Shao Dangguo, Ren Lifan, Ma Lei
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China.
Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology, Kunming 650500, China.
Biomedicines. 2023 Jun 16;11(6):1733. doi: 10.3390/biomedicines11061733.
Segmentation of skin lesion images facilitates the early diagnosis of melanoma. However, this remains a challenging task due to the diversity of target scales, irregular segmentation shapes, low contrast, and blurred boundaries of dermatological graphics. This paper proposes a multi-scale feature fusion network (MSF-Net) based on comprehensive attention convolutional neural network (CA-Net). We introduce the spatial attention mechanism in the convolution block through the residual connection to focus on the key regions. Meanwhile, Multi-scale Dilated Convolution Modules (MDC) and Multi-scale Feature Fusion Modules (MFF) are introduced to extract context information across scales and adaptively adjust the receptive field size of the feature map. We conducted many experiments on the public data set ISIC2018 to verify the validity of MSF-Net. The ablation experiment demonstrated the effectiveness of our three modules. The comparison experiment with the existing advanced network confirms that MSF-Net can achieve better segmentation under fewer parameters.
皮肤病变图像的分割有助于黑色素瘤的早期诊断。然而，由于目标尺度的多样性、分割形状不规则、对比度低以及皮肤病图像边界模糊，这仍然是一项具有挑战性的任务。本文提出了一种基于综合注意力卷积神经网络（CA-Net）的多尺度特征融合网络（MSF-Net）。我们通过残差连接在卷积块中引入空间注意力机制，以聚焦关键区域。同时，引入多尺度扩张卷积模块（MDC）和多尺度特征融合模块（MFF）来跨尺度提取上下文信息，并自适应调整特征图的感受野大小。我们在公共数据集ISIC2018上进行了许多实验，以验证MSF-Net的有效性。消融实验证明了我们三个模块的有效性。与现有先进网络的对比实验证实，MSF-Net在参数较少的情况下能够实现更好的分割。
