Leveraging unsupervised image registration for discovery of landmark shape descriptor (2021-07-09T00:00:00.000000Z)

TL;DR

This paper proposes a self-supervised deep learning approach for discovering landmarks from images that can directly be used as a shape descriptor for subsequent analysis, and proposes a regularization term that allows for robust optimization of the neural network and ensures that the landmarks uniformly span the image domain.

Authors

Shireen Elhabian

2 papers

Riddhish Bhalodia

1 papers

L. Kavan

1 papers

R. Whitaker

1 papers

TL;DR

Authors

References46 items

Adversarial Uni- and Multi-modal Stream Networks for Multimodal Image Registration

Self-Supervised Discovery of Anatomical Shape Landmarks

Quantifying the Severity of Metopic Craniosynostosis: A Pilot Study Application of Machine Learning in Craniofacial Surgery.

Craniosynostosis

A Cooperative Autoencoder for Population-Based Regularization of CNN Image Registration

Learning Conditional Deformable Templates with Convolutional Networks

On the Evaluation and Validation of Off-the-shelf Statistical Shape Modeling Tools: A Clinical Application

DeepSSM: A Deep Learning Framework for Statistical Shape Modeling from Raw Images

VoxelMorph: A Learning Framework for Deformable Medical Image Registration

Left atrial shape predicts recurrence after atrial fibrillation catheter ablation

Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration

SuperPoint: Self-Supervised Interest Point Detection and Description

Integrating Statistical Prior Knowledge into Convolutional Neural Networks

Learning Deep Features for Automated Placement of Correspondence Points on Ensembles of Complex Shapes

Quantitative comparison of cortical bone thickness using correspondence‐based shape modeling in patients with cam femoroacetabular impingement

Convolutional Neural Network Architecture for Geometric Matching

Learning shape correspondence with anisotropic convolutional neural networks

Spatial Transformer Networks

Why Does Mutual-Information Work for Image Registration? A Deterministic Explanation

Adam: A Method for Stochastic Optimization

Personalized assessment of craniosynostosis via statistical shape modeling

Computational Shape Models Characterize Shape Change of the Left Atrium in Atrial Fibrillation

Statistical shape modeling of cam femoroacetabular impingement

A point-correspondence approach to describing the distribution of image features on anatomical surfaces, with application to atrial fibrillation

Three-dimensional Quantification of Femoral Head Shape in Controls and Patients with Cam-type Femoroacetabular Impingement

Interfrontal Angle for Characterization of Trigonocephaly: Part 1: Development and Validation of a Tool for Diagnosis of Metopic Synostosis

Particle Based Shape Regression of Open Surfaces with Applications to Developmental Neuroimaging

A tutorial on spectral clustering

Shape Analysis Using a Point-Based Statistical Shape Model Built on Correspondence Probabilities

Shape Modeling and Analysis with Entropy-Based Particle Systems

Framework for the Statistical Shape Analysis of Brain Structures using SPHARM-PDM.

Computing Large Deformation Metric Mappings via Geodesic Flows of Diffeomorphisms

Unbiased diffeomorphic atlas construction for computational anatomy

Distinctive Image Features from Scale-Invariant Keypoints

A minimum description length approach to statistical shape modeling

Shape analysis of brain ventricles using SPHARM

Hippocampal shape analysis using medial surfaces

Parametric estimate of intensity inhomogeneities applied to MRI

Diatom identification: a double challenge called ADIAC

On growth and form

Hands: A Pattern Theoretic Study of Biological Shapes

ShapeWorks: Particle-Based Shape Correspondence and Visualization Software

Siamese Neural Networks for One-Shot Image Recognition

Review of Femoroacetabular Impingement

the left atrium in atrial ﬁbrillation

Functional maps: a flexible representation of maps between shapes

Field of Study

Journal Information

Name

Page

Volume