SrvfNet: A Generative Network for Unsupervised Multiple Diffeomorphic Shape Alignment

TL;DR

SrvfNet is an unsupervised deep learning framework that aligns large collections of functional data to templates or jointly predicts optimal templates, demonstrated on synthetic and MRI data.

Contribution

It introduces a novel generative encoder-decoder network for unsupervised multiple shape alignment and template prediction from functional data.

Findings

Effective on synthetic data

Successfully applied to MRI diffusion profiles

Capable of joint alignment and template estimation

Abstract

We present SrvfNet, a generative deep learning framework for the joint multiple alignment of large collections of functional data comprising square-root velocity functions (SRVF) to their templates. Our proposed framework is fully unsupervised and is capable of aligning to a predefined template as well as jointly predicting an optimal template from data while simultaneously achieving alignment. Our network is constructed as a generative encoder-decoder architecture comprising fully-connected layers capable of producing a distribution space of the warping functions. We demonstrate the strength of our framework by validating it on synthetic data as well as diffusion profiles from magnetic resonance imaging (MRI) data.