Adaptive cascaded transformer U-Net for MRI brain tumor segmentation.

OBJECTIVE: 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 still suffer from obvious global and local differences among various brain tumors, which are difficult to solve with conventional convolutions. APPROACH: To address the issue, this work 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. MAIN RESULTS: Extensive experiment results evaluated on the public BraTS 2020 and BraTS 2021 brain tumor datasets demonstrate the effectiveness of ACTransU-Net, with average DSC of 84.96% and 91.37%, and HD95 of 10.81 mm and 7.31 mm, proving competitiveness with the state-of-the-art methods. SIGNIFICANCE: The proposed method focuses on adaptively capturing both global information and local details of brain tumors, aiding physicians in their accurate diagnosis. Additionally, 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.

3D asymmetric expectation-maximization attention network for brain tumor segmentation.

Automatic brain tumor segmentation on MRI is a prerequisite to provide a quantitative and intuitive assistance for clinical diagnosis and treatment. Meanwhile, 3D deep neural network related brain tumor segmentation models have demonstrated considerable accuracy improvement over corresponding 2D methodologies. However, 3D brain tumor segmentation models generally suffer from high computation cost. Motivated by a recently proposed 3D dilated multi-fiber network (DMF-Net) architecture that pays more attention to reduction of computation cost, we present in this work a novel encoder-decoder neural network, ie a 3D asymmetric expectation-maximization attention network (AEMA-Net), to automatically segment brain tumors. We modify DMF-Net by introducing an asymmetric convolution block into a multi-fiber unit and a dilated multi-fiber unit to capture more powerful deep features for the brain tumor segmentation. In addition, AEMA-Net further incorporates an expectation-maximization attention (EMA) module into the DMF-Net by embedding the EMA block in the third stage of skip connection, which focuses on capturing the long-range dependence of context. We extensively evaluate AEMA-Net on three MRI brain tumor segmentation benchmarks of BraTS 2018, 2019 and 2020 datasets. Experimental results demonstrate that AEMA-Net outperforms both 3D U-Net and DMF-Net, and it achieves competitive performance compared with the state-of-the-art brain tumor segmentation methods.

SDResU-Net: Separable and Dilated Residual U-Net for MRI Brain Tumor Segmentation.

BACKGROUND: Glioma is one of the most common and aggressive primary brain tumors that endanger human health. Tumors segmentation is a key step in assisting the diagnosis and treatment of cancer disease. However, it is a relatively challenging task to precisely segment tumors considering characteristics of brain tumors and the device noise. Recently, with the breakthrough development of deep learning, brain tumor segmentation methods based on fully convolutional neural network (FCN) have illuminated brilliant performance and attracted more and more attention. METHODS: In this work, we propose a novel FCN based network called SDResU-Net for brain tumor segmentation, which simultaneously embeds dilated convolution and separable convolution into residual U-Net architecture. SDResU-Net introduces dilated block into a residual U-Net architecture, which largely expends the receptive field and gains better local and global feature descriptions capacity. Meanwhile, to fully utilize the channel and region information of MRI brain images, we separate the internal and inter-slice structures of the improved residual U-Net by employing separable convolution operator. The proposed SDResU-Net captures more pixel-level details and spatial information, which provides a considerable alternative for the automatic and accurate segmentation of brain tumors. RESULTS AND CONCLUSION: The proposed SDResU-Net is extensively evaluated on two public MRI brain image datasets, i.e., BraTS 2017 and BraTS 2018. Compared with its counterparts and stateof- the-arts, SDResU-Net gains superior performance on both datasets, showing its effectiveness. In addition, cross-validation results on two datasets illuminate its satisfying generalization ability.