College of Data Science, Taiyuan University of Technology, Jinzhong 030600, China; Technology Research Centre of Spatial Information Network Engineering of Shanxi, Jinzhong 030600, China.
College of Data Science, Taiyuan University of Technology, Jinzhong 030600, China; Technology Research Centre of Spatial Information Network Engineering of Shanxi, Jinzhong 030600, China.
Comput Methods Programs Biomed. 2022 Jan;213:106493. doi: 10.1016/j.cmpb.2021.106493. Epub 2021 Oct 24.
Segmentation of rectal cancerous regions using 2D Magnetic Resonance Imaging (MRI) images is a critical step in radiation therapy. The shape of rectal cancer has significant variations and the shape of some surrounding organs is similar to that of rectal cancer; these conditions significantly affect the segmentation accuracy of rectal cancer and lead to incorrect segmentation. Therefore, automatic segmentation of rectal cancer is urgently needed, and it is a great challenge. For this task, the existing deep learning-based approaches have two shortcomings: 1) The U-Net network plays an important role in the field of medical segmentation. However, the designs of encoders and decoders in traditional U-Net networks are relatively simple and cannot extract good features, resulting in incorrect segmentation results. 2) Conventional neural networks extract high-level features that often do not include sufficient high-resolution contour information, resulting in ambiguity in contour segmentation. In this paper, we propose an improved U-Net network based on contour prediction, aiming at effective segmentation of rectal cancer.
We designed a new U-Net network by improving the traditional U-Net network. We made four improvements: 1) We replaced the encoders with the SENet network. 2) A global pooling layer was added after the last encoder. 3) We added the Spatial and Channel Squeeze & Excitation (SCSE) attention mechanism module to each decoder. 4) We concatenated the output results of each decoder. In addition, the model implemented content segmentation and contour segmentation for rectal cancer in parallel, so that both the content and contour information was learned by the network to enhance the segmentation accuracy.
Our data were obtained from the Shanxi Provincial Cancer Hospital and included 3773 2D MRI rectal cancer images. The proposed method achieved an Mean Intersection over Union of 0.894 (MIoU) on the test set. Compared with state-of-the-art methods, our method had the best performance on the test set, and its MIoU metric was 0.123 higher than that of the second-best model. At the same time, the effectiveness of the improvements to our method was demonstrated through ablation experiments.
Our method can help radiologists to segment effectively, save their time and energy, and enable them to focus on cases that are not easily segmented because of the complex shape of rectal cancer.
使用二维磁共振成像（MRI）图像对直肠癌区域进行分割是放射治疗的关键步骤。直肠癌的形状变化较大，且一些周围器官的形状与直肠癌相似，这会严重影响直肠癌的分割准确性，导致分割错误。因此，迫切需要对直肠癌进行自动分割，这是一个巨大的挑战。对于这项任务，现有的基于深度学习的方法存在两个缺点：1）U-Net 网络在医学分割领域发挥着重要作用。然而，传统 U-Net 网络的编码器和解码器设计相对简单，无法提取良好的特征，导致分割结果不正确。2）传统神经网络提取的高层特征通常不包含足够的高分辨率轮廓信息，导致轮廓分割不明确。本文提出了一种基于轮廓预测的改进 U-Net 网络，旨在实现直肠癌的有效分割。
我们通过改进传统 U-Net 网络设计了一个新的 U-Net 网络。我们对其进行了四项改进：1）用 SENet 网络替换编码器。2）在最后一个编码器后添加一个全局池化层。3）在每个解码器中添加空间和通道挤压激励（SCSE）注意力机制模块。4）将每个解码器的输出结果串联起来。此外，该模型并行实现了直肠癌的内容分割和轮廓分割，使网络同时学习内容和轮廓信息，提高分割精度。
我们的数据来自山西省肿瘤医院，包含 3773 张二维 MRI 直肠癌图像。在测试集上，我们的方法实现了 0.894 的平均交并比（MIoU）。与最先进的方法相比，我们的方法在测试集上的性能最好，其 MIoU 指标比第二好的模型高 0.123。同时，通过消融实验证明了我们方法的改进是有效的。
我们的方法可以帮助放射科医生进行有效的分割，节省他们的时间和精力，使他们能够专注于因直肠癌形状复杂而不易分割的病例。
