GALEN - 2017 - Annual activity report

GALEN

GALEN - 2017

Project-Team Galen

Personnel

Overall Objectives

GALEN@Centrale-Paris

Research Program

Shape, Grouping and Recognition
Machine Learning & Structured Prediction
Self-Paced Learning with Missing Information
Discrete Biomedical Image Perception

Application Domains

Breast tomosynthesis
Inference of gene regulatory networks
Lung Tumor Detection and Characterization
Protein function prediction
Imaging biomarkers for chronic lung diseases
Co-segmentation and Co-registration of Subcortical Brain Structures
Restoration of old video archives

Highlights of the Year

New Software and Platforms

DISD
DPMS
DROP
FastPD
GraPeS
HOAP-SVM
LBSD
mrf-registration
TeXMeG
Platforms

New Results

Graph Based Slice-to-Volume Deformable Registration
Deformable Registration Through Learning of Context-Specific Metric Aggregation
Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology
Multi-atlas segmentation in medical imagery
Protein function prediction
Deformable group-wise registration using a physiological model: Application to diffusion-weighted MRI
Variational Bayesian Approach for Image Restoration
Non-Modular Loss Functions
Graph Structure Discovery
Structured and Efficient Convolutional Networks
Stochastic Majorize-Minimize Subspace Algorithm
Deconvolution and Deinterlacing of Video Sequences
PALMA, an improved algorithm for DOSY signal processing
Proximal Approaches for Solving Matrix Optimization Problems
Fast Algorithm for Least-Squares Regression with GMRF Prior
Optimization Approach for Deep Neural Network Training
Auxiliary Variable Method for MCMC Algorithms in High Dimension
Block Coordinate Approach for Sparse Logistic Regression
An Alternating Proximal Approach for Blind Video Deconvolution
BRANE Clust: Cluster-Assisted Gene Regulatory Network Inference Refinement
Proximity Operators of Discrete Information Divergences
Stochastic Quasi-Fejér Block-Coordinate Fixed Point Iterations With Random Sweeping: Mean-Square and Linear Convergence
Human Joint Angle Estimation and Gesture Recognition for Assistive Robotic Vision
Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
Dense and Low-Rank Gaussian CRFs Using Deep Embeddings
DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild
Structured Output Prediction and Learning for Deep Monocular 3D Human Pose Estimation
Newton-type Methods for Inference in Higher-Order Markov Random Fields
Alternating Direction Graph Matching
Prediction and classification in biological and information networks

Bilateral Contracts and Grants with Industry

Bilateral Contracts with Industry

Partnerships and Cooperations

National Initiatives
European Initiatives
International Initiatives
International Research Visitors

Dissemination

Promoting Scientific Activities
Teaching - Supervision - Juries

Bibliography

Publications of the year

Previous |

Home | Next next

Section: New Software and Platforms

DROP

Keywords: Health - Merging - Registration of 2D and 3D multimodal images - Medical imaging

Functional Description: Drop is a software programme that registers images originating from one or more modes by quickly and efficiently calculating a non-rigid / deformable field of deformation. Drop is a new, quick and effective registration tool based on new algorithms that do not require a cost function derivative.

Partner: Centrale Paris
Contact: Nikolaos Paragyios
URL: http://campar.in.tum.de/Main/Drop

Previous |

Home | Next next