Robust White Matter Hyperintensity Segmentation On Unseen Domain

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.

[1]  Victor S. Lempitsky,et al.  Unsupervised Domain Adaptation by Backpropagation , 2014, ICML.

[2]  Seong Jae Hwang,et al.  Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improve , 2021, ArXiv.

[3]  Daniel C. Castro,et al.  Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects , 2019, ArXiv.

[4]  Alex ChiChung Kot,et al.  Domain Generalization with Adversarial Feature Learning , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[5]  Amedeo Chiribiri,et al.  Domain-Adversarial Learning for Multi-Centre, Multi-Vendor, and Multi-Disease Cardiac MR Image Segmentation , 2020, M&Ms and EMIDEC/STACOM@MICCAI.

[6]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[7]  Jason Weston,et al.  Vicinal Risk Minimization , 2000, NIPS.

[8]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[9]  Pulkit Khandelwal,et al.  Domain Generalizer: A Few-shot Meta Learning Framework for Domain Generalization in Medical Imaging , 2020, DART/DCL@MICCAI.

[10]  Ioannis Mitliagkas,et al.  Generalizing to unseen domains via distribution matching , 2019 .

[11]  Mikhail Belyaev,et al.  First U-Net Layers Contain More Domain Specific Information Than The Last Ones , 2020, DART/DCL@MICCAI.

[12]  Tatsuya Harada,et al.  Domain Generalization Using a Mixture of Multiple Latent Domains , 2019, AAAI.

[13]  Koby Crammer,et al.  Analysis of Representations for Domain Adaptation , 2006, NIPS.

[14]  Hongyi Zhang,et al.  mixup: Beyond Empirical Risk Minimization , 2017, ICLR.

[15]  Thomas Hofmann,et al.  Analysis of Representations for Domain Adaptation , 2007 .

[16]  Koby Crammer,et al.  A theory of learning from different domains , 2010, Machine Learning.

[17]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[18]  Simon Andermatt,et al.  Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge , 2019, IEEE Transactions on Medical Imaging.

[19]  Stefan Klein,et al.  Improving Robustness of Deep Learning Based Knee MRI Segmentation: Mixup and Adversarial Domain Adaptation , 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).

[20]  Daguang Xu,et al.  Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation , 2020, IEEE Transactions on Medical Imaging.

[21]  Bjoern H Menze,et al.  Domain Adaptive Medical Image Segmentation via Adversarial Learning of Disease-Specific Spatial Patterns , 2020 .

[22]  W. Klunk,et al.  Relationships Between Executive Control Circuit Activity, Amyloid Burden, and Education in Cognitively Healthy Older Adults. , 2019, The American journal of geriatric psychiatry : official journal of the American Association for Geriatric Psychiatry.