| 64 | 0 | 34 |
| 下载次数 | 被引频次 | 阅读次数 |
生物医学图像配准与分割在生命科学研究、医学诊断与临床治疗等领域具有重要意义，然而其深度学习方法通常依赖于大规模高质量标注数据，获取成本高昂。现有数据增广技术多基于旋转、平移等线性变换方法生成额外数据，仍难以有效解决生物医学图像对数据亮度多样性与柔性结构形变多样性的需求问题。对此，提出了一种基于配准和分割联合模型的双采样数据增广策略。通过结合亮度场和形变场上的双重采样提升了生成数据的亮度多样性和柔性结构形变多样性。此外，为抑制伪标注数据中错误信息对联合模型产生的误导，采用对抗式训练方式设计了伪标注鉴别器模块来寻找错误的分割预测，抑制了错误信息在数据循环过程中的传播。最后，设计了一种单样本场景下的配准-分割协同框架，在Mindboggle-101人脑MRI数据集、MouseBrain鼠脑fMOST数据集和MM-WHS 2017心脏数据集上，仅使用一幅带标签的训练图像实现了优于对比算法的分割和配准性能，验证了所提数据增广策略的有效性。
Abstract：Biomedical image registration and segmentation are essential in life science research, medical diagnosis, and clinical treatment. However, deep learning methods typically rely on large-scale, high-quality annotated data, which are costly to obtain. The existing data augmentation techniques mainly generate additional samples through linear deformation such as rotation and translation methods, yet they still struggle to effectively solve the demand for data brightness diversity and elastic structure deformation diversity of biomedical images.In this paper, we propose a double-sampling data augmentation strategy based on the joint model of registration and segmentation. Integrating the double sampling on the brightness and deformation fields enriches the brightness diversity and the data's elastic structural deformation diversity.Further, to suppress the misleading of incorrect information in the pseudo-labeled data on the joint model, an adversarial training method is used to train a pseudo-label discriminator module to find inaccurate segmentation predictions and suppress the propagation of incorrect information in the data cycle. Eventually, this paper proposes a joint model for registration and segmentation for a one-shot scenario. It achieves better segmentation and registration performance than the comparison algorithms on the Mindboggle-101 human brain MRI dataset, MouseBrain mouse brain fMOST dataset, and MM-WHS 2017 heart dataset, demonstrating the effectiveness of our data augmentation strategy.
[1] 马露凡，罗凤，严江鹏，等.深度医学图像配准研究进展：迈向无监督学习[J].中国图象图形学报，2021,26(9):2037-2057.MA L F,LUO F,YAN J P,et al.Deep-learning based medical image registration pathway:Towards unsupervised learning[J].Journal of Image and Graphics,2021,26(9):2037-2057.
[2] QU L,LI Y Y,XIE P,et al.Cross-modal coherent registration of whole mouse brains[J].Nature Methods,2022,19(1):111-118.
[3] PENG H C,XIE P,LIU L J,et al.Morphological diversity of single neurons in molecularly defined cell types[J].Nature,2021,598(7879):174-181.
[4] FU Y B,LEI Y,WANG T H,et al.Deep learning in medical image registration:A review[J].Physics in Medicine & Biology,2020,65(20):20TR01.
[5] TAJBAKHSH N,JEYASEELAN L,LI Q,et al.Embracing imperfect datasets:A review of deep learning solutions for medical image segmentation[J].Medical Image Analysis,2020,63:101693.
[6] BALAKRISHNAN G,ZHAO A,SABUNCU M R,et al.An unsupervised learning model for deformable medical image registration[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT:IEEE,2018:9252-9260.
[7] YU L Q,WANG S J,LI X M,et al.Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation[C]//International Conference on Medical Image Computing and Computer Assisted Intervention—MICCAI 2019.Shenzhen,China:Springer,2019:605-613.
[8] LI X M,YU L Q,CHEN H,et al.Transformation-consistent self-ensembling model for semisupervised medical image segmentation[J].IEEE Transactions on Neural Networks and Learning Systems,2020,32(2):523-534.
[9] BORTSOVA G,DUBOST F,HOGEWEG L,et al.Semi-supervised medical image segmentation via learning consistency under transformations[C]//International Conference on Medical Image Computing and Computer Assisted Intervention—MICCAI 2019.Shenzhen,China:Springer,2019:810-818.
[10] CUI W H,LIU Y L,LI Y X,et al.Semi-supervised brain lesion segmentation with an adapted mean teacher model[C]//International Conference on Information Processing in Medical Imaging.Hong Kong,China:Springer,2019:554-565.
[11] HERING A,KUCKERTZ S,HELDMANN S,et al.Enhancing label-driven deep deformable image registration with local distance metrics for state-of-the-art cardiac motion tracking[C]//Bildverarbeitung für die Medizin 2019:Algorithmen-Systeme-Anwendungen.Wiesbaden:Springer,2019:309-314.
[12] HU Y P,GIBSON E,GHAVAMIN,et al.Adversarial deformation regularization for training image registration neural networks[C]//International Conference on Medical Image Computing and Computer Assisted Intervention—MICCAI 2018.Granada,Spain:Springer,2018:774-782.
[13] NIE D,GAO Y Z,WANG L,et al.ASDNet:Attention based semi-supervised deep networks for medical image segmentation[C]//International Conference on Medical Image Computing and Computer Assisted Intervention—MICCAI 2018.Granada,Spain:Springer,2018:370-378.
[14] ZHAO A,BALAKRISHNAN G,DURAND F,et al.Data augmentation using learned transformations for one-shot medical image segmentation[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.Long Beach,CA,USA:IEEE,2019:8543-8553.
