Brain Tumor Cell Density Estimation from Multi-modal MR Images Based on a Synthetic Tumor Growth Model

This paper proposes to employ a detailed tumor growth model to synthesize labelled images which can then be used to train an efficient data-driven machine learning tumor predictor. Our MR image synthesis step generates images with both healthy tissues as well as various tumoral tissue types. Subsequently, a discriminative algorithm based on random regression forests is trained on the simulated ground truth to predict the continuous latent tumor cell density, and the discrete tissue class associated with each voxel. The presented method makes use of a large synthetic dataset of 740 simulated cases for training and evaluation. A quantitative evaluation on 14 real clinical cases diagnosed with low-grade gliomas demonstrates tissue class accuracy comparable with state of the art, with added benefit in terms of computational efficiency and the ability to estimate tumor cell density as a latent variable underlying the multimodal image observations. The idea of synthesizing training data to train data-driven learning algorithms can be extended to other applications where expert annotation is lacking or expensive.

[1]  Dinggang Shen,et al.  Non-diffeomorphic registration of brain tumor images by simulating tissue loss and tumor growth , 2009, NeuroImage.

[2]  Olivier Clatz,et al.  Glioma Dynamics and Computational Models: A Review of Segmentation, Registration, and In Silico Growth Algorithms and their Clinical Applications , 2007 .

[3]  Ron Kikinis,et al.  Statistical Validation of Automated Probabilistic Segmentation against Composite Latent Expert Ground Truth in MR Imaging of Brain Tumors , 2002, MICCAI.

[4]  Christos Davatzikos,et al.  Joint Segmentation and Deformable Registration of Brain Scans Guided by a Tumor Growth Model , 2011, MICCAI.

[5]  Georg Langs,et al.  Medical Computer Vision , 2011 .

[6]  Gustavo Carneiro,et al.  A Discriminative Model-Constrained Graph Cuts Approach to Fully Automated Pediatric Brain Tumor Segmentation in 3-D MRI , 2008, MICCAI.

[7]  Hervé Delingette,et al.  Realistic simulation of the 3-D growth of brain tumors in MR images coupling diffusion with biomechanical deformation , 2005, IEEE Transactions on Medical Imaging.

[8]  Sébastien Ourselin,et al.  Computation of the mid-sagittal plane in 3-D brain images , 2002, IEEE Transactions on Medical Imaging.

[9]  Guido Gerig,et al.  Simulation of brain tumors in MR images for evaluation of segmentation efficacy , 2009, Medical Image Anal..

[10]  Vittorio Cristini,et al.  Multiscale Modeling of Cancer: An Integrated Experimental and Mathematical Modeling Approach , 2010 .

[11]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[12]  Meritxell Bach Cuadra,et al.  A review of atlas-based segmentation for magnetic resonance brain images , 2011, Comput. Methods Programs Biomed..

[13]  Yongyi Yang,et al.  Machine Learning in Medical Imaging , 2010, IEEE Signal Processing Magazine.

[14]  Vittorio Cristini,et al.  Multiscale cancer modeling. , 2010, Annual review of biomedical engineering.

[15]  Koenraad Van Leemput,et al.  Automated segmentation of multiple sclerosis lesions by model outlier detection , 2001, IEEE Transactions on Medical Imaging.

[16]  Nassir Navab,et al.  Medical Image Computing and Computer-Assisted Intervention - MICCAI 2010, 13th International Conference, Beijing, China, September 20-24, 2010, Proceedings, Part III , 2010, MICCAI.

[17]  Dimitris N. Metaxas,et al.  Entangled Decision Forests and Their Application for Semantic Segmentation of CT Images , 2011, IPMI.

[18]  J. Shotton,et al.  Decision Forests for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning , 2011 .

[19]  Nicholas Ayache,et al.  A Generative Model for Brain Tumor Segmentation in Multi-Modal Images , 2010, MICCAI.

[20]  Mark Jenkinson,et al.  Non-local Shape Descriptor: A New Similarity Metric for Deformable Multi-modal Registration , 2011, MICCAI.

[21]  Koenraad Van Leemput,et al.  Segmentation of image ensembles via latent atlases , 2010, Medical Image Anal..

[22]  Gabor Fichtinger,et al.  Medical Image Computing and Computer-Assisted Intervention - MICCAI 2008, 11th International Conference, New York, NY, USA, September 6-10, 2008, Proceedings, Part I , 2008, International Conference on Medical Image Computing and Computer-Assisted Intervention.

[23]  Guido Gerig,et al.  A brain tumor segmentation framework based on outlier detection , 2004, Medical Image Anal..

[24]  Julie Delon,et al.  Differential MRI analysis for quantification of low grade glioma growth , 2012, Medical Image Anal..

[25]  Ron Kikinis,et al.  Medical Image Computing and Computer-Assisted Intervention — MICCAI 2002 , 2002, Lecture Notes in Computer Science.

[26]  Olivier Clatz,et al.  Spatial decision forests for MS lesion segmentation in multi-channel magnetic resonance images , 2011, NeuroImage.

[27]  Antonio Criminisi,et al.  Regression Forests for Efficient Anatomy Detection and Localization in CT Studies , 2010, MCV.

[28]  Alan L. Yuille,et al.  Efficient Multilevel Brain Tumor Segmentation With Integrated Bayesian Model Classification , 2008, IEEE Transactions on Medical Imaging.

[29]  Antti Honkela,et al.  A Generative Approach for Image-Based Modeling of Tumor Growth , 2011, IPMI.

[30]  Andrew W. Fitzgibbon,et al.  Real-time human pose recognition in parts from single depth images , 2011, CVPR 2011.

[31]  Chi-Hoon Lee,et al.  Segmenting Brain Tumors Using Pseudo-Conditional Random Fields , 2008, MICCAI.

[32]  Dinu Coltuc,et al.  Exact histogram specification , 2006, IEEE Transactions on Image Processing.

[33]  Daniel Rueckert,et al.  Random Forest-Based Manifold Learning for Classification of Imaging Data in Dementia , 2011, MLMI.