# Intelligent Robotic Sonographer: Mutual Information-based Disentangled Reward Learning from Few Demonstrations

arXiv: https://arxiv.org/abs/2307.03705 · HTML: https://mlsanity.com/paper/2307.03705/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 67 references that are in the map.
- First posted on arXiv 7 Jul 2023.

## Builds on (most cited first, 20 of 20)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018)
- [SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound](https://mlsanity.com/paper/1612.05601/) (2016)
- [Towards MRI-Based Autonomous Robotic US Acquisitions: A First Feasibility Study](https://mlsanity.com/paper/1607.08371/) (2016)
- [AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers](https://mlsanity.com/paper/1909.04121/) (2019)
- [Automatic Probe Movement Guidance for Freehand Obstetric Ultrasound](https://mlsanity.com/paper/2007.04480/) (2020)
- [Autonomous Robotic Screening of Tubular Structures based only on Real-Time Ultrasound Imaging Feedback](https://mlsanity.com/paper/2011.00099/) (2020)
- [Autonomous Navigation of an Ultrasound Probe Towards Standard Scan Planes with Deep Reinforcement Learning](https://mlsanity.com/paper/2103.00718/) (2021)
- [MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization](https://mlsanity.com/paper/2303.12649/) (2023)
- [Ultrasound-Guided Robotic Navigation with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.13321/) (2020)
- [Mutual Information-based Disentangled Neural Networks for Classifying Unseen Categories in Different Domains: Application to Fetal Ultrasound Imaging](https://mlsanity.com/paper/2011.00739/) (2020)
- [Deformation-Aware Robotic 3D Ultrasound](https://mlsanity.com/paper/2107.08411/) (2021)
- [VesNet-RL: Simulation-based Reinforcement Learning for Real-World US Probe Navigation](https://mlsanity.com/paper/2205.06676/) (2022)
- [Towards Autonomous Atlas-based Ultrasound Acquisitions in Presence of Articulated Motion](https://mlsanity.com/paper/2208.05399/) (2022)
- [Motion-Aware Robotic 3D Ultrasound](https://mlsanity.com/paper/2107.05998/) (2021)
- [Precise Repositioning of Robotic Ultrasound: Improving Registration-based Motion Compensation using Ultrasound Confidence Optimization](https://mlsanity.com/paper/2208.05383/) (2022)
- [Robotic Sonographer: Autonomous Robotic Ultrasound using Domain Expertise in Bayesian Optimization](https://mlsanity.com/paper/2307.02442/) (2023)
- [Learning rewards for robotic ultrasound scanning using probabilistic temporal ranking](https://mlsanity.com/paper/2002.01240/) (2020)

## Built on by (most cited first, 14 of 14)

- [Speckle2Self: Self-Supervised Ultrasound Speckle Reduction Without Clean Data](https://mlsanity.com/paper/2507.06828/) (2025)
- [VibNet: Vibration-Boosted Needle Detection in Ultrasound Images](https://mlsanity.com/paper/2403.14523/) (2024)
- [Class-Aware Cartilage Segmentation for Autonomous US-CT Registration in Robotic Intercostal Ultrasound Imaging](https://mlsanity.com/paper/2406.04100/) (2024)
- [UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptation](https://mlsanity.com/paper/2506.19694/) (2025)
- [Autonomous Path Planning for Intercostal Robotic Ultrasound Imaging Using Reinforcement Learning](https://mlsanity.com/paper/2404.09927/) (2024)
- [Synomaly Noise and Multi-Stage Diffusion: A Novel Approach for Unsupervised Anomaly Detection in Medical Images](https://mlsanity.com/paper/2411.04004/) (2024)
- [Robot-Assisted Deep Venous Thrombosis Ultrasound Examination using Virtual Fixture](https://mlsanity.com/paper/2401.02539/) (2024)
- [CathFlow: Self-Supervised Segmentation of Catheters in Interventional Ultrasound Using Optical Flow and Transformers](https://mlsanity.com/paper/2403.14465/) (2024)
- [Coaching a Robotic Sonographer: Learning Robotic Ultrasound with Sparse Expert's Feedback](https://mlsanity.com/paper/2409.02337/) (2024)
- [Advancing Embodied Intelligence in Robotic-Assisted Endovascular Procedures: A Systematic Review of AI Solutions](https://mlsanity.com/paper/2504.15327/) (2025)
- [Ultrasound-Guided Real-Time Spinal Motion Visualization for Spinal Instability Assessment](https://mlsanity.com/paper/2602.12917/) (2026)
- [Vibration-Based Energy Metric for Restoring Needle Alignment in Autonomous Robotic Ultrasound](https://mlsanity.com/paper/2508.06921/) (2025)
- [ConVibNet: Needle Detection during Continuous Insertion via Frequency-Inspired Features](https://mlsanity.com/paper/2603.01147/) (2026)
- [Scanning While Imagining: A Scene-Graph World Model for Robotic Ultrasound Navigation](https://mlsanity.com/paper/2609.32837/) (2026)

## Abstract (arXiv)

Ultrasound (US) imaging is widely used for biometric measurement and diagnosis of internal organs due to the advantages of being real-time and radiation-free. However, due to inter-operator variations, resulting images highly depend on the experience of sonographers. This work proposes an intelligent robotic sonographer to autonomously "explore" target anatomies and navigate a US probe to a relevant 2D plane by learning from the expert. The underlying high-level physiological knowledge from experts is inferred by a neural reward function, using a ranked pairwise image comparisons approach in a self-supervised fashion. This process can be referred to as understanding the "language of sonography". Considering the generalization capability to overcome inter-patient variations, mutual information is estimated by a network to explicitly disentangle the task-related and domain features in latent space. The robotic localization is carried out in coarse-to-fine mode based on the predicted reward associated with B-mode images. To validate the effectiveness of the proposed reward inference network, representative experiments were performed on vascular phantoms ("line" target), two types of ex-vivo animal organs (chicken heart and lamb kidney) phantoms ("point" target) and in-vivo human carotids, respectively. To further validate the performance of the autonomous acquisition framework, physical robotic acquisitions were performed on three phantoms (vascular, chicken heart, and lamb kidney). The results demonstrated that the proposed advanced framework can robustly work on a variety of seen and unseen phantoms as well as in-vivo human carotid data.