Multi-resolution Super Learner for Voxel-wise Classification of Prostate Cancer Using Multi-parametric MRI

TL;DR

This paper introduces a multi-resolution super learner method that improves voxel-wise prostate cancer classification using multi-parametric MRI by modeling regional heterogeneity and spatial correlations.

Contribution

It presents a novel multi-resolution modeling framework with super learner and spatial Gaussian kernel smoothing for enhanced prostate cancer voxel classification.

Findings

Outperforms conventional models in simulations

Effective in classifying binary prostate cancer status

Extends to ordinal clinical significance detection

Abstract

While current research has shown the importance of Multi-parametric MRI (mpMRI) in diagnosing prostate cancer (PCa), further investigation is needed for how to incorporate the specific structures of the mpMRI data, such as the regional heterogeneity and between-voxel correlation within a subject. This paper proposes a machine learning-based method for improved voxel-wise PCa classification by taking into account the unique structures of the data. We propose a multi-resolution modeling approach to account for regional heterogeneity, where base learners trained locally at multiple resolutions are combined using the super learner, and account for between-voxel correlation by efficient spatial Gaussian kernel smoothing. The method is flexible in that the super learner framework allows implementation of any classifier as the base learner, and can be easily extended to classifying cancer into more sub-categories. We describe detailed classification algorithm for the binary PCa status, as well as the ordinal clinical significance of PCa for which a weighted likelihood approach is implemented to enhance the detection of the less prevalent cancer categories. We illustrate the advantages of the proposed approach over conventional modeling and machine learning approaches through simulations and application to in vivo data.