Probabilistic 3D surface reconstruction from sparse MRI information

TL;DR

This paper introduces a probabilistic deep learning method for 3D surface reconstruction from sparse MRI slices, which predicts shape uncertainty and outperforms existing methods in accuracy and localization.

Contribution

It presents a novel probabilistic approach that reconstructs 3D surfaces from limited MRI data while modeling vertex locations with Gaussian distributions and encoding prior shape information with PCA.

Findings

Successfully reconstructs large 3D surfaces from three MRI slices.

Accurately predicts uncertainty in surface reconstruction.

Outperforms state-of-the-art methods in shape accuracy and localization.

Abstract

Surface reconstruction from magnetic resonance (MR) imaging data is indispensable in medical image analysis and clinical research. A reliable and effective reconstruction tool should: be fast in prediction of accurate well localised and high resolution models, evaluate prediction uncertainty, work with as little input data as possible. Current deep learning state of the art (SOTA) 3D reconstruction methods, however, often only produce shapes of limited variability positioned in a canonical position or lack uncertainty evaluation. In this paper, we present a novel probabilistic deep learning approach for concurrent 3D surface reconstruction from sparse 2D MR image data and aleatoric uncertainty prediction. Our method is capable of reconstructing large surface meshes from three quasi-orthogonal MR imaging slices from limited training sets whilst modelling the location of each mesh vertex through a Gaussian distribution. Prior shape information is encoded using a built-in linear principal component analysis (PCA) model. Extensive experiments on cardiac MR data show that our probabilistic approach successfully assesses prediction uncertainty while at the same time qualitatively and quantitatively outperforms SOTA methods in shape prediction. Compared to SOTA, we are capable of properly localising and orientating the prediction via the use of a spatially aware neural network.