mlsanityData to 14 Oct 2026

Comprehensive Review of Reinforcement Learning for Medical Ultrasound Imaging

arXiv 2503.16543 ↗First posted 19 Mar 2025eess.IV cs.CVcited by 2

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

Abstract (arXiv)

Medical Ultrasound (US) imaging has seen increasing demands over the past years, becoming one of the most preferred imaging modalities in clinical practice due to its affordability, portability, and real-time capabilities. However, it faces several challenges that limit its applicability, such as operator dependency, variability in interpretation, and limited resolution, which are amplified by the low availability of trained experts. This calls for the need of autonomous systems that are capable of reducing the dependency on humans for increased efficiency and throughput. Reinforcement Learning (RL) comes as a rapidly advancing field under Artificial Intelligence (AI) that allows the development of autonomous and intelligent agents that are capable of executing complex tasks through rewarded interactions with their environments. Existing surveys on advancements in the US scanning domain predominantly focus on partially autonomous solutions leveraging AI for scanning guidance, organ identification, plane recognition, and diagnosis. However, none of these surveys explore the intersection between the stages of the US process and the recent advancements in RL solutions. To bridge this gap, this review proposes a comprehensive taxonomy that integrates the stages of the US process with the RL development pipeline. This taxonomy not only highlights recent RL advancements in the US domain but also identifies unresolved challenges crucial for achieving fully autonomous US systems. This work aims to offer a thorough review of current research efforts, highlighting the potential of RL in building autonomous US solutions while identifying limitations and opportunities for further advancements in this field.

Key facts. Cited by 2 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 18 of its 69 references that are in the map. First posted on arXiv 19 Mar 2025.

Builds on

18 of 69 references.

References · 18

  1. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,186
  2. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 166
  3. 2020A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environmentscited by 62
  4. 2023A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyondcited by 55
  5. 2021Deep Reinforcement Learning in Computer Vision: A Comprehensive Surveycited by 43
  6. 2021Deep Multiagent Reinforcement Learning: Challenges and Directionscited by 42
  7. 2021Deep reinforcement learning in medical imaging: A literature reviewcited by 34
  8. 2022Explainable Deep Learning Methods in Medical Image Classification: A Surveycited by 32
  9. 2023Robotic Ultrasound Imaging: State-of-the-Art and Future Perspectivescited by 31
  10. 2020Medical Image Registration Using Deep Neural Networks: A Comprehensive Reviewcited by 22
  11. 2024Machine Learning in Robotic Ultrasound Imaging: Challenges and Perspectivescited by 17
  12. 2022Reinforcement Learning in Medical Image Analysis: Concepts, Applications, Challenges, and Future Directionscited by 16
6 more
  1. 2022Image quality assessment for machine learning tasks using meta-reinforcement learningcited by 10
  2. 2021Searching Collaborative Agents for Multi-plane Localization in 3D Ultrasoundcited by 7
  3. 2025Adaptive Target Localization under Uncertainty using Multi-Agent Deep Reinforcement Learning with Knowledge Transfercited by 3
  4. 2025UAV-assisted Internet of Vehicles: A Framework Empowered by Reinforcement Learning and Blockchaincited by 3
  5. 2023Multi-Target Landmark Detection with Incomplete Images via Reinforcement Learning and Shape Priorcited by 2
  6. 2025Blockchain-based Crowdsourced Deep Reinforcement Learning as a Servicecited by 1

Built on by

Cited by year (2026 to 14 Oct)

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

2 papers.

  1. 2025End-to-End Framework Integrating Generative AI and Deep Reinforcement Learning for Autonomous Ultrasound Scanningcited by 0
  2. 2026Learning-based Hierarchical Tracheal Anatomy Understanding from Sparse Surgical Demonstration Annotations for Ultrasound Robotscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026US-VLA: An Ultrasound Vision-Language-Action Model for Embodied Abdomina
  2. 2024Autonomous Path Planning for Intercostal Robotic Ultrasound Imaging Using Reinforcement Learning
  3. 2025SonoGym: High Performance Simulation for Challenging Surgical Tasks with Robotic Ultrasound
  4. 2024Goal-conditioned reinforcement learning for ultrasound navigation guidance
  5. 2021Learning Robotic Ultrasound Scanning Skills via Human Demonstrations and Guided Explorations
  6. 2026Echo-α: Large Agentic Multimodal Reasoning Model for Ultrasound Interpretation
  7. 2026Anatomical Prior-Driven Framework for Autonomous Robotic Cardiac Ultrasound Standard View Acquisition
  8. 2026From Scanning Guidelines to Action: A Robotic Ultrasound Agent with LLM-Based Reasoning