LRAE-Unet:a lightweight network for fully automatic segmentation of brain tumor from MRI / 中国医学物理学杂志
Chinese Journal of Medical Physics
; (6): 43-49, 2024.
Article
在 Zh
| WPRIM
| ID: wpr-1026187
Responsible library:
WPRO
ABSTRACT
A lightweight residual attention enhanced Unet(LRAE-Unet)is designed for the fully automatic brain tumor segmentation.LRAE-Unet uses lightweight residual module to solve the problems of gradient disappearance and network degradation when the network layers increases,lightweight self-attention module to suppress the irrelevant areas and highlight the significant features of specific local areas,and enhanced average pooling module with a larger field of perception to reduce the space of feature map,save computing resources and avoid over-fitting.The experiment on BraTS 2019 dataset shows that the proposed method has a Dice similarity coefficient of 91.24%,88.64%and 88.32%in the segmentations of the whole tumor,tumor core and enhanced tumor,which proves its feasibility and effectiveness for brain tumor segmentation.