Interpretability Aware Model Training to Improve Robustness against Out-of-Distribution Magnetic Resonance Images in Alzheimer's Disease Classification

11/15/2021
by   Merel Kuijs, et al.
22

Owing to its pristine soft-tissue contrast and high resolution, structural magnetic resonance imaging (MRI) is widely applied in neurology, making it a valuable data source for image-based machine learning (ML) and deep learning applications. The physical nature of MRI acquisition and reconstruction, however, causes variations in image intensity, resolution, and signal-to-noise ratio. Since ML models are sensitive to such variations, performance on out-of-distribution data, which is inherent to the setting of a deployed healthcare ML application, typically drops below acceptable levels. We propose an interpretability aware adversarial training regime to improve robustness against out-of-distribution samples originating from different MRI hardware. The approach is applied to 1.5T and 3T MRIs obtained from the Alzheimer's Disease Neuroimaging Initiative database. We present preliminary results showing promising performance on out-of-distribution samples.

READ FULL TEXT

page 15

page 16

research
08/07/2018

Deep Learning Super-Resolution Enables Rapid Simultaneous Morphological and Quantitative Magnetic Resonance Imaging

Obtaining magnetic resonance images (MRI) with high resolution and gener...
research
07/02/2022

Interpretable Machine Learning for Brain Tumour Analysis using MRI and Whole Slide Images

Tumour-Analyser is a web application that classifies a brain tumour into...
research
02/28/2017

Context-Sensitive Super-Resolution for Fast Fetal Magnetic Resonance Imaging

3D Magnetic Resonance Imaging (MRI) is often a trade-off between fast bu...
research
07/10/2019

Fetal Pose Estimation in Volumetric MRI using a 3D Convolution Neural Network

The performance and diagnostic utility of magnetic resonance imaging (MR...
research
01/14/2021

Dual-cycle Constrained Bijective VAE-GAN For Tagged-to-Cine Magnetic Resonance Image Synthesis

Tagged magnetic resonance imaging (MRI) is a widely used imaging techniq...
research
10/22/2018

Implicit Modeling with Uncertainty Estimation for Intravoxel Incoherent Motion Imaging

Intravoxel incoherent motion (IVIM) imaging allows contrast-agent free i...
research
03/09/2023

Resolving quantitative MRI model degeneracy with machine learning via training data distribution design

Quantitative MRI (qMRI) aims to map tissue properties non-invasively via...

Please sign up or login with your details

Forgot password? Click here to reset