Accurate brain tumor segmentation remains a challenging task due to structural complexity and great individual differences of gliomas. Leveraging the pre-eminent detail resilience of CRF and spatial feature extraction capacity of V-net, we propose a multimodal 3D Volume Generative Adversarial Network (3D-vGAN) for precise segmentation. The model utilizes Pseudo-3D for V-net improvement, adds conditional random field after generator and use original image as supplemental guidance. Results, using the BraTS-2018 dataset, show that 3D-vGAN outperforms classical segmentation models, including U-net, Gan, FCN and 3D V-net, reaching specificity over 99.8%.

翻译：由于胶质瘤结构复杂且个体差异显著，精确的脑肿瘤分割仍具挑战性。本研究结合条件随机场（CRF）卓越的细节保持能力与V-net的空间特征提取优势，提出一种用于精确分割的多模态三维体积生成对抗网络（3D-vGAN）。该模型采用Pseudo-3D技术改进V-net架构，在生成器后引入条件随机场层，并以原始图像作为辅助引导。基于BraTS-2018数据集的实验结果表明，3D-vGAN在分割性能上超越U-net、Gan、FCN及3D V-net等经典分割模型，特异性指标超过99.8%。