Context-endcoding for neural network based skull stripping in magnetic resonance imaging
This addresses the computational and memory challenges in 3D deep learning for medical imaging by improving 2D methods, offering an incremental but efficient solution for brain analysis tasks.
The paper tackles the problem of skull stripping in MRI by proposing a context-encoding method to enhance 2D neural networks with 3D semantic information, achieving dice scores of 99.6% on NFBS, 99.09% on LPBA40, and 99.17% on OASIS, outperforming state-of-the-art methods.
Skull stripping is usually the first step for most brain analysisprocess in magnetic resonance images. A lot of deep learn-ing neural network based methods have been developed toachieve higher accuracy. Since the 3D deep learning modelssuffer from high computational cost and are subject to GPUmemory limit challenge, a variety of 2D deep learning meth-ods have been developed. However, existing 2D deep learn-ing methods are not equipped to effectively capture 3D se-mantic information that is needed to achieve higher accuracy.In this paper, we propose a context-encoding method to em-power the 2D network to capture the 3D context information.For the context-encoding method, firstly we encode the 2Dfeatures of original 2D network, secondly we encode the sub-volume of 3D MRI images, finally we fuse the encoded 2Dfeatures and 3D features with semantic encoding classifica-tion loss. To get computational efficiency, although we en-code the sub-volume of 3D MRI images instead of buildinga 3D neural network, extensive experiments on three bench-mark Datasets demonstrate our method can achieve superioraccuracy to state-of-the-art alternative methods with the dicescore 99.6% on NFBS and 99.09 % on LPBA40 and 99.17 %on OASIS.