计算机科学 ›› 2026, Vol. 53 ›› Issue (3): 277-286.doi: 10.11896/jsjkx.250200049
张伟1,2,3, 梁敦英1, 周婉婷1, 程祥1
ZHANG Wei1,2,3, LIANG Dunying1, ZHOU Wanting1, CHENG Xiang1
摘要： 针对皮肤病灶边缘模糊、毛发等噪声导致的分割病灶区域不完整、病灶特征分布差异较大等问题,基于U-Net提出一种结合浓缩注意力机制和残差空间特征变换的皮肤病灶分割算法CA-SFTNet。首先,在模型下采样过程中进行特征切分,保留皮肤病灶浅层语义信息。其次,在跳跃连接处引入浓缩注意力机制(Condensed Attention Neural Block),使得模型能够聚焦于病灶区域,提高分割精度。最后,在模型尾部加入残差空间特征变换层(Residual Spatial Feature Transformation Layer),增强对皮肤病变图像不同区域的自适应调整能力,提高模型对特征分布差异较大病灶的识别能力。实验在ISIC2017和ISIC2018数据集上进行,结果表明,CA-SFTNet在分割性能上优于传统U-Net,Dice系数分别达到93.12%和92.36%,比U-Net提升7.15个百分点和4.81个百分点;IoU值分别为82.59%和82.31%,比U-Net提升6.23个百分点和4.45个百分点。相比TransUNet和Swin-UNet等拓展算法,Dice系数提升2~6个百分点,IoU值提升1.8~4个百分点。这些结果证明了改进算法在皮肤病变区域分割上的优越性,其能够有效提高分割精度。
中图分类号:
| [1]SUNG H,FERLAY J,SIEGEL R L,et al.Global cancer statistics 2020:GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J].CA:A Cancer Journal for Clinicians,2021,71(3):209-249. [2]FONTANILLAS P,ALIPANAHI B,FURLOTTE N A,et al.Disease risk scores for skin cancers[J].Nature Communications,2021,12(1):160. [3]YEN J C,CHANG F J,CHANG S.A new criterion for auto-matic multilevel thresholding[J].IEEE Transactions on Image Processing,1995,4(3):370-378. [4]TREMEAUA,BOREL N.A region growing and merging algorithm to color segmentation[J].Pattern Recognition,1997,30(7):1191-1203. [5]ADAMS R,BISCHOF L.Seeded region growing[J].IEEETransactions on Pattern Analysis and Machine Intelligence,1994,16(6):641-647. [6]HEARST M A,DUMAIS S T,OSUNA E,et al.Support vector machines[J].IEEE Intelligent Systems and Their Applications,1998,13(4):18-28. [7]FUKUSHIMA K.Neocognitron:A self-organizing neural net-work model for a mechanism of pattern recognition unaffected by shift in position[J].Biological Cybernetics,1980,36(4):193-202. [8]SIDDIQUE N,PAHEDING S,ELKIN C P,et al.U-net and its variants for medical image segmentation:A review of theory and applications[J].IEEE Access,2021,9:82031-82057. [9]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolu-tional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-assisted Intervention-MICCAI 2015:18th International Conference.Springer,2015:234-241. [10]ZHAO H,GOU Y,LI B,et al.Comprehensive and delicate:An efficient transformer for image restoration[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2023:14122-14132. [11]AZAD R,AGHDAM E K,RAULAND A,et al.Medical image segmentation review:The success of u-net[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2024,46(12):10076-10095. [12]LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:3431-3440. [13]JAFARI M H,NASR-ESFAHANI E,KARIMI N,et al.Extraction of skin lesions from non-dermoscopic images for surgical excision of melanoma[J].International Journal of Computer Assisted Radiology and Surgery,2017,12:1021-1030. [14]YUAN Y,CHAO M,LO Y C.Automatic skin lesion segmentation using deep fully convolutional networks withjaccard distance[J].IEEE Transactions on Medical Imaging,2017,36(9):1876-1886. [15]ZHOU Z,RAHMAN SIDDIQUEE M M,TAJBAKHSH N,et al.Unet++:A nested u-net architecture for medical image segmentation[C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support:4th International Workshop.Springer,2018:3-11. [16]OKTAY O,SCHLEMPER J,FOLGOC L L,et al.Attentionu-net:Learning where to look for the pancreas[J].arXiv:1804.03999,2018. [17]JHA D,RIEGLER M A,JOHANSEN D,et al.Doubleu-net:A deep convolutional neural network for medical image segmentation[C]//2020 IEEE 33rd International Symposium on Computer-based Medical Systems(CBMS).IEEE,2020:558-564. [18]YU C,GAO C,WANG J,et al.Bisenet v2:Bilateral networkwith guided aggregation for real-time semantic segmentation[J].International Journal of Computer Vision,2021,129:3051-3068. [19]CHEN J,LU Y,YU Q,et al.Transunet:Transformers make strong encoders for medical image segmentation[J].arXiv:2102.04306,2021. [20]LIANG L M,ZHOU L S,YIN J,et al.Fusion multi-scale Transformer skin lesion segmentation algorithm[J].Journal of Jilin University(Engineering and Technology Edition),2024,54(4):1086-1098. [21]CAO H,WANG Y,CHEN J,et al.Swin-unet:Unet-like puretransformer for medical image segmentation[C]//European Conference on Computer Vision.Cham:Springer,2022:205-218. [22]XU Q,MA Z,NA H E,et al.DCSAU-Net:A deeper and more compact split-attention U-Net for medical image segmentation[J].Computers in Biology and Medicine,2023,154:106626. [23]ULYANOV D.Instance normalization:The missing ingredientfor fast stylization[J].arXiv:1607.08022,2016. [24]IOFFE S.Batch normalization:Accelerating deep network training by reducing internal covariate shift[J].arXiv:1502.03167,2015. [25]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778. [26]SHI W,CABALLERO J,HUSZÁR F,et al.Real-time singleimage and video super-resolution using an efficient sub-pixel convolutional neural network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:1874-1883. |
|
||
首页