mlsanityData to 14 Oct 2026

TractOracle: towards an anatomically-informed reward function for RL-based tractography

arXiv 2403.17845 ↗First posted 26 Mar 2024cs.LGcited by 5

On the map: Deep reinforcement learning methods → RL for clinical treatment and surgery

Abstract (arXiv)

Reinforcement learning (RL)-based tractography is a competitive alternative to machine learning and classical tractography algorithms due to its high anatomical accuracy obtained without the need for any annotated data. However, the reward functions so far used to train RL agents do not encapsulate anatomical knowledge which causes agents to generate spurious false positives tracts. In this paper, we propose a new RL tractography system, TractOracle, which relies on a reward network trained for streamline classification. This network is used both as a reward function during training as well as a mean for stopping the tracking process early and thus reduce the number of false positive streamlines. This makes our system a unique method that evaluates and reconstructs WM streamlines at the same time. We report an improvement of true positive ratios by almost 20% and a reduction of 3x of false positive ratios on one dataset and an increase between 2x and 7x in the number true positive streamlines on another dataset.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in RL for clinical treatment and surgery, one of 15 directions in Deep reinforcement learning methods. Builds on 5 of its 32 references that are in the map. First posted on arXiv 26 Mar 2024.

Builds on

5 of 32 references.

References · 5

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  3. 2020Filtering in tractography using autoencoders (FINTA)cited by 17
  4. 2018DeepTract: A Probabilistic Deep Learning Framework for White Matter Fiber Tractographycited by 11
  5. 2023What Matters in Reinforcement Learning for Tractographycited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025Deep Learning-Based Diffusion MRI Tractography: Integrating Spatial and Anatomical Informationcited by 2
  2. 2025DDTracking: A Deep Generative Framework for Diffusion MRI Tractography with Streamline Local-Global Spatiotemporal Modelingcited by 2
  3. 2025Exploring the robustness of TractOracle methods in RL-based tractographycited by 1
  4. 2025GenTract: Generative Global Tractographycited by 0
  5. 2026TractRLFusion: A GPT-Based Multi-Critic Policy Fusion Framework for Fiber Tractographycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A Deep RL based Framework for Targeted White Matter Tractography
  2. 2024Tract-RLFormer: A Tract-Specific RL policy based Decoder-only Transformer Network
  3. 2024Tractography with T1-weighted MRI and associated anatomical constraints on clinical quality diffusion MRI ↗
  4. 2024Domain Adaptation of Echocardiography Segmentation Via Reinforcement Learning
  5. 2026TractoGraphVLM: A Unified Vision-Language Framework for White Matter Tractography
  6. 2026Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors
  7. 2026When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains
  8. 2026Staged Voxel-Level Deep Reinforcement Learning for 3D Medical Image Segmentation with Noisy Annotations