Automatic View Planning with Multi-scale Deep Reinforcement Learning Agents

TL;DR

This paper introduces a multi-scale deep reinforcement learning approach to automatically identify standardized view planes in 3D medical images, reducing operator dependence and improving accuracy.

Contribution

It presents a novel RL-based framework for automatic view planning in medical imaging, evaluated on brain and cardiac MRI with promising accuracy.

Findings

Achieved landmark detection accuracy within 2mm for brain MRI planes.

Demonstrated effective automatic view planning comparable to expert operators.

Validated the approach on multiple anatomical planes with consistent results.

Abstract

We propose a fully automatic method to find standardized view planes in 3D image acquisitions. Standard view images are important in clinical practice as they provide a means to perform biometric measurements from similar anatomical regions. These views are often constrained to the native orientation of a 3D image acquisition. Navigating through target anatomy to find the required view plane is tedious and operator-dependent. For this task, we employ a multi-scale reinforcement learning (RL) agent framework and extensively evaluate several Deep Q-Network (DQN) based strategies. RL enables a natural learning paradigm by interaction with the environment, which can be used to mimic experienced operators. We evaluate our results using the distance between the anatomical landmarks and detected planes, and the angles between their normal vector and target. The proposed algorithm is assessed on the mid-sagittal and anterior-posterior commissure planes of brain MRI, and the 4-chamber long-axis plane commonly used in cardiac MRI, achieving accuracy of 1.53mm, 1.98mm and 4.84mm, respectively.