Vox2Vox: 3D-GAN for Brain Tumour Segmentation

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 non-enhancing tumour core. Although tumours can easily be detected using multi-modal MRI, accurate tumor segmentation is a challenging task. Hence, data provided by BraTS Challenge 2020, we propose 3D volume-to-volume Generative Adversarial Network for tumours. The model, called Vox2Vox, generates realistic outputs from multi-channel MR images, segmenting whole, core mean values 87.20%, 81.14%, 78.67% as dice scores 6.44mm, 24.36 mm, 18.95 mm Hausdorff distance 95 percentile testing set after ensembling 10 Vox2Vox models obtained 10-fold cross-validation. code available at https://github.com/mdciri/Vox2Vox .