论文标题
VOX2VOX：3D-GAN用于脑肿瘤分割
Vox2Vox: 3D-GAN for Brain Tumour Segmentation
论文作者
论文摘要
神经胶质瘤是最常见的原发性脑恶性肿瘤，具有不同程度的侵略性，可变预后和各种异质组织学子区域，即周围肿瘤性水肿，坏死核心，增强和非增强肿瘤核心。尽管可以使用多模式MRI轻松检测脑肿瘤，但准确的肿瘤分割是一项具有挑战性的任务。因此，使用Brats Challenge 2020提供的数据，我们提出了一个3D体积到体积生成的对抗网络，用于分割脑肿瘤。该模型称为Vox2Vox，从多通道3D MR图像产生了现实的分割输出，整体，核心和增强肿瘤的平均值为87.20％，81.14％，为78.67％，为DICE得分和6.44mm，6.44mm，24.36mm，24.36mm，24.95mm的模型，用于HAUSDER 95米的diCe SECORES和6.44mm，24.36毫米型号。用10倍的交叉验证获得。
Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histological sub-regions, i.e., peritumoral edema, necrotic core, enhancing and non-enhancing tumour core. Although brain tumours can easily be detected using multi-modal MRI, accurate tumor segmentation is a challenging task. Hence, using the data provided by the BraTS Challenge 2020, we propose a 3D volume-to-volume Generative Adversarial Network for segmentation of brain tumours. The model, called Vox2Vox, generates realistic segmentation outputs from multi-channel 3D MR images, segmenting the whole, core and enhancing tumor with mean values of 87.20%, 81.14%, and 78.67% as dice scores and 6.44mm, 24.36mm, and 18.95mm for Hausdorff distance 95 percentile for the BraTS testing set after ensembling 10 Vox2Vox models obtained with a 10-fold cross-validation.
