| 329 | 7 | 435 |
| 下载次数 | 被引频次 | 阅读次数 |
皮肤病变自动分割对协助医生临床诊断、治疗及术后观察都具有非常重要的意义。现有卷积擅长建立局部相关性但无法捕获像素长程依赖关系，而Tansformer可以建立特征信息的全局依赖关系但会造成局部细节信息丢失。因此，提出了一种融合卷积和Transformer的多尺度自动分割网络。采用ResNet34作为基础编码块，利用其金字塔结构建立病灶的多级局部相关性；采用Swin Transformer模块捕获上下文特征的长程依赖关系，考虑到病灶形状多变、大小不一等情况，提出多尺度特征聚合模块来进一步提取上下文特征多尺度信息；采用具有注意力机制的解码块逐步融合编码块提取到的多级语义信息。实验结果表明，所提模型在ISIC 2017数据集上测试所得的Dice系数分别高达89.55%,FPS高达83,与其他先进模型相比，本模型参数更少、推理速度更快、精度更高。
Abstract：Automatic segmentation of skin lesions is of great significance to assist doctors in clinical diagnosis, treatment, and postoperative observation. Existing convolutions are good at establishing local correlations but cannot capture pixel long-range dependencies, while Tansformer can establish global dependencies of feature information but can cause the loss of local details. Therefore, a multi-scale automatic segmentation network that combines convolution and Transformer is proposed. Firstly, ResNet34 is used as the basic coding block, using its pyramid structure to establish multi-level local correlation of lesions; secondly, the Swin Transformer module is used to capture the long-term dependence of context features. Considering the variable shape and size of lesions, a multi-scale feature aggregation module is proposed to further extract multi-scale information of context features; finally, a decoding block with attention mechanism is used to gradually fuse the multi-level semantic information extracted from the coding block. The experimental results show that the Dice coefficients obtained by the proposed model tested on the ISIC 2017 dataset are as high as 89.55%, and the FPS is as high as 83. Compared with other advanced models, this model has fewer parameters, faster reasoning speed, and higher accuracy.
[1] HAY R J,JOHNS N E,WILLIAMS H C,et al.The Global Burden of Skin Disease in 2010:An Analysis of the Prevalence and Impact of Skin Conditions[J].Journal of Investigative Dermatology,2014,134(6):1527-1534.
[2] KASMI R,MOKRANI K.Classification of Malignant Melanoma and Benign Skin Lesions:Implementation of Automatic ABCD Rule[J].IET Image Processing,2016,10(6):448-455.
[3] CELEBI M E,KINGRAVI H A,UDLIN B,et al.A Metho-dological Approach to the Classification of Dermoscopy Images[J].Computerized Medical Imaging and Graphics,2007,31(6):362-373.
[4] SIEGEL R L,MILLER K D,FUCHS H E,et al.Cancer Statistics,2022[J].CA:A Cancer Journal for Clinicians,2022,72(1):7-33.
[5] 徐国雄，张骁，胡进贤，等.基于阈值分割和轮廓提取的图像边缘检测算法[J].计算机技术与发展，2015,25(12):64-67.
[6] RIYANTO I.Morphology Based Melanoma Skin Segmentation Method[J].The Scientific Explorer,2021,11(3):7-13.
[7] 尹雨山，王李进，尹义龙，等.回溯搜索优化算法辅助的多阈值图像分割[J].智能系统学报，2015,10(1):68-74.
[8] LAKSHMI B V,SRIDEVI K.A Qualitative Approach on Denoising and Segmentation Algorithms for Melanoma Ima-ges[J].Annals of the Romanian Society for Cell Biology,2021,25(2):1384-1393.
[9] 孔令军，王茜雯，包云超，等.基于深度学习的医疗图像分割综述[J].无线电通信技术，2021,47(2):121-130.
[10] ALPHONSE A S,STARVIN M S.A Novel and Efficient Approach for the Classification of Skin Melanoma[J].Journal of Ambient Intelligence and Humanized Computing,2021,12(12):10435-10459.
[11] SHELHAMER E,LONG J,DARRELL T.Fully Convolutional Networks for Semantic Segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.
[12] YUAN Y D,CHAO M,LO Y C.Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks with Jaccard Distance[J].IEEE Transactions on Medical Imaging,2017,36(9):1876-1886.
[13] RONNEBERGER O,FISCHER P,BROX T.U-Net:Con-volutional Networks for Biomedical Image Segmentation[C]//MICCAI 2015:Medical Image Computing and Computer-Assisted Intervention.Munich:Springer,2015:234-241.
