首页|融合多尺度Transformer的皮肤病变分割算法

融合多尺度Transformer的皮肤病变分割算法

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
针对现有皮肤病变图像分割时缺乏多尺度特征提取,从而导致细节信息缺失和病变区域误分割的问题,本文提出一种融合多尺度Transformer的编解码网络皮肤病变分割算法.首先运用Transformer模块构建分层编码器,分层编码器从全局特征变化角度出发,多尺度分析皮肤病变区域;然后利用多尺度融合模块、通道注意力模块和联合层构建融合解码器,多尺度融合模块互补分层编码器中浅层网络信息与深层网络信息,增强空间信息和语义信息间的依赖关系,通道注意力模块能够有效识别特征丰富的通道,提高算法分割精度;最后引入扩展模块恢复图像大小以匹配实际需求.将该算法在ISBI2016、ISBI2017和ISIC2018三个公共数据集上进行实验测试,其像素精度分别为 96.70%、94.50%和 95.39%,平均交并比分别为91.69%、85.74%和 89.29%,算法测试整体性能优于现有算法.仿真实验证明,多尺度Transformer编解码网络能够有效地分割皮肤病变图像.
Fusion multi-scale Transformer skin lesion segmentation algorithm
To address the problem of lack of multi-scale feature extraction in existing skin lesion image segmentation,which leads to lack of detailed information and incorrect segmentation of skin lesion regions,this paper proposes a fusion multi-scale Transformer encoder-decoder network skin lesion segmentation algorithm.First,a hierarchical encoder is constructed using Transformer Block,which analyses the skin lesion region from the perspective of global feature variation at multiple scales.Then,the multi-scale fusion module,channel attention module and concat layer are used to construct the fusion decoder.The multi-scale fusion module fuses shallow network information and deep network information in the hierarchical encoder to enhance the dependency between spatial and semantic information,and the channel attention module can effectively identify channels containing rich feature information and improve the segmentation accuracy of the algorithm.Finally,an expansion module is introduced to recover the image size to meet the practical requirements.The proposed algorithm was experimentally tested on three public datasets,ISBI2016,ISBI2017 and ISIC2018.The pixel accuracies were 96.70%,94.50%and 95.39%,respectively,and the mean intersection over union were 91.69%,85.74%and 89.29%,respectively,with the overall performance of the tested algorithms outperforming existing algorithms.Simulation experiments show that the multi-scale Transformer encoder-decoder network can effectively segment skin lesion images,providing a new window for the diagnosis of modern skin diseases.

computer application technologyskin lesionsimage segmentationtransformermulti-scale fusion modulechannel attention module

梁礼明、周珑颂、尹江、盛校棋

展开 >

江西理工大学 电气工程与自动化学院,江西 赣州 341000

华南理工大学 计算机科学与工程学院,广东 广州 510006

计算机应用技术 皮肤病变 图像分割 Transformer 多尺度融合模块 通道注意力模块

国家自然科学基金国家自然科学基金江西省教育厅科学技术研究重点项目江西省研究生创新专项

6146301851365017GJJ170491YC2021-S585

2024

10.13229/j.cnki.jdxbgxb.20220692

吉林大学学报(工学版)
吉林大学

吉林大学学报(工学版)

CSTPCD北大核心
影响因子：0.792
ISSN：1671-5497
年,卷(期)：2024.54(4)
  • 27