Robust White Matter Hyperintensity Segmentation on Unseen Domain

02/12/2021
by   Xingchen Zhao, et al.
13

Typical machine learning frameworks heavily rely on an underlying assumption that training and test data follow the same distribution. In medical imaging which increasingly begun acquiring datasets from multiple sites or scanners, this identical distribution assumption often fails to hold due to systematic variability induced by site or scanner dependent factors. Therefore, we cannot simply expect a model trained on a given dataset to consistently work well, or generalize, on a dataset from another distribution. In this work, we address this problem, investigating the application of machine learning models to unseen medical imaging data. Specifically, we consider the challenging case of Domain Generalization (DG) where we train a model without any knowledge about the testing distribution. That is, we train on samples from a set of distributions (sources) and test on samples from a new, unseen distribution (target). We focus on the task of white matter hyperintensity (WMH) prediction using the multi-site WMH Segmentation Challenge dataset and our local in-house dataset. We identify how two mechanically distinct DG approaches, namely domain adversarial learning and mix-up, have theoretical synergy. Then, we show drastic improvements of WMH prediction on an unseen target domain.

READ FULL TEXT

page 3

page 5

research
08/18/2020

Domain Generalizer: A Few-shot Meta Learning Framework for Domain Generalization in Medical Imaging

Deep learning models perform best when tested on target (test) data doma...
research
06/07/2019

When Unseen Domain Generalization is Unnecessary? Rethinking Data Augmentation

Recent advances in deep learning for medical image segmentation demonstr...
research
04/05/2023

Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentation

Most statistical learning algorithms rely on an over-simplified assumpti...
research
03/11/2019

Distributed deep learning for robust multi-site segmentation of CT imaging after traumatic brain injury

Machine learning models are becoming commonplace in the domain of medica...
research
09/18/2023

DGM-DR: Domain Generalization with Mutual Information Regularized Diabetic Retinopathy Classification

The domain shift between training and testing data presents a significan...
research
03/20/2021

An Empirical Framework for Domain Generalization in Clinical Settings

Clinical machine learning models experience significantly degraded perfo...
research
02/18/2018

RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks

Training complex machine learning models for prediction often requires a...

Please sign up or login with your details

Forgot password? Click here to reset