| 195 | 0 | 29 |
| 下载次数 | 被引频次 | 阅读次数 |
基于深度网络模型对皮肤病医学图像的精确分割可以为临床诊断提供准确的定位和定量信息，但在训练网络时却需要影像专家对图像进行大量的、专业化的标注。本文结合流形理论与深度学习技术，提出一种弱监督的皮肤病图像分割网络，旨在解决皮肤病图像分割中标注数据稀缺、图像特征复杂多变等问题。该网络通过流形学习捕捉图像数据内在的低维流形结构，有效减少噪声和冗余信息的影响；基于提出的像素相关性模型，分析图像中基层特征之间的空间关系和上下文信息，提升像素级伪标签的准确性；基于注意力机制，提取图像中多种尺度的特征，以适应皮肤病斑块的多样性变化。采用了ISIC-2018皮肤病图像数据集对提出的网络模型进行验证，结果表明，所提出的弱监督皮肤病分割网络在分割精度、鲁棒性和泛化能力等方面均表现出优异的性能。
Abstract：The accurate segmentation of dermatological medical images based on deep network models can facilitate precise localization and quantitative information for clinical diagnosis.However, training the network necessitates the involvement of image experts who are responsible for labeling images with a substantial number of specialized annotations.This paper presents a novel approach that integrates manifold theory with deep learning technology to develop a weakly supervised dermatological image segmentation network.This methodology addresses the challenges posed by limited labeling data and the intricate and evolving characteristics of dermatological images.The network captures the intrinsic low-dimensional manifold structure of image data through manifold learning, thereby reducing the impact of noise and redundant information.The proposed pixel correlation model is based on the analysis of the spatial relationship and contextual information between the low-level features in the image, with the objective of improving the accuracy of pixel-level pseudo labels.The proposed network model was validated by using the ISIC-2018 skin disease image dataset.The results demonstrated that the network, which was based on the attention mechanism and capable of extracting features of multiple scales in the image, performed well in terms of segmentation accuracy, robustness, and generalization ability.
[1] LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[2] KATTENBORN T,LEITLOFF J,SCHIEFER F,et al.Review on convolutional neural networks (CNN) in vegetation remote sensing[J].ISPRS Journal of Photogrammetry and Remote Sensing,2021,173:24-49.
[3] 胡捷，赵海涛.基于掩码一致性机制的弱监督图像语义分割研究[J].应用光学，2024,45(4):741-750.
[4] 郑天佑.基于改进卷积神经网络可视化的弱监督图像分割方法研究[D].哈尔滨：哈尔滨工业大学，2022.
[5] IZENMANA J.Introduction to manifold learning[J].Wiley Interdisciplinary Reviews:Computational Statistics,2012,4(5):439-446.
[6] PAN X G,TEWARI A,LEIMKüHLER T,et al.Drag your GAN:interactive point-based manipulation on the generative image manifold[C]//ACM SIGGRAPH 2023 Conference Proceedings,2023:1-11.
[7] BADRINARAYANAN V,KENDALL A.SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[8] GUO Y M,LIU Y,GEORGIOU T,et al.A review of semantic segmentation using deep neural networks[J].International Journal of Multimedia Information Retrieval,2018,7:87-93.
[9] HAFIZA M,BHAT G M.A survey on instance segmentation:state of the art[J].International Journal of Multimedia Information Retrieval,2020,9(3):171-189.
[10] TAKMAZ A,FEDELE E,SUMNER R W,et al.OpenMask3D:open-vocabulary 3D instance segmentation[C]//Proceedings of the 37th International Conference on Neural Information Processing Systems,2023:68367-68390.
[11] KIRILLOVA,HE K,GIRSHICK R,et al.Panoptic segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:9404-9413.
[12] HU J,HUANG L Y,REN T H,et al.You only segment once:towards real-time panoptic segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,2023:17819-17829.
[13] WU Y,JIANG J Y,HUANG Z M,et al.FPANet:feature pyramid aggregation network for real-time semantic segmentation[J].Applied Intelligence,2022,52(3):3319-3336.
[14] 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,2016:770-778.
[15] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.Deeplab:semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected crfs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,40(4):834-848.
[16] RONNEBERGER O,FISCHER P,BROX T.U-Net:convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015,2015:234-241.
[17] MILLETARI F,NAVAB N,AHMADI S A.V-Net:fully convolutional neural networks for volumetric medical image segmentation[C]//2016 Fourth International Conference on 3D Vision (3DV),2016:565-571.
