TY - GEN
T1 - Training Hacks and a Frugal Man's Net with Application to Glioblastoma Segmentation
AU - Abdallah, Jawher Ben
AU - Marrakchi-Kacem, Linda
AU - Rekik, Islem
N1 - Funding Information:
This work was supported by the research project young researchers (19PEJC09-03) entitled Development of automatic survival prediction tool for glioblastoma using multi-contrast MR imaging which is funded by the Ministry of Higher Education and Scientific Research of Tunisia
Publisher Copyright:
© 2022 IEEE.
PY - 2022/6/28
Y1 - 2022/6/28
N2 - In this paper, we investigate the effectiveness of training a sparse Neural Network on a limited number of samples in the context of brain tumor segmentation. Nowadays, Deep Learning architectures are getting deeper, more sophisticated and environmentally unfriendly in an effort to improve their segmentation performance. We use a brain tumor segmentation dataset and apply simple practices to reduce the needed computational resources to allow cheap and fast training. We also present a lighter, cheaper version of the U-Net dubbed Frugal U-Net stemming from our investigation on how far we can push the original U-Net by decreasing its parameter count using Depth-Wise Separable Convolutions instead of regular ones, all the while preserving the minimum levels of accuracy required in Medical Imaging. Our methodology is useful in clinical facilities where high-computation resources are limited.
AB - In this paper, we investigate the effectiveness of training a sparse Neural Network on a limited number of samples in the context of brain tumor segmentation. Nowadays, Deep Learning architectures are getting deeper, more sophisticated and environmentally unfriendly in an effort to improve their segmentation performance. We use a brain tumor segmentation dataset and apply simple practices to reduce the needed computational resources to allow cheap and fast training. We also present a lighter, cheaper version of the U-Net dubbed Frugal U-Net stemming from our investigation on how far we can push the original U-Net by decreasing its parameter count using Depth-Wise Separable Convolutions instead of regular ones, all the while preserving the minimum levels of accuracy required in Medical Imaging. Our methodology is useful in clinical facilities where high-computation resources are limited.
KW - Brain Tumour
KW - Low-Budget
KW - Multiclass-Segmentation
KW - U-Net
UR - http://www.scopus.com/inward/record.url?scp=85134256463&partnerID=8YFLogxK
U2 - 10.1109/ATSIP55956.2022.9805950
DO - 10.1109/ATSIP55956.2022.9805950
M3 - Conference contribution
AN - SCOPUS:85134256463
T3 - International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2022
SP - 1
EP - 4
BT - International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 6th International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2022
Y2 - 24 May 2022 through 27 May 2022
ER -