计算机科学 ›› 2025, Vol. 52 ›› Issue (6): 274-285.doi: 10.11896/jsjkx.240600006
耿胜, 丁卫平, 鞠恒荣, 黄嘉爽, 姜舒, 王海鹏
GENG Sheng, DING Weiping, JU Hengrong, HUANG Jiashuang, JIANG Shu, WANG Haipeng
摘要： 医学图像分割在临床诊疗和病理分析中具有重要的应用价值。近年来,去噪扩散模型在图像分割建模方面取得了显著成功,其能够更好地捕获图像中的复杂结构和细节信息。然而,利用去噪扩散模型进行医学图像分割的方法大多忽略了分割目标的边界不确定和区域模糊因素,从而造成了最终分割结果的不稳定性和不准确性。为了解决这一问题,提出了一种基于模糊逻辑驱动的医学图像扩散融合网络分割模型(FDiff-Fusion)。该模型通过将去噪扩散模型集成到经典U-Net网络中,有效地从输入医学图像中提取丰富的语义信息。由于医学图像的分割目标边界不确定性和区域模糊化现象普遍存在,因此在U-Net网络的跳跃路径上设计了一种模糊学习模块。该模块为输入的编码特征设置多个模糊隶属度函数,以描述特征点之间的相似程度,并对模糊隶属度函数应用模糊规则处理,从而增强了模型对不确定边界和模糊区域的建模能力。此外,为了提高模型分割结果的准确性和鲁棒性,在测试阶段引入了基于迭代注意力特征融合的方法。该方法将局部上下文信息添加到注意力模块中的全局上下文信息中,以融合每个去噪时间步的预测结果。实验结果显示,与现有的先进分割网络相比,FDiff-Fusion在BRATS 2020脑肿瘤数据集上获得的平均Dice分数和HD95距离分别为84.16%和2.473mm,在BTCV腹部多器官数据集上获得的平均Dice分数和HD95距离分别为83.82%和7.98mm,表现出良好的分割性能。
中图分类号:
| [1]ULLAH Z,USMAN M,JEON M,et al.Cascade multiscale residual attention cnns with adaptive roi for automatic brain tumor segmentation[J].Information Sciences,2022,608:1541-1556. [2]TANG Y,YANG D,LI W,et al.Self-supervised pre-training of swin transformers for 3d medical image analysis[C]//Procee-dings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:20730-20740. [3]HE Y,GE R,QI X,et al.Learning better registration to learn better few-shot medical image segmentation:Authenticity,diversity,and robustness[J].IEEE Transactions on Neural Networks and Learning Systems,2022,35(2):2588-2601. [4]CHEN L,BENTLEY P,MORI K,et al.DRINet for medicalimage segmentation[J].IEEE Transactions on Medical Imaging,2018,37(11):2453-2462. [5]LIU F,ZHANG Z,ZHOU R.Automatic modulation recognition based on CNN and GRU[J].Tsinghua Science and Technology,2021,27(2):422-431. [6]SUN P,ZHANG R,JIANG Y,et al.Sparse R-CNN:An end-to-end framework for object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2023,45(12):15650-15664. [7]ZHANG Z M,GUO Y,MA C X,et al.GT-4S:Graph Trans-former for Scene Sketch Semantic Segmentation[J] Journal of Software,2025,36(3):1375-1389. [8]ZHANG C,JIANG W,ZHANG Y,et al.Transformer and CNN hybrid deep neural network for semantic segmentation of very-high-resolution remote sensing imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-20. [9]XIE Y,ZHANG J,SHEN C,et al.Cotr:Efficiently bridging cnn and transformer for 3d medical image segmentation[C]//Medical Image Computing and Computer Assisted Intervention－MICCAI 2021:24th International Conference,Strasbourg,France,September 27-October 1,2021,Proceedings,Part III 24.Springer International Publishing,2021:171-180. [10]OLAF R,FISCHER P,BROX T.U-net:Convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention－MICCAI 2015:18th International Conference,Munich,Germany,October 5-9,2015,proceedings,part III 18.Springer International Publishing,2015:234-241. [11]ANDRIY M.3D MRI brain tumor segmentation using autoencoder regularization[C]//Brainlesion:Glioma,Multiple Sclerosis,Stroke and Traumatic Brain Injuries:4th International Workshop,BrainLes 2018,Held in Conjunction with MICCAI 2018,Granada,Spain,September 16,2018,Revised Selected Papers,Part II 4.Springer International Publishing,2019:311-320. [12]KINGMA D,WELLING M.Auto-encoding variational bayes[J].arXiv:1312.6114,2013. [13]WANG W,CHEN C,DING M,et al.Transbts:Multimodalbrain tumor segmentation using transformer[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Springer,2021:109-119. [14]HATAMIZADEH A,TANG Y,NATH V,et al.Unetr:Transformers for 3d medical image segmentation[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.2022:574-584. [15]DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.Animage is worth 16×16 words:Transformers for image recognition at scale[J].arXiv:2010.11929,2020. [16]HATAMIZADEH A,NATH V,TANG Y,et al.Swin unetr:Swin transformers for semantic segmentation of brain tumors in mri images[C]//International MICCAI Brainlesion Workshop.Cham:Springer International Publishing,2021:272-284. [17]LIU Z,LIN Y,CAO Y,et al.Swin transformer:Hierarchical vision transformer using shifted windows[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:10012-10022. [18]CHEN J,LU Y,YU Q,et al.Transunet:Transformers make strong encoders for medical image segmentation[J].arXiv:2102.04306,2021. [19]HUANG D M,DAI L,WEI L F et al.A secure outsourcing fusion denoising scheme for