Reduced-Reference Learning for Target Localization in Deep Brain Stimulation

This work proposes a supervised machine learning method for target localization in deep brain stimulation (DBS). DBS is a recognized treatment for essential tremor. The effects of DBS significantly depend on the precise implantation of electrodes. Recent research on diffusion tensor imaging shows that the optimal target for essential tremor is related to the dentato-rubro-thalamic tract (DRTT), thus DRTT targeting has become a promising direction. The tractography-based targeting is more accurate than conventional ones, but still too complicated for clinical scenarios, where only structural magnetic resonance imaging (sMRI) data is available. In order to improve efficiency and utility, we consider target localization as a non-linear regression problem in a reduced-reference learning framework, and solve it with convolutional neural networks (CNNs). The proposed method is an efficient two-step framework, and consists of two image-based networks: one for classification and the other for localization. We model the basic workflow as an image retrieval process and define relevant performance metrics. Using DRTT as pseudo groundtruths, we show that individualized tractography-based optimal targets can be inferred from sMRI data with high accuracy. For two datasets of ${280}\times {220}/{272}\times {227}$ (0.7/0.8 mm slice thickness) sMRI input, our model achieves an average posterior localization error of 2.3/1.2 mm, and a median of 1.7/1.02 mm. The proposed framework is a novel application of reduced-reference learning, and a first attempt to localize DRTT from sMRI. It significantly outperforms existing methods using 3D-CNN, anatomical and DRTT atlas, and may serve as a new baseline for general target localization problems.

I. Introduction

Essential tremor (ET) is one of the most common movement disorders. It occurs globally with a rate from 0.4% to 6% [1], and affects approximately 1% of the population [2]. For ET patients, medicine treatment is the first option. However, medicine is only effective to about 50% of ET patients. For the rest, a well acknowledged surgical intervention is called deep brain stimulation (DBS). The basic idea of DBS is to stimulate certain nucleus or white matter tracts in the brain with electrodes, which are typically cylindrical contacts of a 1.5 mm diameter (Fig. 1). These locations are called targets. Since the effectiveness of DBS significantly depends on target locations, finding the optimal targets is a vital issue for DBS, which is referred to as target localization. Fig. 1.

Illustration of deep brain stimulation. For bilateral DBS, there is one target on each half of the brain. The electrode is roughly perpendicular to the x-y plane.