Nonparametric Density Flows for MRI Intensity Normalisation

06/07/2018
by   Daniel Coelho de Castro, et al.
0

With the adoption of powerful machine learning methods in medical image analysis, it is becoming increasingly desirable to aggregate data that is acquired across multiple sites. However, the underlying assumption of many analysis techniques that corresponding tissues have consistent intensities in all images is often violated in multi-centre databases. We introduce a novel intensity normalisation scheme based on density matching, wherein the histograms are modelled as Dirichlet process Gaussian mixtures. The source mixture model is transformed to minimise its L^2 divergence towards a target model, then the voxel intensities are transported through a mass-conserving flow to maintain agreement with the moving density. In a multi-centre study with brain MRI data, we show that the proposed technique produces excellent correspondence between the matched densities and histograms. We further demonstrate that our method makes tissue intensity statistics substantially more compatible between images than a baseline affine transformation and is comparable to state-of-the-art while providing considerably smoother transformations. Finally, we validate that nonlinear intensity normalisation is a step toward effective imaging data harmonisation.

READ FULL TEXT
research
08/08/2022

Learning from imperfect training data using a robust loss function: application to brain image segmentation

Segmentation is one of the most important tasks in MRI medical image ana...
research
10/24/2021

Erlang mixture modeling for Poisson process intensities

We develop a prior probability model for temporal Poisson process intens...
research
09/07/2018

Dirichlet process mixtures under affine transformations of the data

Location-scale Dirichlet process mixtures of Gaussians (DPM-G) have prov...
research
12/11/2018

Evaluating the Impact of Intensity Normalization on MR Image Synthesis

Image synthesis learns a transformation from the intensity features of a...
research
03/05/2021

FedDis: Disentangled Federated Learning for Unsupervised Brain Pathology Segmentation

In recent years, data-driven machine learning (ML) methods have revoluti...
research
02/16/2020

Statistical Simulator for the Engine Knock

This paper proposes a statistical simulator for the engine knock based o...
research
05/11/2020

Deep Medical Image Analysis with Representation Learning and Neuromorphic Computing

We explore three representative lines of research and demonstrate the ut...

Please sign up or login with your details

Forgot password? Click here to reset