TY - GEN
T1 - Multimodal Segmentation Based on a Novel 3D U-Net Deep Learning Architecture
AU - Swaroopa, K. M.
AU - Chetty, Girija
N1 - Publisher Copyright:
© IEEE 2022.
PY - 2021
Y1 - 2021
N2 - In this paper, we propose a new approach for brain image segmentation based on a novel 3D U-Net deep fusion scheme. The proposed approach takes into consideration a fusion of multiple scan modalities including FLAIR, T1, T1Gd and T2, and by using a stacked CNN based 3D U-Net architecture allows modelling of multiclass segmentation of Gliomas, an aggressive form of brain tumours. The proposed model performs well for low resource settings, and requires lesser resource requirements, and with imbalanced class distribution, and natural data augmentation, by transforming 3D volumes to 2D sequences. An extensive quantitative and qualitative experimental evaluation of the proposed model in terms of dice score and dice loss performance metrics, for two publicly available datasets, corresponding to 2018 BraTS and 2021 BraTS challenge segmentation task, shows improved performance and generalization capability of the proposed lightweight model.
AB - In this paper, we propose a new approach for brain image segmentation based on a novel 3D U-Net deep fusion scheme. The proposed approach takes into consideration a fusion of multiple scan modalities including FLAIR, T1, T1Gd and T2, and by using a stacked CNN based 3D U-Net architecture allows modelling of multiclass segmentation of Gliomas, an aggressive form of brain tumours. The proposed model performs well for low resource settings, and requires lesser resource requirements, and with imbalanced class distribution, and natural data augmentation, by transforming 3D volumes to 2D sequences. An extensive quantitative and qualitative experimental evaluation of the proposed model in terms of dice score and dice loss performance metrics, for two publicly available datasets, corresponding to 2018 BraTS and 2021 BraTS challenge segmentation task, shows improved performance and generalization capability of the proposed lightweight model.
KW - Deep Learning
KW - Fusion
KW - Image Segmentation
KW - Medical
KW - Multimodal
UR - http://www.scopus.com/inward/record.url?scp=85127904521&partnerID=8YFLogxK
UR - https://ieee-csde.org/2021/
U2 - 10.1109/CSDE53843.2021.9718438
DO - 10.1109/CSDE53843.2021.9718438
M3 - Conference contribution
AN - SCOPUS:85127904521
T3 - 2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering, CSDE 2021
BT - 2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering, CSDE 2021
A2 - Khan, MGM
A2 - Chetty, Girija
A2 - Xia, Feng
PB - IEEE, Institute of Electrical and Electronics Engineers
CY - United States
T2 - 2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering, CSDE 2021
Y2 - 8 December 2021 through 10 December 2021
ER -