[15] DING Y H,YU X,YANG Y.Modeling the probabilistic distribution of unlabeled data for one-shot medical image segmentation[J].Proceedings of the AAAI Conference on Artificial Intelligence,2021,35(2):1246-1254.
[16] ZHAO Y X,ZHANG Y M,SONG M,et al.Multi-view semi-supervised 3D whole brain segmentation with a self-ensemble network[C]//International Conference on Medical Image Computing and Computer Assisted Intervention—MICCAI 2019.Shenzhen,China:Springer,2019:256-265.
[17] CHAITANYA K,KARANI N,BAUMGARTINER C F,et al.Semi-supervised and task-driven data augmentation[C]//International Conference on Information Processing in Medical Imaging.Hong Kong,China:Springer,2019:29-41.
[18] BAI W J,OKTAY O,SINCLAIR M,et al.Semi-supervised learning for network-based cardiac MR image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention—MICCAI 2017.Quebec City,QC,Canada:Springer,2017:253-260.
[19] HE Y T,LI T T,YANG G Y,et al.Deep complementary joint model for complex scene registration and few-shot segmentation on medical images[C]//International Conference on Computer Vision—ECCV 2020.Glasgow,UK:Springer,2020:770-786.
[20] ESTIENNE T,LEROUSSEAU M,VAKALOPOULOU M,et al.Deep learning-based concurrent brain registration and tumor segmentation[J].Frontiers in Computational Neuroscience,2020,14:17.
[21] XU Z L,NIETHAMMER M.DeepAtlas:Joint semi-supervised learning of image registrationand segmentation[C]//International Conference on Medical Image Computing and Computer Assisted Intervention—MICCAI 2019.Shenzhen,China:Springer,2019:420-429.
[22] HE Y T,LI T T,GE R J,et al.Few-shot learning for deformable medical image registration with perception-correspondence decoupling and reverse teaching[J].IEEE Journal of Biomedical and Health Informatics,2022,26(3):1177-1187.
[23] LI B,NIESSEN W J,KLEIN S,et al.A hybrid deep learning framework for integrated segmentation and registration:Evaluation on longitudinal white matter tract changes[C]//International Conference on Medical Image Computing and Computer Assisted Intervention—MICCAI 2019.Shenzhen,China:Springer,2019:645-653.
[24] SHI H B,LU L Y,YIN M X,et al.Joint few-shot registration and segmentation self-training of 3D medical images[J].Biomedical Signal Processing and Control,2023,80:104294.
[25] LIU F Z,CAI J Z,HUO Y K,et al.JSSR:A joint synthesis,segmentation,and registration system for 3D multi-modal image alignment of large-scale pathological CT scans[C]//European Conference on Computer Vision.Cham:Springer,2020:257-274.
[26] ESTIENNE T,VAKALOPOULOU M,CHRISTODOULIDIS S,et al.U-ReSNet:Ultimate coupling of registration and segmentation with deep nets[C]//International Conference on Medical Image Computing and Computer Assisted Intervention—MICCAI 2019.Shenzhen,China:Springer,2019:310-319.
[27] QIU L,REN H L.U-RSNet:An unsupervised probabilistic model for joint registration and segmentation[J].Neurocomputing,2021,450:264-274.
[28] WANG R S,LEI T,CUI R X,et al.Medical image segmentation using deep learning:A survey[J].IET Image Processing,2022,16(5):1243-1267.
[29] YEZZI A,Z??LLEI L,KAPUR T.A variational framework for integrating segmentation and registration through active contours[J].Medical Image Analysis,2003,7(2):171-185.
[30] POHL K M,FISHER J,GRIMSON W E L,et al.A Bayesian model for joint segmentation and registration[J].NeuroImage,2006,31(1):228-239.
[31] CHEN X H,BRADY M,RUECKERT D.Simultaneous segmentation and registration for medical image[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention—MICCAI 2004.Berlin,Heidelberg:Springer,2004:663-670.
[32] DUAY V,BRESSON X,CASTRO J S,et al.An active contour-based atlas registration model applied to automatic subthalamic nucleus targeting on MRI:Method and validation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention—MICCAI 2008.New York,NY,USA:Springer,2008:980-988.
[33] GASS T,SZEKELY G,GOKSEL O.Simultaneous segmentation and multiresolution nonrigid atlas registration[J].IEEE Transactions on Image Processing,2014,23(7):2931-2943.
[34] DALCA A V,BALAKRISHNAN G,GUTTAG J,et al.Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces[J].Medical Image Analysis,2019,57:226-236.
[35] KLEIN A,TOURVILLE J.101 labeled brain images and a consistent human cortical labeling protocol[J].Frontiers in Neuroscience,2012,6:171.
[36] ZHUANG X H,SHEN J.Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI[J].Medical Image Analysis,2016,31:77-87.
[37] ??I??EK ??,ABDULKADIR A,LIENKAMP S S,et al.3D U-Net:Learning dense volumetric segmentation from sparse annotation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention—MICCAI 2016.Athens,Greece:Springer,2016:424-432.
基本信息:
DOI：10.16152/j.cnki.xdxbzr.2026-01-009
中图分类号:TP391.41;TP18;R318
引用信息:
[1]吴军,章勇,冯浩然,等.基于双采样数据增广策略的生物医学图像配准-分割联合优化深度网络[J].西北大学学报(自然科学版),2026,56(01):96-107.DOI:10.16152/j.cnki.xdxbzr.2026-01-009.
基金信息:
科技创新2030重大项目(2022ZD0205204); 国家自然科学基金(62201008); 安徽省高校协同创新项目(GXXT-2021-001)
2026-02-23
2026-02-23