School of Computer Science and Engineering, Dalian Minzu University, Dalian, 116600, People's Republic of China.
Faculty of Electronic and Information Engineering, Dalian University of Technology, Dalian, 116024, People's Republic of China.
Phys Med Biol. 2024 May 27;69(11). doi: 10.1088/1361-6560/ad4081.
Brain tumor segmentation on magnetic resonance imaging (MRI) plays an important role in assisting the diagnosis and treatment of cancer patients. Recently, cascaded U-Net models have achieved excellent performance via conducting coarse-to-fine segmentation of MRI brain tumors. However, they are still restricted by obvious global and local differences among various brain tumors, which are difficult to solve with conventional convolutions.To address the issue, this study proposes a novel Adaptive Cascaded Transformer U-Net (ACTransU-Net) for MRI brain tumor segmentation, which simultaneously integrates Transformer and dynamic convolution into a single cascaded U-Net architecture to adaptively capture global information and local details of brain tumors. ACTransU-Net first cascades two 3D U-Nets into a two-stage network to segment brain tumors from coarse to fine. Subsequently, it integrates omni-dimensional dynamic convolution modules into the second-stage shallow encoder and decoder, thereby enhancing the local detail representation of various brain tumors through dynamically adjusting convolution kernel parameters. Moreover, 3D Swin-Transformer modules are introduced into the second-stage deep encoder and decoder to capture image long-range dependencies, which helps adapt the global representation of brain tumors.Extensive experiment results evaluated on the public BraTS 2020 and BraTS 2021 brain tumor data sets demonstrate the effectiveness of ACTransU-Net, with average DSC of 84.96% and 91.37%, and HD95 of 10.81 and 7.31 mm, proving competitiveness with the state-of-the-art methods.The proposed method focuses on adaptively capturing both global information and local details of brain tumors, aiding physicians in their accurate diagnosis. In addition, it has the potential to extend ACTransU-Net for segmenting other types of lesions. The source code is available at:https://github.com/chenbn266/ACTransUnet.
磁共振成像 (MRI) 上的脑肿瘤分割在协助癌症患者的诊断和治疗中起着重要作用。最近，级联 U-Net 模型通过对 MRI 脑肿瘤进行粗到精的分割，取得了优异的性能。然而，它们仍然受到各种脑肿瘤之间明显的全局和局部差异的限制，这些差异很难用传统的卷积来解决。为了解决这个问题，本研究提出了一种新颖的自适应级联 Transformer U-Net (ACTransU-Net) 用于 MRI 脑肿瘤分割，它将 Transformer 和动态卷积同时集成到单个级联 U-Net 架构中，以自适应地捕捉脑肿瘤的全局信息和局部细节。ACTransU-Net 首先将两个 3D U-Nets 级联成一个两阶段网络，从粗到精地分割脑肿瘤。然后，它将全维动态卷积模块集成到第二阶段的浅层编码器和解码器中，通过动态调整卷积核参数来增强各种脑肿瘤的局部细节表示。此外，将 3D Swin-Transformer 模块引入到第二阶段的深编码器和解码器中，以捕获图像的长程依赖关系，有助于适应脑肿瘤的全局表示。在公共 BraTS 2020 和 BraTS 2021 脑肿瘤数据集上进行的广泛实验结果表明了 ACTransU-Net 的有效性，平均 DSC 分别为 84.96%和 91.37%，HD95 分别为 10.81mm 和 7.31mm，与最先进的方法相比具有竞争力。该方法的重点是自适应地捕捉脑肿瘤的全局信息和局部细节，帮助医生进行准确的诊断。此外，它还有潜力将 ACTransU-Net 扩展到其他类型的病变分割。源代码可在：https://github.com/chenbn266/ACTransUnet。
