摘要：

针对现有很多皮肤黑色素瘤图像分割算法因病灶区域形状多样、边缘模糊导致分割结果不精准的问题, 基于YOLOv8提出一种结合多尺度特征提取和边缘分割增强的皮肤黑色素瘤分割算法YOLOv8-Skin。首先, 将YOLOv8的主干网络CSPDarkNet53更换为更适合医学图像分割的U-Net v2网络, 使得在低级特征中注入丰富的语义信息, 同时精细化高级特征, 从而实现对皮肤黑色素瘤图像中对象边界的精确勾画和小结构的有效提取; 其次, 在颈部的C2f中引入可变形大核注意力(D-LKA)机制, 通过使用可变形卷积提升模型对于不规则图像结构信息的捕捉能力, 并利用大核卷积融合不同层次的特征; 最后, 在头部引入多样化分支块(DBB)形成新的分割头, 通过结合不同规模和复杂度的多样化分支增强单个卷积的表示能力, 从而增强模型对于病灶区域的特征提取。实验结果表明, YOLOv8-Skin的Dice系数、特异性、灵敏度、准确度在ISIC2017数据集上分别达到88.86%、91.34%、97.24%、96.29%, 在ISIC2018数据集上分别达到91.64%、95.42%、96.69%、95.83%, 在PH²数据集上分别达到95.92%、95.43%、97.02%、96.13%, 具有更强的分割性能, 能够更好地适用于皮肤黑色素瘤分割任务。

关键词: YOLOv8网络, 皮肤黑色素瘤分割, U-Net v2网络, 可变形大核注意力机制, 多样化分支块

Abstract:

This study proposes a skin melanoma segmentation algorithm, YOLOv8-Skin, designed to address the issue of imprecise results in existing algorithms caused by diverse shapes and blurred edges. YOLOv8-Skin combines multiscale feature extraction and enhanced edge segmentation based on YOLOv8. First, the backbone network CSPDarkNet53 of YOLOv8 is replaced with U-Net v2, which is more suitable for medical image segmentation. This change introduces rich semantic information into low-level features and refines high-level features, enabling precise delineation of lesion boundaries and effective extraction of small structures in melanoma images. Second, a Deformable-Large Kernel Attention (D-LKA) mechanism is introduced into the neck's C2f, enhancing the model's ability to capture irregular image structures through deformable convolutions and improving multilevel feature fusion using large kernel convolutions. Finally, a Diverse Branch Block (DBB) is incorporated into the head, forming a new segmentation head that enhances the representation capability of single convolutions by combining diverse branches of different scales and complexities. This enriches the feature space and improves feature extraction. Experiments conducted on the ISIC2017, ISIC2018, and PH² datasets verify the algorithm's effectiveness. On the ISIC2017 dataset, the Dice coefficient, Specificity, Sensitivity, and Accuracy reach 88.86%, 91.34%, 97.24%, and 96.29%, respectively. On the ISIC2018 dataset, they reach 91.64%, 95.42%, 96.69%, and 95.83%, respectively. On the PH² dataset, they reach 95.92%, 95.43%, 97.02%, and 96.13%, respectively. The algorithm demonstrates stronger segmentation performance and is better suited for melanoma segmentation tasks compared to existing methods.

Key words: YOLOv8 network, skin melanoma segmentation, U-Net v2 network, Deformable-Large Kernel Attention (D-LKA) mechanism, Diverse Branch Block (DBB)