Exploring the robustness of TractOracle methods in RL-based tractography

TL;DR

This paper evaluates the robustness of RL-based tractography methods, introduces a new training scheme called IRT, and demonstrates improved accuracy and reliability across multiple datasets.

Contribution

It extends the TractOracle-RL framework with recent RL advances and proposes IRT, a novel training scheme that enhances tractography performance.

Findings

RL methods with oracle feedback outperform traditional techniques.

Combining an oracle with RL yields consistent robustness across datasets.

IRT improves the accuracy and anatomical validity of tractography results.

Abstract

Tractography algorithms leverage diffusion MRI to reconstruct the fibrous architecture of the brain's white matter. Among machine learning approaches, reinforcement learning (RL) has emerged as a promising framework for tractography, outperforming traditional methods in several key aspects. TractOracle-RL, a recent RL-based approach, reduces false positives by incorporating anatomical priors into the training process via a reward-based mechanism. In this paper, we investigate four extensions of the original TractOracle-RL framework by integrating recent advances in RL, and we evaluate their performance across five diverse diffusion MRI datasets. Results demonstrate that combining an oracle with the RL framework consistently leads to robust and reliable tractography, regardless of the specific method or dataset used. We also introduce a novel RL training scheme called Iterative Reward Training (IRT), inspired by the Reinforcement Learning from Human Feedback (RLHF) paradigm. Instead of relying on human input, IRT leverages bundle filtering methods to iteratively refine the oracle's guidance throughout training. Experimental results show that RL methods trained with oracle feedback significantly outperform widely used tractography techniques in terms of accuracy and anatomical validity.