Related Experiment Video
Updated: Jun 5, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
2.7K
Leveraging SO(3)-steerable convolutions for pose-robust semantic segmentation in 3D medical data.
Ivan Diaz1, Mario Geiger2, Richard Iain McKinley1
1Support Center for Advanced Neuroimaging (SCAN), University Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Inselspital, Bern University Hospital, Bern, Switzerland.
The Journal of Machine Learning for Biomedical Imaging
|December 10, 2024
Summary
New rotationally-equivariant convolutional networks improve medical image segmentation. These networks offer better performance, require less data, and are more efficient than standard convolutional neural networks (CNNs).
Area of Science:
- Medical Image Analysis
- Computer Vision
- Deep Learning
Background:
- Convolutional Neural Networks (CNNs) are widely used in medical image analysis.
- Standard CNNs lack rotational equivariance, limiting performance and requiring extensive data augmentation.
- Existing segmentation networks often rely on standard convolutional kernels, despite the benefits of rotationally-equivariant layers.
Purpose of the Study:
- To introduce a novel family of segmentation networks utilizing equivariant voxel convolutions based on spherical harmonics.
- To enhance robustness to unseen data poses and reduce the need for rotation-based data augmentation.
- To improve segmentation performance in medical imaging tasks, specifically for MRI brain tumor and healthy brain structure segmentation.
Main Methods:
- Development of a new family of segmentation networks employing equivariant voxel convolutions.
- Utilizing spherical harmonics to achieve SO(3)-steerable kernels for improved parameter sharing and translational equivariance.
- Implementation of these networks for MRI brain tumor and healthy brain structure segmentation tasks.
Main Results:
- Demonstrated improved segmentation performance compared to standard convolutional networks.
- Showcased enhanced robustness to reduced amounts of training data.
- Achieved improved parameter efficiency and reduced need for rotation-based data augmentation.
Conclusions:
- Equivariant voxel convolutions offer significant advantages for medical image segmentation.
- These networks provide increased robustness, better sample efficiency, and smaller network sizes.
- The proposed networks represent a promising advancement for medical image analysis, particularly in challenging segmentation tasks.
