基于U-Net的颅内出血识别算法

doi:10.13190/j.jbupt.2019-146

北京邮电大学学报 ›› 2020, Vol. 43 ›› Issue (3): 92-98.doi: 10.13190/j.jbupt.2019-146

基于U-Net的颅内出血识别算法

张天麒¹, 康波^2,1, 孟祥飞¹, 刘奕琳³, 周颖³

1. 国家超级计算天津中心, 天津 300457;
2. 天津大学智能与计算学部, 天津 300350;
3. 北京大学滨海医院, 天津 300450

收稿日期:2019-07-09 出版日期:2020-06-28 发布日期:2020-06-24
通讯作者: 康波(1986-),男,高级工程师,E-mail:kangbo@nscc-tj.cn. E-mail:kangbo@nscc-tj.cn
作者简介:张天麒(1990-),男,研发工程师.
基金资助:

U-Net Based Intracranial Hemorrhage Recognition

ZHANG Tian-qi¹, KANG Bo^2,1, MENG Xiang-fei¹, LIU Yi-lin³, ZHOU Ying³

1. National Supercomputer Center in Tianjin, Tianjin 300457, China;
2. College of Intelligence and Computing, Tianjin University, Tianjin 300350, China;
3. Peking University Binhai Hospital, Tianjin 300450, China

Received:2019-07-09 Online:2020-06-28 Published:2020-06-24
Supported by:

摘要/Abstract

摘要： 针对颅脑计算机断层成像（CT）影像中脑出血的分析和识别，提出采用神经网络模型U-Net与轮廓识别相结合的方法提取脑实质区域，通过阈值分割算法分析血块的图像纹理特征，并过滤软组织、脑组织和脑脊液等无关生理组织结构，实现对颅内出血点的精确定位，最后采用插值方法将出血区域进行三维重建，对血块的三维形态作出评估.在天津市某医疗机构提供的500例颅脑CT数据上进行了验证测试，实验结果表明，该算法达到97.4%的目标识别准确率，能够为脑出血诊断提供参考.

关键词: 深度学习, 图像分割, 脑出血, 颅脑计算机断层成像

Abstract: Aiming at analysis and recognition of cerebral hemorrhage from craniocerebral computed tomography (CT) images, a method combining neural network model U-Net with contour recognition is proposed to extract brain parenchymal regions. The image texture features of hemorrhagic area are firstly extracted by adaptive threshold segmentation algorithm, the precise location of hemorrhagic area is thereafter obtained through filtering the irrelevant physiological tissues such as soft tissue, brain tissue and cerebrospinal fluid. Finally, a three-dimensional structure of the hemorrhagic area is reconstructed based on interpolation to evaluate the amount of hemorrhage. A validation test with 500 patients from medical institution in Tianjin shows that the algorithm achieves a target recognition accuracy of 97.4% and could provide reference for the diagnosis of cerebral hemorrhage.

Key words: deep learning, image segmentation, cerebral hemorrhage, craniocerebral computed tomography

中图分类号:

TN319

张天麒, 康波, 孟祥飞, 刘奕琳, 周颖. 基于U-Net的颅内出血识别算法[J]. 北京邮电大学学报, 2020, 43(3): 92-98.

ZHANG Tian-qi, KANG Bo, MENG Xiang-fei, LIU Yi-lin, ZHOU Ying. U-Net Based Intracranial Hemorrhage Recognition[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(3): 92-98.

