Discovery Radiomics via a Mixture of Deep ConvNet Sequencers for Multi-parametric MRI Prostate Cancer Classification

Prostate cancer is the most diagnosed form of cancer in men, but prognosis is relatively good with a sufficiently early diagnosis. Radiomics has been shown to be a powerful prognostic tool for cancer detection; however, these radiomics-driven methods currently rely on hand-crafted sets of quantitative imaging-based features, which can limit their ability to fully characterize unique prostate cancer tumour traits. We present a novel discovery radiomics framework via a mixture of deep convolutional neural network (ConvNet) sequencers for generating custom radiomic sequences tailored for prostate cancer detection. We evaluate the performance of the mixture of ConvNet sequencers against state-of-the-art hand-crafted radiomic sequencers for binary computer-aided prostate cancer classification using real clinical prostate multi-parametric MRI data. Results for the mixture of ConvNet sequencers demonstrate good performance in prostate cancer classification relative to the hand-crafted radiomic sequencers, and show potential for more efficient and reliable automatic prostate cancer classification.

[1]  Masoom A. Haider,et al.  Discovery Radiomics for Imaging-driven Quantitative Personalized Cancer Decision Support , 2015 .

[2]  Xin Liu,et al.  Prostate Cancer Segmentation With Simultaneous Estimation of Markov Random Field Parameters and Class , 2009, IEEE Transactions on Medical Imaging.

[3]  P. Lambin,et al.  Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach , 2014, Nature Communications.

[4]  Olivier Gevaert,et al.  Non-small cell lung cancer: identifying prognostic imaging biomarkers by leveraging public gene expression microarray data--methods and preliminary results. , 2012, Radiology.

[5]  Masoom A. Haider,et al.  Prostate Cancer Localization With Multispectral MRI Using Cost-Sensitive Support Vector Machines and Conditional Random Fields , 2010, IEEE Transactions on Image Processing.

[6]  Masoom A. Haider,et al.  Prostate cancer localization with multispectral MRI based on Relevance Vector Machines , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[7]  Masoom A. Haider,et al.  Discovery Radiomics for Multi-Parametric MRI Prostate Cancer Detection , 2015, ArXiv.

[8]  Masoom A. Haider,et al.  A Multi-Parametric Diffusion Magnetic Resonance Imaging Texture Feature Model for Prostate Cancer Analysis , 2014 .

[9]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[10]  Dimitris N. Metaxas,et al.  Automated detection of prostatic adenocarcinoma from high-resolution ex vivo MRI , 2005, IEEE Transactions on Medical Imaging.

[11]  Masoom A. Haider,et al.  Automated prostate cancer detection via comprehensive multi-parametric magnetic resonance imaging texture feature models , 2015, BMC Medical Imaging.

[12]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[13]  Patrick Granton,et al.  Radiomics: extracting more information from medical images using advanced feature analysis. , 2012, European journal of cancer.

[14]  M. Mostafizur Rahman,et al.  Addressing the Class Imbalance Problem in Medical Datasets , 2013 .

[15]  Yongyi Yang,et al.  Supervised and unsupervised methods for prostate cancer segmentation with multispectral MRI. , 2010, Medical physics.

[16]  Francisco Herrera,et al.  A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based Approaches , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[17]  N Karssemeijer,et al.  Automatic computer-aided detection of prostate cancer based on multiparametric magnetic resonance image analysis , 2012, Physics in medicine and biology.

[18]  Masoom A. Haider,et al.  Discovery Radiomics for Computed Tomography Cancer Detection , 2015, ArXiv.

[19]  Masoom A. Haider,et al.  Discovery Radiomics via StochasticNet Sequencers for Cancer Detection , 2015, ArXiv.

[20]  P. Lambin,et al.  Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach , 2014, Nature Communications.

[21]  Maryellen L. Giger,et al.  A study of T2-weighted MR image texture features and diffusion-weighted MR image features for computer-aided diagnosis of prostate cancer , 2013, Medical Imaging.