Automatic view planning with multi-scale deep reinforcement learning agents
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
We propose a fully automatic method to find standardized
view planes in 3D image acquisitions. Standard view images are impor-
tant 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 DeepQ-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.
view planes in 3D image acquisitions. Standard view images are impor-
tant 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 DeepQ-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.
Date Issued
2018-09-26
Date Acceptance
2018-05-25
Citation
Lecture Notes in Computer Science, 2018, pp.277-285
ISSN
0302-9743
Publisher
Springer Verlag
Start Page
277
End Page
285
Journal / Book Title
Lecture Notes in Computer Science
Copyright Statement
© Springer Nature Switzerland AG 2018. The final publication is available at Springer via https://doi.org/10.1007/978-3-030-00928-1_32
Sponsor
Engineering & Physical Science Research Council (E
Wellcome Trust
Identifier
https://link.springer.com/chapter/10.1007%2F978-3-030-00928-1_32
Grant Number
RTJ5557761-1
PO :RTJ5557761-1
Source
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)
Subjects
Science & Technology
Technology
Computer Science, Theory & Methods
Imaging Science & Photographic Technology
Computer Science
MID-SAGITTAL PLANE
cs.CV
cs.CV
Artificial Intelligence & Image Processing
Publication Status
Published
Start Date
2018-09-16
Finish Date
2018-09-20
Coverage Spatial
Granada, Spain
Date Publish Online
2018-09-26