Local Rotation Invariance in 3D CNNs

by   Vincent Andrearczyk, et al.

Locally Rotation Invariant (LRI) image analysis was shown to be fundamental in many applications and in particular in medical imaging where local structures of tissues occur at arbitrary rotations. LRI constituted the cornerstone of several breakthroughs in texture analysis, including Local Binary Patterns (LBP), Maximum Response 8 (MR8) and steerable filterbanks. Whereas globally rotation invariant Convolutional Neural Networks (CNN) were recently proposed, LRI was very little investigated in the context of deep learning. LRI designs allow learning filters accounting for all orientations, which enables a drastic reduction of trainable parameters and training data when compared to standard 3D CNNs. In this paper, we propose and compare several methods to obtain LRI CNNs with directional sensitivity. Two methods use orientation channels (responses to rotated kernels), either by explicitly rotating the kernels or using steerable filters. These orientation channels constitute a locally rotation equivariant representation of the data. Local pooling across orientations yields LRI image analysis. Steerable filters are used to achieve a fine and efficient sampling of 3D rotations as well as a reduction of trainable parameters and operations, thanks to a parametric representations involving solid Spherical Harmonics (SH), which are products of SH with associated learned radial profiles.Finally, we investigate a third strategy to obtain LRI based on rotational invariants calculated from responses to a learned set of solid SHs. The proposed methods are evaluated and compared to standard CNNs on 3D datasets including synthetic textured volumes composed of rotated patterns, and pulmonary nodule classification in CT. The results show the importance of LRI image analysis while resulting in a drastic reduction of trainable parameters, outperforming standard 3D CNNs trained with data augmentation.



There are no comments yet.


page 4


3D Solid Spherical Bispectrum CNNs for Biomedical Texture Analysis

Locally Rotation Invariant (LRI) operators have shown great potential in...

Dense Steerable Filter CNNs for Exploiting Rotational Symmetry in Histology Images

Histology images are inherently symmetric under rotation, where each ori...

Designing Rotationally Invariant Neural Networks from PDEs and Variational Methods

Partial differential equation (PDE) models and their associated variatio...

Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis

Rotation-invariance is a desired property of machine-learning models for...

Rotational 3D Texture Classification Using Group Equivariant CNNs

Convolutional Neural Networks (CNNs) traditionally encode translation eq...

Roto-Translation Covariant Convolutional Networks for Medical Image Analysis

We propose a framework for rotation and translation covariant deep learn...

Local Unsupervised Learning for Image Analysis

Local Hebbian learning is believed to be inferior in performance to end-...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.