arXiv:2507.11486v2 Announce Type: replace 
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.

أدت التطورات الأخيرة في التعلم المعزز (RL) إلى استكشاف طرق TractOracle في التتبع القائم على RL، والتي تستخدم التصوير بالرنين المغناطيسي الانتشاري لإعادة بناء بنية المادة البيضاء في الدماغ بدقة. تقيم الدراسة أربعة امتدادات لإطار TractOracle-RL، مما يوضح أن دمج أوراكل مع RL يعزز باستمرار أداء التتبع عبر مجموعات بيانات متنوعة.

Los avances recientes en el aprendizaje por refuerzo (RL) han llevado a la exploración de los métodos TractOracle en la tractografía basada en RL, que utilizan la IRM de difusión para reconstruir con precisión la arquitectura de la materia blanca del cerebro. El estudio evalúa cuatro extensiones del marco TractOracle-RL, demostrando que la integración de un oráculo con el RL mejora consistentemente el rendimiento de la tractografía en diversos conjuntos de datos.

Des avancées récentes en apprentissage par renforcement (RL) ont conduit à l'exploration des méthodes TractOracle dans la tractographie basée sur le RL, qui utilisent l'IRM de diffusion pour reconstruire avec précision l'architecture de la matière blanche du cerveau. L'étude évalue quatre extensions du cadre TractOracle-RL, démontrant que l'intégration d'un oracle avec le RL améliore systématiquement les performances de tractographie sur divers ensembles de données.

Recent advancements in reinforcement learning (RL) have led to the exploration of TractOracle methods in RL-based tractography, which utilize diffusion MRI to accurately reconstruct the brain's white matter architecture. The study evaluates four extensions of the TractOracle-RL framework, demonstrating that integrating an oracle with RL consistently enhances tractography performance across various datasets.