Convolutional neural networks (CNNs) have been used quite successfully for semantic segmentation of brain tumors. However, current CNNs and attention mechanisms are stochastic in nature and neglect the morphological indicators used by radiologists to manually annotate regions of interest. In this paper, we introduce a channel and spatial wise asymmetric attention (CASPIAN) by leveraging the inherent structure of tumors to detect regions of saliency. To demonstrate the efficacy of our proposed layer, we integrate this into a well-established convolutional neural network (CNN) architecture to achieve higher Dice scores, with less GPU resources. Also, we investigate the inclusion of auxiliary multiscale and multiplanar attention branches to increase the spatial context crucial in semantic segmentation tasks. The resulting architecture is the new CASPIANET++, which achieves Dice Scores of 91.19%, 87.6% and 81.03% for whole tumor, tumor core and enhancing tumor respectively. Furthermore, driven by the scarcity of brain tumor data, we investigate the Noisy Student method for segmentation tasks. Our new Noisy Student Curriculum Learning paradigm, which infuses noise incrementally to increase the complexity of the training images exposed to the network, further boosts the enhancing tumor region to 81.53%. Additional validation performed on the BraTS2020 data shows that the Noisy Student Curriculum Learning method works well without any additional training or finetuning.

1. Mazzara, G. P., et al. (2004). Brain tumor target volume determination for radiation treatment planning through automated MRI segmentation. International Journal of Radiation Oncology, Biology, Physics.
2. Stupp, R. (2009). Effects of radiotherapy with concomitant and adjuvant temozolomide versus radiotherapy alone on survival in glioblastoma in a randomised phase III study: 5-year analysis of the EORTC-NCIC trial. The Lancet Oncology.
3. Havaei, M., et al. (2017). Brain tumor segmentation with deep neural networks. Medical Image Analysis.
4. Kamnitsas, K., et al. (2017). Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Medical Image Analysis.
5. Schlemper, J., et al. (2019). Attention gated networks: Learning to leverage salient regions in medical images. Medical Image Analysis.
6. Daimary, D., et al. Brain tumor segmentation from MRI images using hybrid convolutional neural networks.
7. Chen, H., et al. (2020). Brain tumor segmentation with deep convolutional symmetric neural network. Neurocomputing.
8. Crawford, T. J., et al. (2017). Expertise affects inter-observer agreement at peripheral locations within a brain tumor. Frontiers in Psychology.
9. Ostrom, Q. T., et al. (2019). CBTRUS statistical report: Primary brain and other central nervous system tumors diagnosed in the United States in 2012–2016. Neuro-Oncology.
10. Pereira, S., et al. Deep convolutional neural networks for the segmentation of gliomas in multi-sequence MRI.
11. Long, J., Shelhamer, E., & Darrell, T. Fully convolutional networks for semantic segmentation.
12. Ronneberger, O., Fischer, P., & Brox, T. U-Net: Convolutional networks for biomedical image segmentation.
13. Vaswani, A., et al. Attention is all you need.
14. Hu, J., Shen, L., & Sun, G. Squeeze-and-Excitation networks.
15. Tustison, N. J., et al. (2015). Optimal symmetric multimodal templates and concatenated random forests for supervised brain tumor segmentation (simplified) with ANTsR. Neuroinformatics.
16. Erihov, M., et al. A cross saliency approach to asymmetry-based tumor detection.
17. Menze, B. H., et al. (2015). The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Transactions on Medical Imaging.
18. Deng, J., et al. (2010). ImageNet: A large-scale hierarchical image database.
19. Lee, D.-H. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks.
20. Xie, Q., et al. (2020). Self-training with noisy student improves ImageNet classification.
21. Zoph, B., et al. (2020). Rethinking pre-training and self-training.
22. Isensee, F., et al. nnU-Net for brain tumor segmentation.