20 Jul 20. Featured Paper

Link to paper on Elsevier, Medical Image Analysis

 

Authors

Muhammad Febrian Rachmadi, Maria del C.Valdés-Hernández, Stephen Makin, Joanna Wardlaw, Taku Komura

 

Abstract

Previous studies have indicated that white matter hyperintensities (WMH), the main radiological feature of small vessel disease, may evolve (i.e., shrink, grow) or stay stable over a period of time.

Predicting these changes are challenging because it involves some unknown clinical risk factors that leads to a non-deterministic prediction task.

In this study, we propose a deep learning model to predict the evolution of WMH from baseline to follow-up (i.e., 1-year later), namely “Disease Evolution Predictor” (DEP) model, which can be adjusted to become a non-deterministic model.

The DEP model receives a baseline image as input & produces a map called “Disease Evolution Map” (DEM), which represents the evolution of WMH from baseline to follow-up.

Two DEP models are proposed, namely DEP-UResNet & DEP-GAN, which are representatives of the supervised (i.e., need expert-generated manual labels to generate the output) & unsupervised (i.e., do not require manual labels produced by experts) deep learning algorithms respectively.

To simulate the non-deterministic & unknown parameters involved in WMH evolution, we modulate a Gaussian noise array to the DEP model as auxiliary input.

This forces the DEP model to imitate a wider spectrum of alternatives in the prediction results.

The alternatives of using other types of auxiliary input instead, such as baseline WMH & stroke lesion loads are also proposed & tested.

Based on our experiments, the fully supervised machine learning scheme DEP-UResNet regularly performed better than the DEP-GAN which works in principle without using any expert-generated label (i.e., unsupervised).

However, a semi-supervised DEP-GAN model, which uses probability maps produced by a supervised segmentation method in the learning process, yielded similar performances to the DEP-UResNet & performed best in the clinical evaluation.

Furthermore, an ablation study showed that an auxiliary input, especially the Gaussian noise, improved the performance of DEP models compared to DEP models that lacked the auxiliary input regardless of the model’s architecture.

To the best of our knowledge, this is the first extensive study on modelling WMH evolution using deep learning algorithms, which deals with the non-deterministic nature of WMH evolution.

 

Keywords

• DEP Generative adversarial network (DEP-GAN)
• DEP U-Residual Network (DEP-UResNet)
• Disease evolution predictor (DEP) models
• Small vessel disease (SVD)
• White matter hyperintensities (WMH)
• WMH Evolution