TY - JOUR
T1 - Single level UNet3D with multipath residual attention block for brain tumor segmentation
AU - Akbar, Agus Subhan
AU - Fatichah, Chastine
AU - Suciati, Nanik
N1 - Publisher Copyright:
© 2022 The Author(s)
PY - 2022/6
Y1 - 2022/6
N2 - Atrous convolution and attention have improved the performance of the UNet architecture for segmentation purposes. However, a perfect combination of atrous convolution and attention to improve brain tumor segmentation performance is still an interesting challenge. In this paper, we propose UNet architecture with the addition of attention in the skip connection and the replacement of the processing block with two atrous convolution sequences connected to the attention unit combined with one residual path called the Multipath Residual Attention Block (MRAB). The architecture was trained using the Brain Tumor Segmentation(BraTS) 2018, 2019, 2020, and 2021 challenge datasets. The ensembled model was validated online and obtained dice scores of 77.71%, 79.77%, 89.59% for BraTS2018, 74.91%, 80.98%, 88.48% for BraTS2019, 72.91%, 80.19%, 88.57% for BraTS2020, and 77.73%, 82.19%, 89.33% for BraTS2021 validation datasets for Enhanced Tumor(ET), Tumor Core(TC), and Whole Tumor(WT) areas, respectively. These dice score performances outperformed state-of-the-art brain tumor segmentation architectures and promised to be developed for clinical application.
AB - Atrous convolution and attention have improved the performance of the UNet architecture for segmentation purposes. However, a perfect combination of atrous convolution and attention to improve brain tumor segmentation performance is still an interesting challenge. In this paper, we propose UNet architecture with the addition of attention in the skip connection and the replacement of the processing block with two atrous convolution sequences connected to the attention unit combined with one residual path called the Multipath Residual Attention Block (MRAB). The architecture was trained using the Brain Tumor Segmentation(BraTS) 2018, 2019, 2020, and 2021 challenge datasets. The ensembled model was validated online and obtained dice scores of 77.71%, 79.77%, 89.59% for BraTS2018, 74.91%, 80.98%, 88.48% for BraTS2019, 72.91%, 80.19%, 88.57% for BraTS2020, and 77.73%, 82.19%, 89.33% for BraTS2021 validation datasets for Enhanced Tumor(ET), Tumor Core(TC), and Whole Tumor(WT) areas, respectively. These dice score performances outperformed state-of-the-art brain tumor segmentation architectures and promised to be developed for clinical application.
KW - Attention unit
KW - Brain tumor segmentation
KW - Multipath residual attention block
KW - Single level UNet3D
KW - atrous convolution
UR - http://www.scopus.com/inward/record.url?scp=85129039500&partnerID=8YFLogxK
U2 - 10.1016/j.jksuci.2022.03.022
DO - 10.1016/j.jksuci.2022.03.022
M3 - Article
AN - SCOPUS:85129039500
SN - 1319-1578
VL - 34
SP - 3247
EP - 3258
JO - Journal of King Saud University - Computer and Information Sciences
JF - Journal of King Saud University - Computer and Information Sciences
IS - 6
ER -