Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis (2020-02-20T00:00:00.000000Z)

TL;DR

A framework to encode the geometric structure of the special Euclidean motion group SE(2) in convolutional networks to yield translation and rotation equivariance via the introduction of SE( 2)-group convolution layers is proposed.

Authors

M. Veta

3 papers

J. Pluim

3 papers

Maxime W. Lafarge

1 papers

E. Bekkers

1 papers

R. Duits

1 papers

TL;DR

Authors

References59 items

B-Spline CNNs on Lie Groups

Learning Domain-Invariant Representations of Histological Images

Rotation equivariant and invariant neural networks for microscopy image analysis

Pulmonary nodule detection in CT scans with equivariant CNNs

Enhanced Rotation-Equivariant U-Net for Nuclear Segmentation

Deep Scale-spaces: Equivariance Over Scale

Rota-Net: Rotation Equivariant Network for Simultaneous Gland and Lumen Segmentation in Colon Histology Images

Gauge Equivariant Convolutional Networks and the Icosahedral CNN

Equivariant Transformer Networks

Exploring local rotation invariance in 3D CNNs with steerable filters

A General Theory of Equivariant CNNs on Homogeneous Spaces

Deeply Supervised Rotation Equivariant Network for Lesion Segmentation in Dermoscopy Images

3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data

Rotation Equivariant CNNs for Digital Pathology

Computing CNN Loss and Gradients for Pose Estimation with Riemannian Geometry

CubeNet: Equivariance to 3D Rotation and Translation

3D G-CNNs for Pulmonary Nodule Detection

Roto-Translation Covariant Convolutional Networks for Medical Image Analysis

Design and Processing of Invertible Orientation Scores of 3D Images

HexaConv

Tensor Field Networks: Rotation- and Translation-Equivariant Neural Networks for 3D Point Clouds

On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups

Spherical CNNs

Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer

Learning Steerable Filters for Rotation Equivariant CNNs

Learning SO(3) Equivariant Representations with Spherical CNNs

Polar Transformer Networks

A Dataset and a Technique for Generalized Nuclear Segmentation for Computational Pathology

Oriented Response Networks

Rotation Equivariant Vector Field Networks

Harmonic Networks: Deep Translation and Rotation Equivariance

Warped Convolutions: Efficient Invariance to Spatial Transformations

Template Matching via Densities on the Roto-Translation Group

Group Equivariant Convolutional Networks

Exploiting Cyclic Symmetry in Convolutional Neural Networks

A Liver Atlas Using the Special Euclidean Group

Robust and Fast Vessel Segmentation via Gaussian Derivatives in Orientation Scores

Improving Fiber Alignment in HARDI by Combining Contextual PDE Flow with Constrained Spherical Deconvolution

Spatial Transformer Networks

U-Net: Convolutional Networks for Biomedical Image Segmentation

Locally Adaptive Frames in the Roto-Translation Group and Their Applications in Medical Imaging

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Training of Templates for Object Recognition in Invertible Orientation Scores: Application to Optic Nerve Head Detection in Retinal Images

Deep Symmetry Networks

Assessment of algorithms for mitosis detection in breast cancer histopathology images

Crossing-Preserving Multi-scale Vesselness

Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks

Comprehensive molecular portraits of human breast tumors

Left-Invariant Diffusions on the Space of Positions and Orientations and their Application to Crossing-Preserving Smoothing of HARDI images

Group Invariant Scattering

Crossing-Preserving Coherence-Enhancing Diffusion on Invertible Orientation Scores

A method for normalizing histology slides for quantitative analysis

A fast diffeomorphic image registration algorithm

Image Analysis and Reconstruction using a Wavelet Transform Constructed from a Reducible Representation of the Euclidean Motion Group

A Log-Euclidean Framework for Statistics on Diffeomorphisms

Riemannian Geometric Statistics in Medical Image Analysis

Relying on interpolation methods to transform kernels Bekkers et al.

Expanding convolution kernels in a special basis, tailored to the transformation group of interest, that enables to build steerable CNNs

Perceptual organization in image analysis

Field of Study

Journal Information

Name

Page

Volume