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

<p>In this paper we propose to create an end-to-end brain tumor segmentation system that applies three variants of the well-known U-Net convolutional neural networks. In our results we obtain and analyse the detection performances of U-Net, VGG16-UNet and ResNet-UNet on the BraTS2020 training dataset. Further, we inspect the behavior of the ensemble model obtained as the weighted response of the three CNN models. We introduce essential preprocessing and post-processing steps so as to improve the detection performances. The original images were corrected and the different intensity ranges were transformed into the 8-bit grayscale domain to uniformize the tissue intensities, while preserving the original histogram shapes. For post-processing we apply region connectedness onto the whole tumor and conversion of background pixels into necrosis inside the whole tumor. As a result, we present the Dice scores of our system obtained for WT (whole tumor), TC (tumor core) and ET (enhanced tumor) on the BraTS2020 training dataset.</p>
</abstract>

In this paper we propose to create an end-to-end brain tumor segmentation system that applies three variants of the well-known U-Net convolutional neural networks. In our results we obtain and analyse the detection performances of U-Net, VGG16-UNet and ResNet-UNet on the BraTS2020 training dataset. Further, we inspect the behavior of the ensemble model obtained as the weighted response of the three CNN models. We introduce essential preprocessing and post-processing steps so as to improve the detection performances. The original images were corrected and the different intensity ranges were transformed into the 8-bit grayscale domain to uniformize the tissue intensities, while preserving the original histogram shapes. For post-processing we apply region connectedness onto the whole tumor and conversion of background pixels into necrosis inside the whole tumor. As a result, we present the Dice scores of our system obtained for WT (whole tumor), TC (tumor core) and ET (enhanced tumor) on the BraTS2020 training dataset.

U-Net architecture variants for brain tumor segmentation of histogram corrected images

George Emil Palade University of Medicine, Pharmacy, Science, and Technology Târgu Mureş

Department of Electrical Engineering and Information Technology

Sapientia Hungarian University of Transylvania

Cluj-Napoca Department of Electrical Engineering

Acta Universitatis Sapientiae, Informatica

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

In this paper we propose to create an end-to-end brain tumor segmentation system that applies three variants of the well-known U-Net convolutional neural...

U-Net architecture variants for brain tumor segmentation of histogram corrected images

Publié en ligne: 12 août 2022

Pages: 49 - 74

Reçu: 20 avr. 2022

Accepté: 09 mai 2022

DOI: https://doi.org/10.2478/ausi-2022-0004

Mots clés
brain tumor segmentation, histogram uniformization, U-Net, VGG16-UNet, ResNet50-UNet, BraTS2020

© 2022 Szidónia Lefkovits et al., published by Sciendo

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

U-Net architecture variants for brain tumor segmentation of histogram corrected images

Publié en ligne: 12 août 2022

Pages: 49 - 74

Reçu: 20 avr. 2022

Accepté: 09 mai 2022

DOI: https://doi.org/10.2478/ausi-2022-0004

Mots clésbrain tumor segmentation, histogram uniformization, U-Net, VGG16-UNet, ResNet50-UNet, BraTS2020

© 2022 Szidónia Lefkovits et al., published by Sciendo

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

Mots clés
brain tumor segmentation, histogram uniformization, U-Net, VGG16-UNet, ResNet50-UNet, BraTS2020