Our projects

Huntington Disease
Started on Sept. 30, 2016  By Artyom Borzov , Mikhail Belyaev
Something to write down for Artyom Borzov

Generative Models of Connectomes
Started on Oct. 21, 2016  By Yulia Denisova
Something to write down by Ayagoz

Convolution Networks for 3D MRI Data Analysis
Started on Dec. 6, 2016  By Sergey Korolev , Mikhail Belyaev
Somethid about first steps in deeep deeep learning

Geometry of the Set of Symmetric Positive Semidefinite Matrices
Started on Jan. 17, 2017  By Daria Belyaeva , Mikhail Belyaev
This project can be written by Artem @nexxoff

Brain Tumor Image Retrieval
Started on March 15, 2018  By Maxim Pisov , Mikhail Belyaev
Description


Metric Learning via Diffeomorphic Image Registration
Started on May 1, 2018  By Ayagoz Mussabayeva
Large Deformation Diffeomorphic Metric Mapping method induces a Riemannian structure on the space of diffeomorphism between images. Riemannian structure allow to use kernel methods of machine learning. The main goal is optimize the parameters of Riemannian metric to build a representative geometry. In practice, this may lead to a biologyaware registration, focusing its attention on the predictive task at hand such as identifying the effects of disease. In future work, we plan to extend flexibility of the metric.
people: Ayagoz Mussabayeva, Boris Gutman
current work: Image Registration and Predictive Modeling: Learning the Metric on the Space of Diffeomorphism

