基于变换器的并联网络在皮肤黑色素瘤分割中的应用

Application of a parallel branches network based on Transformer for skin melanoma segmentation

皮肤恶性黑色素瘤是一种常见的恶性肿瘤,针对病灶区域进行准确的分割对于该病的早期诊断非常重要。为了实现对皮肤病灶区域进行更有效、准确的分割,本文提出了一种基于变换器(Transformer)的并联网络结构。该网络由两条并联支路构成:前者为本文新构建的多重残差频域通道注意网络(MFC),后者为视觉变换网络(ViT)。首先,在MFC网络支路中,本文将多重残差模块和频域通道注意力模块(FCA)进行融合,在提高网络鲁棒性的同时加强对图像细节特征的提取;其次,在ViT网络支路中采用Transformer中的多头自注意机制(MSA)使图像的全局特征得以保留;最后,通过并联的方式将两条支路提取的特征信息结合起来,更有效地实现对图像的分割。为了验证本文算法,本文在国际皮肤成像合作组织(ISIC)2018年所公开的皮肤镜图像数据集上进行实验,结果表明本文算法的分割结果中交并比(IoU)和戴斯(Dice)系数分别达到了90.15%和94.82%,相比于最新的皮肤黑色素瘤分割网络均有较好的提升。因此,本文提出的网络能够更好地对病灶区域进行分割,为皮肤科医生提供更准确的病灶数据。

Cutaneous malignant melanoma is a common malignant tumor. Accurate segmentation of the lesion area is extremely important for early diagnosis of the disease. In order to achieve more effective and accurate segmentation of skin lesions, a parallel network architecture based on Transformer is proposed in this paper. This network is composed of two parallel branches: the former is the newly constructed multiple residual frequency channel attention network(MFC), and the latter is the visual transformer network(ViT). First, in the MFC network branch, the multiple residual module and the frequency channel attention module(FCA) module are fused to improve the robustness of the network and enhance the capability of extracting image detailed features. Second, in the ViT network branch, multiple head selfattention(MSA) in Transformer is used to preserve the global features of the image. Finally, the feature information extracted from the two branches are combined in parallel to realize image segmentation more effectively. To verify the proposed algorithm, we conducted experiments on the dermoscopy image dataset published by the International Skin Imaging Collaboration(ISIC) in 2018. The results show that the intersection-over-union(IoU) and Dice coefficients of the proposed algorithm achieve 90.15% and 94.82%, respectively, which are better than the latest skin melanoma segmentation networks. Therefore, the proposed network can better segment the lesion area and provide dermatologists with more accurate lesion data.