基于知识引导的缺血性脑卒中梗死区分割方法

doi:10.3785/j.issn.1008-973X.2025.04.017

浙江大学学报(工学版)

2025, Vol. 59

Issue (4): 814-820 DOI: 10.3785/j.issn.1008-973X.2025.04.017

计算机技术与控制工程

基于知识引导的缺血性脑卒中梗死区分割方法

顾正宇1(

),赖菲菲2,耿辰3,王希明4,戴亚康1,3,*(

)

1. 徐州医科大学医学影像学院，江苏徐州 221004
2. 无锡市精神卫生中心放射科，江苏无锡，214151
3. 中国科学院苏州生物医学工程技术研究所，江苏苏州 215163
4. 苏州大学附属第一医院放射科，江苏苏州 215006

Knowledge-guided infarct segmentation of ischemic stroke

Zhengyu GU1(

),Feifei LAI2,Chen GENG3,Ximing WANG4,Yakang DAI1,3,*(

)

1. School of Medical Imaging, Xuzhou Medical University, Xuzhou 221004, China
2. Department of Radiology, Wuxi Mental Health Center, Wuxi 214151, China
3. Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou 215163, China
4. Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou 215006, China

全文: PDF(1203 KB) HTML

摘要：

针对缺血性脑卒中梗死区在医学影像上显示出低密度特征，提出基于阈值分割和加权滤波的梗死概率图生成方法. 通过自适应参数的阈值分割找出低密度区，由多尺度自定义权重的滤波器计算二值图，获得梗死概率图. 当概率图引导网络参数学习时，通过降低低概率区域的权重来提高所提方法的分割准确度. 使用梗死概率图引导U-Net、DRINet和DeepLabV3+，相比未使用梗死概率图引导的模型，Dice系数分别提升了0.0466，0.0418和0.0363，交并比（IoU）分别提升了0.0322、0.0440和0.0356. 统计结果表明，梗死概率图引导的网络对急性期数据的Dice系数有提升作用，对亚急性数据分割结果影响不大. 所提方法为自动分割急性缺血性脑卒中梗死区提供了可行方案.

关键词： 深度学习; 知识引导; 缺血性卒中; 脑卒中梗死区; 语义分割

Abstract:

Ischemic stroke infarcts show low-density features on imaging. Based on threshold segmentation and weighted filtering for the features, an infarct probability map generation method was proposed. The low-density region was identified by threshold segmentation with adaptive parameters, and the infarct probability map was obtained by calculating the binary map through the filter with customized weights at multiscale. The weights of the low-probability regions were reduced when the probability map guided the net parameters learning, thus improving the segmentation accuracy of the proposed method. The probability map was used to guide U-Net, DRINet and DeepLabV3+, the Dice coefficient was increased by 0.0466, 0.0418 and 0.0363, and the intersection over union (IoU) was increased by 0.0322, 0.0440 and 0.0356, respectively, compared to the models not guided with infarct probability maps. Statistical results show that the infarct probability map-guided network has an enhancement effect on the Dice coefficient for acute-phase data and has little effect on the segmentation results for sub-acute data. The proposed method provides a feasible solution for automatic segmentation of the acute ischemic stroke infarct.

Key words: deep learning knowledge-guided ischemic stroke cerebral infarcts semantic segmentation

收稿日期: 2023-12-03 出版日期: 2025-04-25

CLC:

TP 391.7

基金资助: 国家自然科学基金资助项目（81971685，62441114）；江苏省前沿引领技术基础研究项目（BK20192004）；山东省自然科学基金资助项目（ZR2022QF093）；苏州科技计划项目（SKY2022151）；浙江省医药卫生科技计划项目（2022KY1426）.

通讯作者: 戴亚康 E-mail: 2297764691@qq.com;daiyk@sibet.ac.cn

作者简介: 顾正宇（1999—），男，硕士生，从事医学图像分割研究. orcid.org/0000-0002-5585-7680. E-mail：2297764691@qq.com

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	作者相关文章
	顾正宇
	赖菲菲
	耿辰
	王希明
	戴亚康

引用本文:

顾正宇,赖菲菲,耿辰,王希明,戴亚康. 基于知识引导的缺血性脑卒中梗死区分割方法[J]. 浙江大学学报(工学版), 2025, 59(4): 814-820.