multi-frame remote sensing images[J].Journal of Computer Research and Development,2017,54(10):2378-2389. [20]GOYAL B,DOGRA A,AGRAWAL S,et al.Image denoising review:From classical to state-of-the-art approaches[J].Information Fusion,2020,55:220-244. [21]CROITORU F,HONDRU V,IONESUC R,et al.Diffusionmodels in vision:A survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2023,45(9):10850-10869. [22]YANG L,ZHANG Z,SONG Y,et al.Diffusion models:A comprehensive survey of methods and applications[J].ACM Computing Surveys,2023,56(4):1-39. [23]WU J,FU R,FANG H,et al.Medsegdiff:Medical image seg-mentation with diffusion probabilistic model[C]//Medical Imaging with Deep Learning.PMLR,2024:1623-1639. [24]WU J,JI W,FU H,et al.Medsegdiff-v2:Diffusion based medical image segmentation with transformer[J].arXiv:2301.11798,2023. [25]XING Z,WAN L,FU H,et al.Diff-unet:A diffusion embedded network for volumetric segmentation[J].arXiv:2303.10326,2023. [26]WOLLEB J,ROBIN S,BIEDER F,et al.Diffusion models forimplicit image segmentation ensembles[C]//International Conference on Medical Imaging with Deep Learning.PMLR,2022:1336-1348. [27]ZHOU T Y,DING W P,HUANG J S,et al.Fuzzy Logic Guided Deep Neural Network with Multi-granularity [J].Pattern Re-cognition and Artificial Intelligence,2023,36(9):778-792. [28]KUMAR D,AGRAWAL R K,KUMAR P.Bias-corrected intuitionistic fuzzy c-means with spatial neighborhood information approach for human brain MRI image segmentation[J].IEEE Transactions on Fuzzy Systems,2020,30(3):687-700. [29]李季,胡锦萍,乔敏,王艳.一种针对脑部图像分割强度不均匀性的改进方法[J].重庆工商大学学报(自然科学版),2023,40(1):34-39. [30]YANG L,WANG S,LIEW A.Fine-Grained Lip Image Segmentation using Fuzzy Logic and Graph Reasoning[J].IEEE Tran-sactions on Fuzzy Systems, 2024,32(2):349-359. [31]ZHOU M,SHANG C,LI G,et al.Transformation-based fuzzy rule interpolation with Mahalanobis distance measures supported by Choquet integral[J].IEEE Transactions on Fuzzy Systems,2022,31(4):1083-1097. [32]SONG S,JIA Z,YANG J,et al.Image segmentation based onfuzzy low-rank structural clustering[J].IEEE Transactions on Fuzzy Systems,2023,31(7):2153-2166. [33]LIU Z,TAN Y,HE Q,et al.SwinNet:Swin transformer drives edge-aware RGB-D and RGB-T salient object detection[J].IEEE Transactions on Circuits and Systems for Video Technology,2021,32(7):4486-4497. [34]PHAM T.The Kolmogorov-Sinai entropy in the setting of fuzzy sets for image texture analysis and classification[J].Pattern Recognition,2016,53:229-237. [35]LI D,ZHANG H,LI T,et al.Hybrid missing value imputation algorithms using fuzzy c-means and vaguely quantified rough set[J].IEEE Transactions on Fuzzy Systems,2021,30(5):1396-1408. [36]HO J,JAIN A,ABBEEL P.Denoising diffusion probabilisticmodels[J].Advances in Neural Information Processing Systems,2020,33:6840-6851. [37]NICHOL A,DHARIWAL P.Improved denoising diffusionprobabilistic models[C]//International Conference on Machine Learning.PMLR,2021:8162-8171. [38]GAO Q,LI Z,ZHANG J,et al.CoreDiff:Contextual error-mo-dulated generalized diffusion model for low-dose CT denoising and generalization[J].arXiv:2304.01814,2023. [39]YUE J,FANG L,XIA S,et al.Dif-fusion:Towards high color fidelity in infrared and visible image fusion with diffusion models[J].IEEE Transactions on Image Processing,2023,32:5705-5720. [40]SONG J,MENG C,ERMON S.Denoising diffusion implicitmodels[J].arXiv:2010.02502,2020. [41]WANG Y,LIU H,FENG Y,et al.HeadDiff:Exploring Rotation Uncertainty with Diffusion Models for Head Pose Estimation[J].IEEE Transactions on Image Processing,2024,33:1868-1882. [42]GONG K,JOHNSON K,EL FAKHRI G,et al.PET image denoising based on denoising diffusion probabilistic model[J].European Journal of Nuclear Medicine and Molecular Imaging,2024,51(2):358-368. [43]DING Y,YU X,YANG Y,et al.RFNet:Region-aware fusion network for incomplete multi-modal brain tumor segmentation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:3975-3984. [44]ULLAH Z,USMAN M JEON M,et al.Cascade multiscale residual attention cnns with adaptive roi for automatic brain tumor segmentation[J].Information sciences,2022,608:1541-1556. [45]FANG X,YAN P.Multi-organ segmentation over partially labeled datasets with multi-scale feature abstraction[J].IEEE Transactions on Medical Imaging,2020,39(11):3619-3629. |
|
||
首页