Agent with Tangent-based Formulation and Anatomical Perception for Standard Plane Localization in 3D Ultrasound

  title={Agent with Tangent-based Formulation and Anatomical Perception for Standard Plane Localization in 3D Ultrasound},
  author={Yuxin Zou and Haoran Dou and Yuhao Huang and Xin Yang and Jikuan Qian and Chaojiong Zhen and Xiaodan Ji and Nishant Ravikumar and Guoqiang Chen and WeiJun Huang and Alejandro F. Frangi and Dong Ni},
. Standard plane (SP) localization is essential in routine clinical ultrasound (US) diagnosis. Compared to 2D US, 3D US can acquire multiple view planes in one scan and provide complete anatomy with the addition of coronal plane. However, manually navigating SPs in 3D US is laborious and biased due to the orientation variability and huge search space. In this study, we introduce a novel reinforcement learning (RL) framework for automatic SP localization in 3D US. Our contri-bution is three-fold… 

Figures and Tables from this paper



Searching Collaborative Agents for Multi-plane Localization in 3D Ultrasound

The proposed novel multi-agent reinforcement learning (MARL) framework is the first to realize automatic SP localization in pelvic US volumes, and the approach can handle both normal and abnormal uterus cases.

Agent with Warm Start and Active Termination for Plane Localization in 3D Ultrasound

A novel reinforcement learning (RL) framework to automatically localize fetal brain standard planes in 3D US using a recurrent neural network based strategy for active termination of the agent's interaction procedure, which improves both the accuracy and efficiency of the localization system.

Agent With Warm Start and Adaptive Dynamic Termination for Plane Localization in 3D Ultrasound

This study enhances the previous RL framework with a newly designed adaptive dynamic termination to enable an early stop for the agent searching, saving at most 67% inference time, thus boosting the accuracy and efficiency of the RL framework at the same time.

Automatic View Planning with Multi-scale Deep Reinforcement Learning Agents

A fully automatic method to find standardized view planes in 3D image acquisitions by employing a multi-scale reinforcement learning (RL) agent framework and extensively evaluate several Deep Q-Network (DQN) based strategies is proposed.

Autonomous Navigation of an Ultrasound Probe Towards Standard Scan Planes with Deep Reinforcement Learning

  • Keyu LiJian Wang M. Meng
  • Computer Science
    2021 IEEE International Conference on Robotics and Automation (ICRA)
  • 2021
A deep reinforcement learning framework to autonomously control the 6-D pose of a virtual US probe based on real-time image feedback to navigate towards the standard scan planes under the restrictions in real-world US scans is proposed.

Image-Guided Navigation of a Robotic Ultrasound Probe for Autonomous Spinal Sonography Using a Shadow-Aware Dual-Agent Framework

A novel dual-agent framework is proposed that integrates a reinforcement learning (RL) agent and a deep learning (DL) agent to jointly determine the movement of the US probe based on the real-time US images, in order to mimic the decision-making process of an expert sonographer to achieve autonomous standard view acquisitions in spinal sonography.

Standard Plane Detection in 3D Fetal Ultrasound Using an Iterative Transformation Network

This work proposes a new Iterative Transformation Network (ITN) for the automatic detection of standard planes in 3D volumes and introduces additional classification probability outputs to the network to act as confidence measures for the regressed transformation parameters in order to further improve the localisation accuracy.

Learning to map 2D ultrasound images into 3D space with minimal human annotation

Automated abdominal plane and circumference estimation in 3D US for fetal screening

A fully automated pipeline has been designed starting with a random forest based anatomical landmark detection to address a part of the canonical fetal screening program, namely the localization of the abdominal cross-sectional plane with the corresponding measurement of the abdomen circumference in this plane.

Sketch guided and progressive growing GAN for realistic and editable ultrasound image synthesis

The first work that can synthesize realistic B-mode US images with high-resolution and customized texture editing features is presented, and a feature loss is proposed to minimize the difference of high-level features between the generated and real images.