[14] ZHANG J X,JIANG Z K,DONG J,et al.Attention Gate ResU-Net for Automatic MRI Brain Tumor Segmentation[J].IEEE Access,2020,8:58533-58545.
[15] ZHOU Z W,SIDDIQUEE M M R,TAJBAKHSH N,et al.Unet++:A Nested U-Net Architecture for Medical Image Segmentation[C]//DLMIA 2018,ML-CDS 2018:Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support.Granada:Springer,2018:3-11.
[16] GU Z W,CHENG J,FU H Z,et al.CE-Net:Context Encoder Network for 2D Medical Image Segmentation[J].IEEE Transactions on Medical Imaging,2019,38(10):2281-2292.
[17] BI L,KIM J,AHN E,et al.Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks[J].IEEE Transactions on Biomedical Engineering,2017,64(9):2065-2074.
[18] TANG Y J,YANG F,YUAN S F.A Multi-stage Framework with Context Information Fusion Structure for Skin Lesion Segmentation[C]//2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).Venice:IEEE,2019:1407-1410.
[19] DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.An Image Is Worth 16×16 Words:Transformers for Image Recognition at Scale[EB/OL].(2021-06-03) [2023-05-11].https://arxiv.org/abs/2010.11929.
[20] LIU Z,LIN Y T,CAO Y,et al.Swin Transformer:Hierarchical Vision Transformer Using Shifted Windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.Montreal:IEEE,2021:10012-10022.
[21] CAO H,WANG Y Y,CHEN J,et al.Swin-Unet:Unet-like Pure Transformer for Medical Image Segmentation[C]//European Conference on Computer Vision.Tel Aviv:Springer,2023:205-218.
[22] CHEN J N,LI Y Y,YU Q H,et al.TransUNet:Transfor-mers Make Strong Encoders for Medical Image Segmentation[EB/OL].(2021-02-08) [2023-05-11].https://arxiv.org/abs/2102.04306.
[23] CHEN J Y,CHEN J N,ZHOU Z W,et al.MT-TransUNet:Mediating Multi-task Tokens in Transformers for Skin Lesion Segmentation and Classification[EB/OL].(2021-12-03) [2023-05-11].https://arxiv.org/abs/2112.01767.
[24] LIN A,CHEN B,XU J,et al.DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation[J].IEEE Transactions on Instrumentation and Measurement,2022,71:1-15.
[25] HE K M,ZHANG X Y,REN S Q,et al.Deep Residual Learning for Image Recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016:770-778.
[26] WANG Q L,WU B G,ZHU P F,et al.ECA-Net:Efficient Channel Attention for Deep Convolutional Neural Networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Settle:IEEE,2020:11534-11542.
[27] CODELLA N C F,GUTMAN D,CELEBI M E,et al.Skin Lesion Analysis Toward Melanoma Detection:A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI),Hosted by the International Skin Imaging Collaboration (ISIC)[C]//2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).Washington D.C.:IEEE,2018:168-172.
[28] XIE Y T,ZHANG J P,XIA Y,et al.A Mutual Hootstranning Model for Automated Skin Lesion Segmentation and Classification[J].IEEE Transactions on Medical Ima-ging,2020,39(7):2482-2493.
[29] GOYAL M,OAKLEY A,BANSAL P,et al.Skin Lesion Segmentation in Dermoscopic Images with Ensemble Deep Learning Methods[J].IEEE Access,2019,8:4171-4181.
[30] LEI B Y,XIA Z M,JIANG F,et al.Skin Lesion Segmentation via Generative Adversarial Networks with Dual Discriminators[J].Medical Image Analysis,2020,64:101716.
[31] WANG H N,CAO P,WANG J Q,et al.UCTransNet:Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer[C]//Proceedings of the AAAI Conference on Artificial Intelligence.[S.l.]:AAAI,2022:2441-2449.
[32] WU H S,CHEN S H,CHEN G L,et al.FAT-Net:Feature Adaptive Transformers for Automated Skin Lesion Segmentation[J].Medical image analysis,2022,76:102327.
基本信息:
中图分类号:R739.5;TP391.41
引用信息:
[1]蒋新辉,李筱林,韦春苗,等.融合卷积和Transformer的多尺度皮肤病变分割算法[J].无线电工程,2024,54(03):670-678.
基金信息:
2022年度广西高校中青年项目(2022KY1414); 2023年度广西高校中青年项目(2023KY1264)~~
2023-09-04
2023-09-04
2023-09-04