A transformer-based generative adversarial network for brain tumor segmentation

• Published in: Frontiers in neuroscience Vol. 16; p. 1054948
• Main Authors: Huang, Liqun, Zhu, Enjun, Chen, Long, Wang, Zhaoyang, Chai, Senchun, Zhang, Baihai
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 30.11.2022; Frontiers Media S.A
• Subjects: automatic segmentation; Brain cancer; brain tumor; Brain tumors; Datasets; deep learning; generative adversarial network; Image processing; Magnetic resonance imaging; Medical research; Methods; Neuroscience; Segmentation; Semantics; transformer; Tumors; generative adversarial network; transformer; deep learning; brain tumor; automatic segmentation
• ISSN: 1662-4548; 1662-453X; 1662-453X
• DOI: 10.3389/fnins.2022.1054948

Brain tumor segmentation remains a challenge in medical image segmentation tasks. With the application of transformer in various computer vision tasks, transformer blocks show the capability of learning long-distance dependency in global space, which is complementary to CNNs. In this paper, we proposed a novel transformer-based generative adversarial network to automatically segment brain tumors with multi-modalities MRI. Our architecture consists of a generator and a discriminator, which is trained in min-max game progress. The generator is based on a typical "U-shaped" encoder-decoder architecture, whose bottom layer is composed of transformer blocks with Resnet. Besides, the generator is trained with deep supervision technology. The discriminator we designed is a CNN-based network with multi-scale loss, which is proved to be effective for medical semantic image segmentation. To validate the effectiveness of our method, we conducted exclusive experiments on BRATS2015 dataset, achieving comparable or better performance than previous state-of-the-art methods. On additional datasets, including BRATS2018 and BRATS2020, experimental results prove that our technique is capable of generalizing successfully.