After a certain point, the complexity started to increase and accuracy started to decrease.
![residual neural network residual neural network](https://nmhkahn.github.io/assets/Casestudy-CNN/plain.png)
In ERV-Net, a computation-efficient network, 3D ShuffleNetV2, is firstly utilized as encoder to reduce GPU memory and improve the efficiency of ERV-Net, and then the decoder with residual blocks (Res-decoder) is introduced to avoid degradation. In this paper, we propose an efficient 3D residual neural network (ERV-Net) for brain tumor segmentation, which has less computational complexity and GPU memory consumption. However, due to the limitation of parameters and computational complexity, there is still much room for improvement in these methods. In recent years, deep learning-based methods achieve great success in brain tumor segmentation. A reliable and efficient automatic or semi-automatic segmentation method is significant for clinical practice.
![residual neural network residual neural network](https://image.slidesharecdn.com/defensadetesis-171101210111/95/deep-residual-hashing-neural-network-for-image-retrieval-23-638.jpg)
Brain tumors are the most aggressive and mortal cancers, which lead to short life expectancy.