Multi-resolution super learner for voxel-wise classification of prostate cancer using multi-parametric MRI

Abstract

Multi-parametric MRI (mpMRI) is a critical tool in prostate cancer (PCa) diagnosis and management. To further advance the use of mpMRI in patient care, computer aided diagnostic methods are under continuous development for supporting/supplanting standard radiological interpretation. While voxel-wise PCa classification models are the gold standard, few if any approaches have incorporated the inherent structure of the mpMRI data, such as spatial heterogeneity and between-voxel correlation, into PCa classification. We propose a machine learning-based method to fill in this gap. Our method uses an ensemble learning approach to capture regional heterogeneity in the data, where classifiers are developed at multiple resolutions and combined using the super learner algorithm, and further account for between-voxel correlation through a Gaussian kernel smoother. It allows any type of classifier to be the base learner and can be extended to further classify PCa sub-categories. We introduce the algorithms for binary PCa classification, as well as for classifying the ordinal clinical significance of PCa for which a weighted likelihood approach is implemented to improve the detection of less prevalent cancer categories. The proposed method has shown important advantages over conventional modeling and machine learning approaches in simulations and application to our motivating patient data.

Keywords:

• Multi-parametric MRI
• multi-resolution modeling
• ordinal clinical significance of PCa
• super learner
• voxel-wise PCa classification

Mathematics subject classifications:

• 62
• 62P10

Acknowledgments

Opinions, interpretations, conclusions, and recommendations are those of the author and are not necessarily endorsed by the Department of Defense.

Code availability

The R code for implementing of the proposed classification algorithms are available at https://github.com/Jin93/Multi-Resolution-SL.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by National Cancer Institute NCI R01 CA155268, NCI P30 CA077598, National Institute of Biomedical Imaging and Bioengineering NIBIB P41 EB027061, and the Assistant Secretary of Defense for Health affairs, through the Prostate Cancer Research Program under Award No. W81XWH-15-1-0478.