参考文献

[1] 陈旭, 耿翔. 脑出血的研究现状和治疗进展[J]. 中华老年心脑血管病杂志, 2009, 11(12):947-949. Chen Xu, Geng Xiang. Research status and treatment progress of cerebral hemorrhage[J]. Chinese Journal of Geriatric Cardiovascular and Cerebrovascular Diseases, 2009, 11(12):947-949.
[2] 高明, 秦立国. 颅脑CT在脑出血诊断中应用体会[J]. 医学理论与实践, 2016, 29(20):3529-3530. Gao Ming, Qin Liguo. Application experience of cranial CT in the diagnosis of cerebral hemorrhage[J]. The Journal of Medical Theory and Practice, 2016, 29(20):3529-3530.
[3] 刘丰伟, 李汉军, 张逸鹤, 等. 人工智能在医学影像诊断中的应用[J]. 北京生物医学工程, 2019, 38(2):206-211. Liu Fengwei, Li Hanjun, Zhang Yihe, et al. Application of artificial intelligence in medical imaging diagnosis[J]. Beijing Biomedical Engineering, 2019, 38(2):206-211.
[4] Dou Q, Chen H, Yu Lequan, et al. Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks[J]. IEEE Transactions on Medical Imaging, 2016, 35(5):1182-1195.
[5] Payer C, Štern D, Bischof H, et al. Regressing heatmaps for multiple landmark localization using CNNs[J]. Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016, 2016:230-238.
[6] Zhu Wentao, Xiang Xiang, Tran T D, et al. Adversarial deep structured nets for mass segmentation from mammograms[C]//2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).[S.l.]:IEEE Press, 2018:847-850.
[7] Sarker M M K, Rashwan H A, Akram F, et al. SLSdeep:skin lesion segmentation based on dilated residual and pyramid pooling networks[C]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2018. Cham:Springer International Publishing, 2018:21-29.
[8] 李七渝, 张绍祥, 王平安, 等. 人体大脑数字化解剖模型的构建及可视化[J]. 解剖学报, 2005, 36(6):638-641. Li Qiyu, Zhang Shaoxiang, Wang Ping'an, et al. Construction of digitized anatomical model and visualization of human cerebrum[J]. Acta Anatomica Sinica, 2005, 36(6):638-641.
[9] 杨滨, 付峰, 董秀珍. 颅脑CT图像的自动分割和轮廓提取[C]//中国生物医学工程学会成立30周年纪念大会暨2010中国生物医学工程学会学术大会论文集. 北京:[s.n.], 2010:151-156.
[10] 孙涛. 基于特征向量的二维颅脑CT图像配准与分割[D]. 合肥:中国科学技术大学, 2009.
[11] 周平. 基于纹理特征的颅脑CT图像病变自动化检出算法研究[D]. 合肥:中国科学技术大学, 2007.
[12] 王海波. 颅脑CT图像分割算法研究[D]. 哈尔滨:哈尔滨工程大学, 2009.
[13] 于杰夫. 人工智能识别CT颅内血肿影像及脑出血混合征相关算法的研究[D]. 沈阳:中国医科大学, 2018.
[14] Ronneberger O, Fischer P, Brox T. U-net:convolutional networks for biomedical image segmentation[C]//Lecture Notes in Computer Science. Cham:Springer International Publishing, 2015:234-241.
[15] 段瑞玲, 李庆祥, 李玉和. 图像边缘检测方法研究综述[J]. 光学技术, 2005(03):415-419. Duan Ruiling, Li Qingxiang, Li Yuhe. Summary of image edge detection[J]. Optical Technique, 2005, 31(3):415-419.
[16] 马艳, 张治辉. 几种边缘检测算子的比较[J]. 工矿自动化, 2004, 30(1):54-56. Ma Yan, Zhang Zhihui. Comparison of some operators of edge detection[J]. Industry and Automation, 2004, 30(1):54-56.
[17] 唐阳山, 徐忠帅, 黄贤丞, 等. 基于Roberts算子的车道线图像的边缘检测研究[J]. 辽宁工业大学学报(自然科学版), 2017, 37(6):383-386, 390. Tang Yangshan, Xu Zhongshuai, Huang Xiancheng, et al. Research on edge detection for the lane line image based on Roberts operator[J]. Journal of Liaoning University of Technology (Natural Science Edition), 2017, 37(6):383-386, 390.
[18] 罗文村. 基于阈值法与区域生长法综合集成的图像分割法[J]. 现代计算机, 2001(5):43-46. Luo Wencun. A new image segmentation approach by integration of thresholding and regiongrowing[J]. Modern Computer, 2001(5):43-46.
[19] Arbeláez P, Maire M, Fowlkes C, et al. Contour detection and hierarchical image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(5):898-916.
[20] Brusseau E, de Korte C L, Mastik F, et al. Fully automatic luminal contour segmentation in intracoronary ultrasound imaging-a statistical approach[J]. IEEE Transactions on Medical Imaging, 2004, 23(5):554-566.
[21] Pohle R, Toennies K D. Segmentation of medical images using adaptive region growing[C]//Medical Imaging 2001. Proc SPIE 4322, Medical Imaging 2001:Image Processing. San Diego:[s.n.], 2001:1337-1346.
[22] Cui Lingling, Zhang Hui. Study on threshold segmentation of multi-resolution 3D human brain CT image[J]. Journal of Innovative Optical Health Sciences, 2018, 11(6):1850037.
[23] Abbood A A, Sulong G, Razzaq A A A, et al. Segmentation and enhancement of fingerprint images based on automatic threshold calculations[C]//Recent Trends in Information and Communication Technology-IRICT 2017. Cham:Springer International Publishing, 2017:400-411.

