1194.Google ScholarDigital Library
- A. Mang and G. Biros. 2016. A Semi-Lagrangian two-level preconditioned Newton-Krylov solver for constrained diffeomorphic image registration. arXiv e-prints (2016). in review (arXiv preprint: http://arxiv.org/abs/1604.02153).Google Scholar
- A. Mang, A. Gholami, and G. Biros. 2016. Distributed-memory large-deformation diffeomorphic 3D image registration. In Proc ACM/IEEE Conference on Supercomputing. Google ScholarDigital Library
- A. Mang, A. Toma, T. A. Schuetz, S. Becker, T. Eckey, C. Mohr, D. Petersen, and T. M. Buzug. 2012. Biophysical modeling of brain tumor progression: from unconditionally stable explicit time integration to an inverse problem with parabolic PDE constraints for model calibration. Medical Physics 39, 7 (2012), 4444--4459.Google ScholarCross Ref
- J. Markert, V. Devita, S. Rosenberg, and S. Hellman. 2005. Gliobalastoma Multi-forme. Burlington, MA: Jones Bartlett (2005).Google Scholar
- B. H. Menze, A. Jakab, S. Bauer, J. Kalpathy-Cramer, K. Farahani, et al. 2015. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Transactions on Medical Imaging 34, 10 (2015), 1993--2024.Google ScholarCross Ref
- B. H. Menze, K. V. Leemput, E. Konukoglu, A. Honkela, M.-A. Weber, N. Ayache, and P. Golland. 2011. A generative approach for image-based modeling of tumor growth. In Proc Information Processing in Medical Imaging, Vol. 22. 735--747. Google ScholarDigital Library
- J. Modersitzki. 2004. Numerical methods for image registration. Oxford University Press, New York.Google Scholar
- J. Modersitzki. 2009. FAIR: Flexible algorithms for image registration. SIAM, Philadelphia, Pennsylvania, US. Google ScholarDigital Library
- T. Munson, J. Sarich, S. Wild, S. Benson, and L. C. McInnes. 2015. TAO 3.6 Users Manual. Argonne National Laboratory, Mathematics and Computer Science Division.Google Scholar
- J. Nocedal and S. J. Wright. 2006. Numerical Optimization. Springer, New York, New York, US.Google Scholar
- T. Riklin-Raviv, K. Van Leemput, B.H. Menze, W.M. Wells III, and P. Golland. 2010. Segmentation of image ensembles via latent atlases. Medical image analysis 14, 5 (2010), 654.Google Scholar
- M. Sermesant, H. Delingette, and N. Ayache. 2006. An Electromechanical Model of the Heart for Image Analysis and Simulation. IEEE Transactions in Medical Imaging 25, 5 (2006), 612--625.Google ScholarCross Ref
- M. Sermesant, P. Moireau, O. Camara, J. Sainte-Marie, R. Andriantsimiavona, R. Cimrman, D.L. Hill, D. Chapelle, and R. Razavi. 2006. Cardiac function estimation from MRI using a heart model and data assimilation: Advances and difficulties. Medical Image Analysis 10, 4 (2006), 642--656.Google ScholarCross Ref
- A. Sotiras, C. Davatzikos, and N. Paragios. 2013. Deformable medical image registration: A survey. Medical Imaging, IEEE Transactions on 32, 7 (2013), 1153--1190.Google ScholarCross Ref
- K. R. Swanson, E. C. Alvord, and J. D. Murray. 2000. A quantitative model for differential motility of gliomas in grey and white matter. Cell Proliferation 33, 5 (2000), 317--330.Google ScholarCross Ref
- K. R. Swanson, H. L. Harpold, D. L. Peacock, R. Rockne, C. Pennington, L. Kilbride, R. Grant, J. M. Wardlaw, and E. C. Alvord. 2008. Velocity of radial expansion of contrast-enhancing gliomas and the effectiveness of radiotherapy in individual patients: A proof of principle. Clin Oncol (R Coll Radiol) 20, 4 (2008), 301--308.Google ScholarCross Ref
- Raju Tomer, Li Ye, Brian Hsueh, and Karl Deisseroth. 2014. Advanced CLARITY for rapid and high-resolution imaging of intact tissues. Nature protocols 9, 7 (2014), 1682--1697.Google Scholar
- Northwestern University and Argonne National Laboratory. 2017. PnetCDF: https://trac.mcs.anl.gov/projects/parallel-netcdf. (2017).Google Scholar
- F.-X. Vialard, L. Risser, D. Rueckert, and C. J. Cotter. 2012. Diffeomorphic 3D image registration via geodesic shooting using an efficient adjoint calculation. International Journal of Computer Vision 97 (2012), 229--241. Google ScholarDigital Library
- Warfield, S.K. and Talos, F. and Kemper, C. and O'Donnell, L. and Westin, C.F. and Wells W.M. and Black, P. Mc L. and Jolesz, F.A. and Kikinis, R. 2003. Capturing brain deformation (Surgery Simulation and Soft Tissue Modeling. International Symposium, IS4TM 2003. Proceedings (Lecture Notes in Comput. Sci. Vol.2673)). Springer-Verlag, Juan-Les-Pins, France, 203. Google ScholarDigital Library
- L. Weizman, L. Sira, L. Joskowicz, S. Constantini, R. Precel, B. Shortly, and D. Bashat. 2012. Automatic segmentation, internal classification, and follow-up of optic pathway gliomas in MRI. Med. Image Anal., vol. 16, pp. 177--188 (2012).Google ScholarCross Ref
- K.C.L. Wong, L. Wang, H. Zhang, H. Liu, and P. Shi. 2007. Integrating Functional and Structural Images for Simultaneous Cardiac Segmentation and Deformation Recovery. In Medical Image Computing and Computer-Assisted Intervention - MICCAI 2007 (LNCS), Nicholas Ayache, Sébastien Ourselin, and Anthony Maeder (Eds.), Vol. 4791. Springer, 270--277. Google ScholarDigital Library
- T.E. Yankeelov, N. Atuegwu, D. Hormuth, J.A. Weis, S.L. Barnes, M.I. Miga, E.C. Rericha, and V. Quaranta. 2013. Clinically relevant modeling of tumor growth and treatment response. Science translational medicine 5, 187 (2013), 187ps9--187ps9.Google Scholar
- E. I. Zacharaki, C. S. Hogea, D. Shen, G. Biros, and C. Davatzikos. 2009. Non-diffeomorphic registration of brain tumor images by simulating tissue loss and tumor growth. NeuroImage 46, 3 (2009), 762--774.Google ScholarCross Ref
Index Terms
- A framework for scalable biophysics-based image analysis
Recommendations
Object density-based image segmentation and its applications in biomedical image analysis
In many applications of medical image analysis, the density of an object is the most important feature for isolating an area of interest (image segmentation). In this research, an object density-based image segmentation methodology is developed, which ...
Scalable joint segmentation and registration framework for infant brain images
The first year of life is the most dynamic and perhaps the most critical phase of postnatal brain development. The ability to accurately measure structure changes is critical in early brain development study, which highly relies on the performances of ...
Comments