Zhengyu GU,Feifei LAI,Chen GENG,Ximing WANG,Yakang DAI. Knowledge-guided infarct segmentation of ischemic stroke. Journal of ZheJiang University (Engineering Science), 2025, 59(4): 814-820.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2025.04.017 或 https://www.zjujournals.com/eng/CN/Y2025/V59/I4/814

图 1 梗死概率图生成方法的框架图

图 2 梗死概率图的生成结果

表 1 实验数据集的数据分布

表 2 概率图有效性实验结果

图 3 梗死概率图（左）与标签（右）

图 4 概率图优化基线网络的可视化分析

表 3 超参数选择实验结果

表 4 不同基线网络的缺血性脑卒中梗死数据统计结果

图 5 概率图优化基线网络的局限性

21	YUSHKEVICH P A, GAO Y, GERIG G. ITK-SNAP: an interactive tool for semi-automatic segmentation of multi-modality biomedical images [C]// Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society . Orlando: IEEE, 2016: 3342–3345.
22	NAJM M, KUANG H, FEDERICO A, et al Automated brain extraction from head CT and CTA images using convex optimization with shape propagation[J]. Computer Methods and Programs in Biomedicine, 2019, 176: 1- 8 doi: 10.1016/j.cmpb.2019.04.030
23	QIU W, YUAN J, UKWATTA E, et al Prostate segmentation: an efficient convex optimization approach with axial symmetry using 3-D TRUS and MR images[J]. IEEE Transactions on Medical Imaging, 2014, 33 (4): 947- 960 doi: 10.1109/TMI.2014.2300694
24	ÇIÇEK Ö, ABDULKADIR A, LIENKAMP S S, et al. 3D U-Net: learning dense volumetric segmentation from sparse annotation [C]// Medical Image Computing and Computer-Assisted Intervention . [S. l.]: Springer, 2016: 424–432.
1	《中国脑卒中防治报告2020》编写组《中国脑卒中防治报告2020》概要[J]. 中国脑血管病杂志, 2022, 19 (2): 136- 144 Report on Stroke Prevention and Treatment in China Writing Group Brief report on stroke prevention and treatment in China, 2020[J]. Chinese Journal of Cerebrovascular Diseases, 2022, 19 (2): 136- 144
2	朱红霞, 张国柱半夏白术天麻汤治疗脑卒中后眩晕疗效观察[J]. 安徽中医药大学学报, 2018, 37 (5): 22- 24 ZHU Hongxia, ZHANG Guozhu Clinical effect of Banxia Baizhu Tianma decoction in treatment of post-stroke vertigo[J]. Journal of Anhui University of Chinese Medicine, 2018, 37 (5): 22- 24 doi: 10.3969/j.issn.2095-7246.2018.05.007
3	GOYAL M, DEMCHUK A M, MENON B K, et al Randomized assessment of rapid endovascular treatment of ischemic stroke[J]. New England Journal of Medicine, 2015, 372 (11): 1019- 1030 doi: 10.1056/NEJMoa1414905
4	DANKBAAR J W, HORSCH A D, VAN DEN HOVEN A F, et al Prediction of clinical outcome after acute ischemic stroke: the value of repeated noncontrast computed tomography, computed tomographic angiography, and computed tomographic perfusion[J]. Stroke, 2017, 48 (9): 2593- 2596 doi: 10.1161/STROKEAHA.117.017835
5	王姗, 赵建华基于CT和MRI的影像组学在缺血性脑卒中的研究进展[J]. CT理论与应用研究(中英文), 2024, 33 (1): 83- 89 WANG Shan, ZHAO Jianhua Research progress in imaging radiomics based on computed tomography and magnetic resonance in ischemic stroke[J]. Computerized Tomography Theory and Applications, 2024, 33 (1): 83- 89
6	POWERS W J, RABINSTEIN A A, ACKERSON T, et al Guidelines for the early management of patients with acute ischemic stroke: 2019 update to the 2018 guidelines for the early management of acute ischemic stroke[J]. Stroke, 2019, 50 (12): e344- e418
7	REKIK I, ALLASSONNIÈRE S, CARPENTER T K, et al Medical image analysis methods in MR/CT-imaged acute-subacute ischemic stroke lesion: segmentation, prediction and insights into dynamic evolution simulation models. A critical appraisal[J]. NeuroImage Clinical, 2012, 1 (1): 164- 178 doi: 10.1016/j.nicl.2012.10.003
8	KUANG H, MENON B K, QIU W Semi-automated infarct segmentation from follow-up noncontrast CT scans in patients with acute ischemic stroke[J]. Medical Physics, 2019, 46 (9): 4037- 4045 doi: 10.1002/mp.13703
9	KUANG H, NAJM M, MENON B K, et al. Joint segmentation of intracerebral hemorrhage and infarct from non-contrast CT images of post-treatment acute ischemic stroke patients [C]// Medical Image Computing and Computer Assisted Intervention . [S.l.]: Springer, 2018: 681–688.
10	KUANG H, MENON B K, QIU W. Automated infarct segmentation from follow-up non-contrast CT scans in patients with acute ischemic stroke using dense multi-path contextual generative adversarial network [C]// Medical Image Computing and Computer Assisted Intervention . [S.l.]: Springer, 2019: 856–863.
11	VAN VOORST H, KONDURI P R, VAN POPPEL L M, et al Unsupervised deep learning for stroke lesion segmentation on follow-up CT based on generative adversarial networks[J]. AJNR American Journal of Neuroradiology, 2022, 43 (8): 1107- 1114 doi: 10.3174/ajnr.A7582
12	NIE X, LIU X, YANG H, et al Fully automatic identification of post-treatment infarct lesions after endovascular therapy based on non-contrast computed tomography[J]. Neural Computing and Applications, 2023, 35 (30): 22101- 22114 doi: 10.1007/s00521-022-08094-4
13	LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Honolulu: IEEE, 2017: 936–944.
14	DAI J, QI H, XIONG Y, et al. Deformable convolutional networks [C]// Proceedings of the IEEE International Conference on Computer Vision . Venice: IEEE, 2017: 764–773.
15	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems . [S.l.]: Curran Associates Inc., 2017: 6000–6010.
16	LI S, ZHENG J, LI D Precise segmentation of non-enhanced computed tomography in patients with ischemic stroke based on multi-scale U-Net deep network model[J]. Computer Methods and Programs in Biomedicine, 2021, 208: 106278 doi: 10.1016/j.cmpb.2021.106278
17	RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation [C]// Medical Image Computing and Computer-Assisted Intervention . [S. l.]: Springer, 2015: 234–241.
18	CHEN L C, ZHU Y, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation [C]// Computer Vision – ECCV 2018 . [S.l.]: Springer, 2018: 833–851.
19	CHEN L, BENTLEY P, MORI K, et al DRINet for medical image segmentation[J]. IEEE Transactions on Medical Imaging, 2018, 37 (11): 2453- 2462 doi: 10.1109/TMI.2018.2835303
20	SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Boston: IEEE, 2015: 1–9.

