南方医科大学学报2025，Vol.45Issue(6)：1317-1326,10.DOI:10.12122/j.issn.1673-4254.2025.06.21
SG-UNet:基于全局注意力和自校准卷积增强的黑色素瘤分割模型
SG-UNet:a melanoma segmentation model enhanced with global attention and self-calibrated convolution
摘要
Abstract
Objective We propose a new melanoma segmentation model,SG-UNet,to enhance the precision of melanoma segmentation in dermascopy images to facilitate early melanoma detection.Methods We utilized a U-shaped convolutional neural network,UNet,and made improvements to its backbone,skip connections,and downsampling pooling sections.In the backbone,with reference to the structure of VGG,we increased the number of convolutions from 10 to 13 in the downsampling part of UNet to achieve a deepened network hierarchy that allowed capture of more refined feature representations.To further enhance feature extraction and detail recognition,we replaced the traditional convolution the backbone section with self-calibrated convolution to enhance the model's ability to capture both spatial and channel dimensional features.In the pooling part,the original pooling layer was replaced by Haar wavelet downsampling to achieve more effective multi-scale feature fusion and reduce the spatial resolution of the feature map.The global attention mechanism was then incorporated into the skip connections at each layer to enhance the understanding of contextual information of the image.Results The experimental results showed that the SG-UNet model achieved significantly improved segmentation accuracy on ISIC 2017 and ISIC 2018 datasets as compared with other current state-of-the-art segmentation models,with Dice reached 92.41%and 86.62%and IoU reaching 92.31%and 86.48%on the two datasets,respectively.Conclusion The proposed model is capable of effective and accurate segmentation of melanoma from dermoscopy images.关键词
图像分割/全局注意力机制/黑色素瘤/UNet/自校准卷积/哈尔小波下采样/SG-UNetKey words
image segmentation/global attention mechanism/melanoma/UNet/self-calibrated convolution/Haar wavelet downsampling/SG-UNet引用本文复制引用
计寰宇,王蕊,高盛祥,车文刚..SG-UNet:基于全局注意力和自校准卷积增强的黑色素瘤分割模型[J].南方医科大学学报,2025,45(6):1317-1326,10.基金项目
国家自然科学基金(U23A20388,U21B2027) （U23A20388,U21B2027）
云南省重点研发计划(202303AP140008,202401BC070021,202302AD080003) （202303AP140008,202401BC070021,202302AD080003）
云南省基础研究项目(202301AT070393) （202301AT070393）
昆明理工大学"双一流"科技专项(202402AG050007) Supported by National Natural Science Foundation of China(U23A20388,U21B2027). （202402AG050007）
