The context-based convolutional neural network (CNN) is one of the most well-known CNNs to improve the performance of semantic segmentation. It has achieved remarkable success in various medical image segmentation tasks. However, extracting rich and useful context information from complex and changeable medical images is a challenge for medical image segmentation. In this study, a novel Multi-Receptive-Field CNN (MRFNet) is proposed to tackle this challenge. MRFNet offers the optimal receptive field for each subnet in the encoder-decoder module (EDM) and generates multi-receptive-field context information at the feature map level. Moreover, MRFNet fuses these multi-feature maps by the concatenation operation. MRFNet is evaluated on 3 public medical image data sets, including SISS, 3DIRCADb, and SPES. Experimental results show that MRFNet achieves the outstanding performance on all 3 data sets, and outperforms other segmentation methods on 3DIRCADb test set without pre-training the model.

中文翻译：

---

用于医学图像语义分割的多感受野 CNN


基于上下文的卷积神经网络（CNN）是最著名的提高语义分割性能的 CNN 之一。它在各种医学图像分割任务中取得了显着的成功。然而，从复杂多变的医学图像中提取丰富且有用的上下文信息是医学图像分割的挑战。在这项研究中，提出了一种新颖的多感受野 CNN (MRFNet) 来应对这一挑战。 MRFNet 为编码器-解码器模块 (EDM) 中的每个子网提供最佳感受野，并在特征图级别生成多感受野上下文信息。此外，MRFNet 通过串联操作融合这些多特征图。 MRFNet 在 3 个公共医学图像数据集上进行评估，包括 SISS、3DIRCADb 和 SPES。实验结果表明，MRFNet 在所有 3 个数据集上都实现了出色的性能，并且在无需预训练模型的 3DIRCADb 测试集上优于其他分割方法。