[1]	马莉,王永顺,胡瑶,范磊. 预训练长短时空交错Transformer在交通流预测中的应用[J]. 浙江大学学报(工学版), 2025, 59(4): 669-678.
[2]	李沈崇,曾新华,林传渠. 基于轴向注意力的多任务自动驾驶环境感知算法[J]. 浙江大学学报(工学版), 2025, 59(4): 769-777.
[3]	张振利,胡新凯,李凡,冯志成,陈智超. 基于CNN和Efficient Transformer的多尺度遥感图像语义分割算法[J]. 浙江大学学报(工学版), 2025, 59(4): 778-786.
[4]	陈巧红,郭孟浩,方贤,孙麒. 基于跨模态级联扩散模型的图像描述方法[J]. 浙江大学学报(工学版), 2025, 59(4): 787-794.
[5]	姚明辉,王悦燕,吴启亮,牛燕,王聪. 基于小样本人体运动行为识别的孪生网络算法[J]. 浙江大学学报(工学版), 2025, 59(3): 504-511.
[6]	梁礼明,龙鹏威,金家新,李仁杰,曾璐. 基于改进YOLOv8s的钢材表面缺陷检测算法[J]. 浙江大学学报(工学版), 2025, 59(3): 512-522.
[7]	杨凯博,钟铭恩,谭佳威,邓智颖,周梦丽,肖子佶. 基于半监督学习的多场景火灾小规模稀薄烟雾检测[J]. 浙江大学学报(工学版), 2025, 59(3): 546-556.
[8]	陈智超,杨杰,李凡,冯志成. 基于深度学习的列车运行环境感知关键算法研究综述[J]. 浙江大学学报(工学版), 2025, 59(1): 1-17.
[9]	刘登峰,陈世海,郭文静,柴志雷. 基于轻量残差网络的高效半色调算法[J]. 浙江大学学报(工学版), 2025, 59(1): 62-69.
[10]	赵顗,安醇,李铭浩,马健霄,怀硕. 城市快速路互通交织区车辆的换道持续距离选择[J]. 浙江大学学报(工学版), 2025, 59(1): 205-212.
[11]	李凡,杨杰,冯志成,陈智超,付云骁. 基于图像识别的弓网接触点检测方法[J]. 浙江大学学报(工学版), 2024, 58(9): 1801-1810.
[12]	肖力,曹志刚,卢浩冉,黄志坚,蔡袁强. 基于深度学习和梯度优化的弹性超材料设计[J]. 浙江大学学报(工学版), 2024, 58(9): 1892-1901.
[13]	吴书晗,王丹,陈远方,贾子钰,张越棋,许萌. 融合注意力的滤波器组双视图图卷积运动想象脑电分类[J]. 浙江大学学报(工学版), 2024, 58(7): 1326-1335.
[14]	李林睿,王东升,范红杰. 基于法条知识的事理型类案检索方法[J]. 浙江大学学报(工学版), 2024, 58(7): 1357-1365.
[15]	马现伟,范朝辉,聂为之,李东,朱逸群. 对失效传感器具备鲁棒性的故障诊断方法[J]. 浙江大学学报(工学版), 2024, 58(7): 1488-1497.

Viewed

Full text

Abstract

Cited

Shared

Discussed