TractRLFusion: A GPT-Based Multi-Critic Policy Fusion Framework for Fiber Tractography
This work addresses the problem of improving brain connectivity mapping for neurosurgical planning, representing an incremental advancement by integrating multiple RL policies with a novel fusion strategy.
The paper tackles the challenge of accurately reconstructing white matter fiber tracts while minimizing spurious connections in tractography, proposing TractRLFusion, a GPT-based multi-critic policy fusion framework that outperforms state-of-the-art methods in accuracy and anatomical reliability on datasets like HCP, ISMRM, and TractoInferno.
Tractography plays a pivotal role in the non-invasive reconstruction of white matter fiber pathways, providing vital information on brain connectivity and supporting precise neurosurgical planning. Although traditional methods relied mainly on classical deterministic and probabilistic approaches, recent progress has benefited from supervised deep learning (DL) and deep reinforcement learning (DRL) to improve tract reconstruction. A persistent challenge in tractography is accurately reconstructing white matter tracts while minimizing spurious connections. To address this, we propose TractRLFusion, a novel GPT-based policy fusion framework that integrates multiple RL policies through a data-driven fusion strategy. Our method employs a two-stage training data selection process for effective policy fusion, followed by a multi-critic fine-tuning phase to enhance robustness and generalization. Experiments on HCP, ISMRM, and TractoInferno datasets demonstrate that TractRLFusion outperforms individual RL policies as well as state-of-the-art classical and DRL methods in accuracy and anatomical reliability.