[18] LI X M,CHEN H,QI X J,et al.H-DenseUNet:hybrid densely connected UNet for liver and tumor segmentation from CT volumes[J].IEEE Transactions on Medical Imaging,2018,37(12):2663-2674.
[19] SZEGEDY C,VANHOUCKE V,IOFFE S,et al.Rethinking the inception architecture for computer vision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:2818-2826.
[20] PATHAK D,KRAHENBUHL P,DARRELL T.Constrained convolutional neural networks for weakly supervised segmentation[C]//Proceedings of the IEEE International Conference on Computer Vision,2015:1796-1804.
[21] PANG N,ZHAO X,WANG W,et al.Few-shot text classification by leveraging bi-directional attention and cross-class knowledge[J].Science China Information Sciences,2021,64:130103.
[22] DENG J,YU J G.A simple graph-based semi-supervised learning approach for imbalanced classification[J].Pattern Recognition,2021,118:108026.
[23] TENENBAUM J B,SILVA V,LANGFORD J C.A global geometric framework for nonlinear dimensionality reduction[J].Science,2000,290(5500):2319-2323.
[24] VAN DER MAATEN L,HINTON G.Visualizing data using t-SNE[J].Journal of Machine Learning Research,2008,9(11):2579-2605.
[25] ROWEISS T,SAUL L K.Nonlinear dimensionality reduction by locally linear embedding[J].Science,2000,290(5500):2323-2326.
[26] HEALY J,MCINNES L.Uniform manifold approximation and projection[J].Nature Reviews Methods Primers,2024,4(82):2662-8449.
[27] ZHAO X M,LI C,WU J,et al.Riemannian manifold-based feature space and corresponding image clustering algorithms[J].IEEE Transactions on Neural Networks and Learning Systems,2022,35(2):2680-2693.
[28] GUO M H,XU T X,LIU J J,et al.Attention mechanisms in computer vision:a survey[J].Computational Visual Media,2022,8(3):331-368.
[29] MNIH V,HEESS N,GRAVES A.Recurrent models of visual attention[J].Advances in Neural Information Processing Systems,2014,27:2204-2212.
[30] 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;2020:11534-11542.
[31] GUO M H,LU C Z,LIU Z N,et al.Visual attention network[J].Computational Visual Media,2023,9(4):733-752.
[32] SHI J G,LIU X,QI C.Global consistency,local sparsity and pixel correlation:a unified framework for face hallucination[J].Pattern Recognition,2014,47(11):3520-3534.
[33] GRAY M,NEUHOFF D L.Quantization[J].IEEE Transactions on Information Theory,1998,44(6):2325-2383.
[34] HARTIGAN J A,WONG M A.A k-means clustering algorithm[J].Applied Statistics,1979,28(1):100-108.
[35] CODELLA N,GUTMAN D,CELEBI M E,et al.Skin lesion analysis toward melanoma detection:a challenge at the 2017 ISBI[C]//2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018),2018:168-172.
[36] 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.
[37] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.Deeplab:semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected crfs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,40(4):834-848.
[38] AL-MASNIM A,AL-ANTARI M A,CHOI M T,et al.Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks[J].Computer Methods and Programs in Biomedicine,2018,162:221-231.
[39] ADIGA V S,DOLZ J,LOMBAERT H.Manifold-driven attention maps for weakly supervised segmentation[J].arXiv:2004.03046,2020.
[40] HONG Y F,ZHANG G S,WEI B Z,et al.Weakly supervised semantic segmentation for skin cancer via CNN superpixel region response[J].Multimedia Tools and Applications,2023,82(5):6829-6847.
[41] AL-HUDA Z,YAO Y,YAO J,et al.Weakly supervised skin lesion segmentation based on spot-seeds guided optimal regions[J].IET Image Processing,2023,17(1):239-255.
基本信息:
DOI：10.20062/j.cnki.CN37-1453/N.2025.03.004
中图分类号:R318;TP391.41
引用信息:
[1]蔡晟玮,孙玉娟,王桦,等.基于流形学习与弱监督的医学图像分割网络模型[J].鲁东大学学报(自然科学版),2025,41(03):233-242.DOI:10.20062/j.cnki.CN37-1453/N.2025.03.004.
基金信息:
国家自然科学基金(U24A20328,62171209,62272281,61873117); 山东省高校青创团队项目(2023KJ212)