College of Computer Science and Technology, Jilin University, Changchun 130000, China.
College of Artificial Intelligence, Jilin University, Changchun 130000, China.
Comput Intell Neurosci. 2022 May 20;2022:4103524. doi: 10.1155/2022/4103524. eCollection 2022.
Medical multiobjective image segmentation aims to group pixels to form multiple regions based on the different properties of the medical images. Segmenting the 3D cardiovascular magnetic resonance (CMR) images is still a challenging task owing to several reasons, including individual differences in heart shapes, varying signal intensities, and differences in data signal-to-noise ratios. This paper proposes a novel and efficient U-Net-based 3D sparse convolutional network named SparseVoxNet. In this network, there are direct connections between any two layers with the same feature-map size, and the number of connections is reduced. Therefore, the SparseVoxNet can effectively cope with the optimization problem of gradients vanishing when training a 3D deep neural network model on small sample data by significantly decreasing the network depth, and achieveing better feature representation using a spatial self-attention mechanism finally. The proposed method in this paper has been thoroughly evaluated on the HVSMR 2016 dataset. Compared with other methods, the method achieves better performance.
医学多目标图像分割旨在根据医学图像的不同特性将像素分组形成多个区域。由于多种原因，分割 3D 心血管磁共振（CMR）图像仍然是一项具有挑战性的任务，包括心脏形状的个体差异、不同的信号强度以及数据信噪比的差异。本文提出了一种新颖而有效的基于 U-Net 的 3D 稀疏卷积网络，名为 SparseVoxNet。在该网络中，任何两个具有相同特征图大小的层之间都有直接连接，并且连接的数量减少了。因此，SparseVoxNet 通过显著减少网络深度，在小样本数据上训练 3D 深度神经网络模型时，可以有效地应对梯度消失的优化问题，并最终使用空间自注意机制实现更好的特征表示。本文提出的方法在 HVSMR 2016 数据集上进行了全面评估。与其他方法相比，该方法表现更好。
