Xiong Siyu, Pan Lili, Lei Qianhui, Ma Junyong, Shao Weizhi, Beckman Eric
College of Computer and Information Engineering, Central South University of Forestry and Technology, Changsha, 410004, People's Republic of China.
Chaplin School of Hospitality and Tourism Management, Florida International University, North Miami, United States of America.
Phys Med Biol. 2023 Apr 12;68(8). doi: 10.1088/1361-6560/acc630.
Skin lesion segmentation plays an important role in the diagnosis and treatment of melanoma. Existing skin lesion segmentation methods have trouble distinguishing hairs, air bubbles, and blood vessels around lesions, which affects the segmentation performance.To clarify the lesion boundary and raise the accuracy of skin lesion segmentation, a joint attention and adversarial learning network (JAAL-Net) is proposed that consists of a generator and a discriminator. In the JAAL-Net, the generator is a local fusion network (LF-Net) utilizing the encoder-decoder structure. The encoder contains a convolutional block attention module to increase the weight of lesion information. The decoder involves a contour attention to obtain edge information and locate the lesion. To aid the LF-Net generate higher confidence predictions, a discriminant dual attention network is constructed with channel attention and position attention.The JAAL-Net is evaluated on three datasets ISBI2016, ISBI2017 and ISIC2018. The intersection over union of the JAAL-Net on the three datasets are 90.27%, 89.56% and 80.76%, respectively. Experimental results show that the JAAL-Net obtains rich lesion and boundary information, enhances the confidence of the predictions, and improves the accuracy of skin lesion segmentation.The proposed approach effectively improves the performance of the model for skin lesion segmentation, which can assist physicians in accurate diagnosis well.
皮肤病变分割在黑色素瘤的诊断和治疗中起着重要作用。现有的皮肤病变分割方法难以区分病变周围的毛发、气泡和血管，这影响了分割性能。为了明确病变边界并提高皮肤病变分割的准确性，提出了一种联合注意力和对抗学习网络（JAAL-Net），它由一个生成器和一个判别器组成。在JAAL-Net中，生成器是一个利用编码器-解码器结构的局部融合网络（LF-Net）。编码器包含一个卷积块注意力模块以增加病变信息的权重。解码器涉及轮廓注意力以获取边缘信息并定位病变。为了帮助LF-Net生成更高置信度的预测，构建了一个具有通道注意力和位置注意力的判别式双注意力网络。JAAL-Net在三个数据集ISBI2016、ISBI2017和ISIC2018上进行了评估。JAAL-Net在这三个数据集上的交并比分别为90.27%、89.56%和80.76%。实验结果表明，JAAL-Net获得了丰富的病变和边界信息，增强了预测的置信度，并提高了皮肤病变分割的准确性。所提出的方法有效地提高了皮肤病变分割模型的性能，能够很好地协助医生进行准确诊断。
