<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Researchers address the generalization problem of deep image processing networks mainly through extensive use of data augmentation techniques such as random flips, rotations, and deformations. A data augmentation technique called mixup, which constructs virtual training samples from convex combinations of inputs, was recently proposed for deep classification networks. The algorithm contributed to increased performance on classification in a variety of datasets, but so far has not been evaluated for image segmentation tasks. In this paper, we tested whether the mixup algorithm can improve the generalization performance of deep segmentation networks for medical image data. We trained a standard U-net architecture to segment the prostate in 100 T2-weighted 3D magnetic resonance images from prostate cancer patients, and compared the results with and without mixup in terms of Dice similarity coefficient and mean surface distance from a reference segmentation made by an experienced radiologist. Our results suggest that mixup offers a statistically significant boost in performance compared to non-mixup training, leading to up to 1.9% increase in Dice and a 10.9% decrease in surface distance. The mixup algorithm may thus offer an important aid for medical image segmentation applications, which are typically limited by severe data scarcity.</p>
</abstract>

Researchers address the generalization problem of deep image processing networks mainly through extensive use of data augmentation techniques such as random flips, rotations, and deformations. A data augmentation technique called mixup, which constructs virtual training samples from convex combinations of inputs, was recently proposed for deep classification networks. The algorithm contributed to increased performance on classification in a variety of datasets, but so far has not been evaluated for image segmentation tasks. In this paper, we tested whether the mixup algorithm can improve the generalization performance of deep segmentation networks for medical image data. We trained a standard U-net architecture to segment the prostate in 100 T2-weighted 3D magnetic resonance images from prostate cancer patients, and compared the results with and without mixup in terms of Dice similarity coefficient and mean surface distance from a reference segmentation made by an experienced radiologist. Our results suggest that mixup offers a statistically significant boost in performance compared to non-mixup training, leading to up to 1.9% increase in Dice and a 10.9% decrease in surface distance. The mixup algorithm may thus offer an important aid for medical image segmentation applications, which are typically limited by severe data scarcity.

Mixup (Sample Pairing) Can Improve the Performance of Deep Segmentation Networks

Department of Oncology and Hemato-oncology

Journal of Artificial Intelligence and Soft Computing Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"Mixup (Sample Pairing) Can Improve the Performance of Deep Segmentation Networks"}

Researchers address the generalization problem of deep image processing networks mainly through extensive use of data augmentation techniques such as random...

Mixup (Sample Pairing) Can Improve the Performance of Deep Segmentation Networks

Published Online: Oct 08, 2021

Page range: 29 - 39

Received: Mar 11, 2021

Accepted: Jul 02, 2021

DOI: https://doi.org/10.2478/jaiscr-2022-0003

Keywords
magnetic resonance imaging, segmentation, prostate, data augmentation, mixup

© 2022 Lars J. Isaksson et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Mixup (Sample Pairing) Can Improve the Performance of Deep Segmentation Networks

Published Online: Oct 08, 2021

Page range: 29 - 39

Received: Mar 11, 2021

Accepted: Jul 02, 2021

DOI: https://doi.org/10.2478/jaiscr-2022-0003

Keywordsmagnetic resonance imaging, segmentation, prostate, data augmentation, mixup

© 2022 Lars J. Isaksson et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Keywords
magnetic resonance imaging, segmentation, prostate, data augmentation, mixup