Journal
MEDICAL IMAGE ANALYSIS
Volume 68, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.media.2020.101907
Keywords
Medical image segmentation; Cross-scanner robustness; Cross-protocol robustness; Domain generalization
Categories
Funding
- Swiss Platform for Advanced Scientific Computing (PASC)
- Clinical Research Priority Program Grant on Artificial Intelligence in Oncological Imaging Network from University of Zurich
- Personalized Health and Related Technologies (PHRT) [222]
Ask authors/readers for more resources
In this study, a method to address the mismatch between training and test images in medical image segmentation is proposed. The segmentation network consists of a shallow image normalization CNN and a deep CNN, with a denoising autoencoder used to model an implicit prior. Experimental results demonstrate the performance improvement achieved by test-time adaptation.
Convolutional Neural Networks (CNNs) work very well for supervised learning problems when the train-ing dataset is representative of the variations expected to be encountered at test time. In medical image segmentation, this premise is violated when there is a mismatch between training and test images in terms of their acquisition details, such as the scanner model or the protocol. Remarkable performance degradation of CNNs in this scenario is well documented in the literature. To address this problem, we design the segmentation CNN as a concatenation of two sub-networks: a relatively shallow image nor-malization CNN, followed by a deep CNN that segments the normalized image. We train both these sub-networks using a training dataset, consisting of annotated images from a particular scanner and protocol setting. Now, at test time, we adapt the image normalization sub-network for each test image , guided by an implicit prior on the predicted segmentation labels. We employ an independently trained denoising autoencoder (DAE) in order to model such an implicit prior on plausible anatomical segmentation labels. We validate the proposed idea on multi-center Magnetic Resonance imaging datasets of three anatomies: brain, heart and prostate. The proposed test-time adaptation consistently provides performance improve-ment, demonstrating the promise and generality of the approach. Being agnostic to the architecture of the deep CNN, the second sub-network, the proposed design can be utilized with any segmentation net-work to increase robustness to variations in imaging scanners and protocols. Our code is available at: https://github.com/neerakara/test- time- adaptable- neural- networks- for- domain-generalization . (c) 2020 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ )
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available