Boost-S: Gradient Boosted Trees for Spatial Data and Its Application to FDG-PET Imaging Data

TL;DR

Boost-S introduces a novel gradient boosted trees algorithm tailored for spatially correlated data, effectively incorporating spatial structure into the ensemble learning process, demonstrated on FDG-PET imaging data in cancer treatment.

Contribution

This paper develops the first gradient boosted trees method for spatial data, integrating spatial correlation into the boosting framework with an efficient algorithm.

Findings

Boost-S outperforms existing methods on FDG-PET imaging data.

Incorporating spatial correlation improves predictive accuracy.

The algorithm is computationally efficient for large spatial datasets.

Abstract

Boosting Trees are one of the most successful statistical learning approaches that involve sequentially growing an ensemble of simple regression trees (i.e., "weak learners"). However, gradient boosted trees are not yet available for spatially correlated data. This paper proposes a new gradient Boosted Trees algorithm for Spatial Data (Boost-S) with covariate information. Boost-S integrates the spatial correlation structure into the classical framework of gradient boosted trees. Each tree is grown by solving a regularized optimization problem, where the objective function involves two penalty terms on tree complexity and takes into account the underlying spatial correlation. A computationally-efficient algorithm is proposed to obtain the ensemble trees. The proposed Boost-S is applied to the spatially-correlated FDG-PET (fluorodeoxyglucose-positron emission tomography) imaging data collected during cancer chemoradiotherapy. Our numerical investigations successfully demonstrate the advantages of the proposed Boost-S over existing approaches for this particular application.