Dutta Tapas Kumar, Nayak Deepak Ranjan, Pachori Ram Bilas
School of Computer Science and Electronic Engineering, University of Surrey, Guildford, GU27XH United Kingdom.
Department of Computer Science and Engineering, Malaviya National Institute of Technology Jaipur, Jaipur, Rajasthan 302017 India.
Biomed Eng Lett. 2024 May 31;14(5):1069-1077. doi: 10.1007/s13534-024-00393-0. eCollection 2024 Sep.
Multiclass classification of brain tumors from magnetic resonance (MR) images is challenging due to high inter-class similarities. To this end, convolution neural networks (CNN) have been widely adopted in recent studies. However, conventional CNN architectures fail to capture the small lesion patterns of brain tumors. To tackle this issue, in this paper, we propose a global transformer network dubbed GT-Net for multiclass brain tumor classification. The GT-Net mainly comprises a global transformer module (GTM), which is introduced on the top of a backbone network. A generalized self-attention block (GSB) is proposed to capture the feature inter-dependencies not only across spatial dimension but also channel dimension, thereby facilitating the extraction of the detailed tumor lesion information while ignoring less important information. Further, multiple GSB heads are used in GTM to leverage global feature dependencies. We evaluate our GT-Net on a benchmark dataset by adopting several backbone networks, and the results demonstrate the effectiveness of GTM. Further, comparison with state-of-the-art methods validates the superiority of our model.
由于脑肿瘤在磁共振（MR）图像中的类间相似度较高，因此对其进行多类别分类具有挑战性。为此，卷积神经网络（CNN）在最近的研究中得到了广泛应用。然而，传统的CNN架构无法捕捉脑肿瘤的小病灶模式。为了解决这个问题，在本文中，我们提出了一种名为GT-Net的全局Transformer网络用于多类别脑肿瘤分类。GT-Net主要由一个全局Transformer模块（GTM）组成，该模块被引入到骨干网络的顶部。我们提出了一种广义自注意力块（GSB），它不仅可以跨空间维度捕捉特征间的依赖关系，还可以跨通道维度捕捉特征间的依赖关系，从而在忽略不太重要信息的同时，促进详细肿瘤病灶信息的提取。此外，GTM中使用了多个GSB头来利用全局特征依赖关系。我们通过采用几种骨干网络在一个基准数据集上评估了我们的GT-Net，结果证明了GTM的有效性。此外，与现有方法的比较验证了我们模型的优越性。