基于U-Net的颅内出血识别算法

U-Net Based Intracranial Hemorrhage Recognition

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	刘阳, 滕颖蕾, 牛涛, 郅佳琳. 基于深度强化学习的滤波器剪枝方案[J]. 北京邮电大学学报, 2023, 46(3): 31-36.
[2]	张小乾, 王潇, 薛旭倩, 谈振, 蒲磊. 基于加权多核子空间聚类的图像分割方法[J]. 北京邮电大学学报, 2023, 46(3): 78-83.
[3]	靳梦凡, 黄智濒, 储志强. 复杂环境下多模态指导的点云补全方法[J]. 北京邮电大学学报, 2023, 46(3): 103-108.
[4]	王薇谢沈惟闫浩田张闯吴铭. 基于道路中心线的分阶段弱监督遥感图像道路提取[J]. 北京邮电大学学报, 2023, 46(2): 84-90.
[5]	荣震宇刘建毅. 基于Transformer和MLP的眼底血管分割算法[J]. 北京邮电大学学报, 2023, 46(1): 26-31.
[6]	刘金桐, 杨国兴, 刘晓鸿, 王光宇. 针对心电图分类模型的平滑攻击算法[J]. 北京邮电大学学报, 2022, 45(4): 44-50.
[7]	黄柳婷, 刘可欣, 牛凯, 常春, 贺志强. 基于深度学习的哮喘患者CT影像黏液栓自动识别[J]. 北京邮电大学学报, 2022, 45(4): 58-63.
[8]	柳长源, 虎浩媛, 毕晓君. 双线性融合网络的驾驶员分心行为识别[J]. 北京邮电大学学报, 2022, 45(2): 79-84.
[9]	赵海英, 朱会, 侯小刚. 基于改进EMA单元的传统服饰图像语义分割[J]. 北京邮电大学学报, 2022, 45(1): 69-74.
[10]	张滨宇, 赵衍运, 杜昀昊, 万俊峰, 佟知航. 一种基于深度学习的PCB图像字符检测方法[J]. 北京邮电大学学报, 2022, 45(1): 108-114.
[11]	贾珺, 冯春燕, 夏海轮, 张天魁, 李成钢. 基于样本均衡与特征交互的通信网络故障预测方法[J]. 北京邮电大学学报, 2021, 44(6): 59-66.
[12]	普运伟, 郭江, 刘涛涛, 吴海潇. 基于多学习单元卷积神经网络的雷达辐射源信号识别[J]. 北京邮电大学学报, 2021, 44(6): 74-82.
[13]	王艺霏, 莫爽, 吴文睿, 范少华, 肖丁. 基于内外卷积网络的网络入侵检测[J]. 北京邮电大学学报, 2021, 44(5): 94-100.
[14]	高慧, 张继威, 来扬, 王文东. 深度学习的人体图像半自动标注系统[J]. 北京邮电大学学报, 2021, 44(1): 104-109.
[15]	蒲悦逸, 王文涵, 朱强, 陈朋朋. 基于CNN-ResNet-LSTM模型的城市短时交通流量预测算法[J]. 北京邮电大学学报, 2020, 43(5): 9-14.