基于卷积神经网络的自发性脑出血血肿分割方法的一致性评价

doi:10.3969/j.issn.1672-6731.2020.07.005

中国现代神经疾病杂志 ›› 2020, Vol. 20 ›› Issue (7): 585-590. doi: 10.3969/j.issn.1672-6731.2020.07.005

2 基于卷积神经网络的自发性脑出血血肿分割方法的一致性评价

常健博¹, 姜燊种¹, 陈显金², 骆嘉希³, 李沃霖³, 张庆华², 魏俊吉¹, 石林⁴, 冯铭¹, 王任直¹

1 100730 中国医学科学院北京协和医学院北京协和医院神经外科;
2 518051 华中科技大学协和深圳医院(南山医院)神经外科;
3 518000 深圳博脑研究院;
4 999077 香港中文大学医学院影像及介入放射学系

收稿日期:2020-05-02 出版日期:2020-07-25 发布日期:2020-07-24
通讯作者: 冯铭,Email:jackietz@163.com;王任直,Email:wangrz@126.com
基金资助:
北京市自然科学基金资助项目（项目编号：7182137）；中国医学科学院医学与健康科技创新工程重大协同创新项目（项目编号：2017-I2M-3-014）；中国医学科学院北京协和医学院研究生教育教学立项项目（项目编号：10023201900107）

Consistency evaluation of an automatic segmentation for quantification of intracerebral hemorrhage using convolution neural network

CHANG Jian-bo¹, JIANG Shen-zhong¹, CHEN Xian-jin², LOK Ka-hei³, LEE Yuk-lam³, ZHANG Qing-hua², WEI Jun-ji¹, SHI Lin⁴, FENG Ming¹, WANG Ren-zhi¹

1 Department of Neurosurgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China;
2 Department of Neurosurgery, Union Shenzhen Hospital(Nanshan Hospital), Huazhong University of Science and Technology, Shenzhen 518051, Guangdong, China;
3 Shenzhen BrainNow Research Institute, Shenzhen 518000, Guangdong, China;
4 Department of Imaging and Interventional Radiology, the Chinese University of Hong Kong, Hongkong 999077, China

Received:2020-05-02 Online:2020-07-25 Published:2020-07-24
Supported by:
This study was supported by the Natural Science Foundation of Beijing (No. 7182137), Chinese Academy of Medical Sciences (CAMS) Innovation Fund for Medical Sciences (No. 2017-I2M-3-014), and Chinese Academy of Medical Sciences (CAMS) & Peking Union Medical School Postgraduate Teaching Innovation Fund (No. 10023201900107).

摘要/Abstract

摘要：

目的建立一种基于卷积神经网络的脑血肿分割算法，探讨算法与手动分割结果的一致性。方法纳入中国颅内出血影像数据库中146例头部CT平扫影像图片，采用随机数字表法分为训练集（90例）、测试集（26例）和验证集（30例），验证集采用手动分割、算法分割、精确多田公式和传统多田公式共4种方法对血肿体积进行测量，以手动分割为“金标准”，分别对其他3种算法进行一致性检验。结果与多田公式方法相比，算法分割的百分误差最小，为15.54（8.41，23.18）%，组内相关系数最高，为0.983；Bland-Altman一致性检测显示，93.33%的数据在95%一致性界限（95% LoA），且其95% LoA最窄，为-6.46~5.97 ml。算法分割的百分误差在不同血肿形态、体积比较中差异无统计学意义（均P > 0.05）。结论卷积神经网络构建的算法分割具有一定的临床应用前景，但仍需更大样本的临床试验加以验证。

关键词: 脑出血, 人工智能, 神经网络(计算机), 体层摄影术, X线计算机

Abstract:

Objective To establish an automatic segmentation algorithm using convolution neural network, and to validate the consistency between the algorithm and manual segmentation. Methods One hundred and forty-six CT scans of intracerebral hemorrhage (ICH) were included from Chinese Intracranial Hemorrhage Image Database (CICHID). They were randomly divided into training set (n=90), testing set (n=26) and validation set (n=30). All CT scans were manual segmentation. Training set and testing set were used for algorithm training. The validation set was measured by four methods including manual segmentation, algorithm segmentation, accurate Tada formula and traditional Tada formula. The consistency test was performed. Results Compared with the Tada formula methods, the percentage error of algorithm values was the smallest 15.54 (8.41, 23.18)%, and algorithm agreement with the manual reference was the strongest (correlation coefficient 0.983). Bland-Altman analysis showed that 93.33% of the data was within the 95% limits of agreement (95% LoA), and 95% LoA was narrow (-6.46-5.97 ml). No significant differences were found in size and shape (P > 0.05, for all). Conclusions The algorithm using convolutional neural network has a certain application prospect, but it needs still more validation in large sample research.

Key words: Cerebral hemorrhage, Artificial intelligence, Neural networks (computer), Tomography, X-ray computed

常健博, 姜燊种, 陈显金, 骆嘉希, 李沃霖, 张庆华, 魏俊吉, 石林, 冯铭, 王任直. 基于卷积神经网络的自发性脑出血血肿分割方法的一致性评价[J]. 中国现代神经疾病杂志, 2020, 20(7): 585-590.

CHANG Jian-bo, JIANG Shen-zhong, CHEN Xian-jin, LOK Ka-hei, LEE Yuk-lam, ZHANG Qing-hua, WEI Jun-ji, SHI Lin, FENG Ming, WANG Ren-zhi. Consistency evaluation of an automatic segmentation for quantification of intracerebral hemorrhage using convolution neural network[J]. Chinese Journal of Contemporary Neurology and Neurosurgery, 2020, 20(7): 585-590.

http://journal11.magtechjournal.com/cjcnn/CN/Y2020/V20/I7/585

参考文献

[1] GBD 2016 Stroke Collaborators. Global, regional, and national burden of stroke, 1990-2016:a systematic analysis for the Global Burden of Disease Study 2016[J]. Lancet Neurol, 2019, 18:439-458.
[2] An SJ, Kim TJ, Yoon BW. Epidemiology, risk factors, and clinical features of intracerebral hemorrhage:an update[J]. J Stroke, 2017, 19:3-10.
[3] Wu S, Wu B, Liu M, Chen Z, Wang W, Anderson CS, Sandercock P, Wang Y, Huang Y, Cui L, Pu C, Jia J, Zhang T, Liu X, Zhang S, Xie P, Fan D, Ji X, Wong KL, Wang L; China Stroke Study Collaboration. Stroke in China:advances and challenges in epidemiology, prevention, and management[J].Lancet Neurol, 2019, 18:394-405.
[4] Xu X, Chen X, Zhang J, Zheng Y, Sun G, Yu X, Xu B. Comparison of the Tada formula with software slicer:precise and low-cost method for volume assessment of intracerebral hematoma[J]. Stroke, 2014, 45:3433-3435.
[5] Jiang CY, Liu JX, Zhong HX, Li HY, Li DJ. Study on CT image segmentation of intracranial hemorrhage based on improved FCM fuzzy clustering[J]. Zhongguo Yi Liao She Bei, 2018, 33:16-20.[姜春雨, 刘景鑫, 钟慧湘, 李慧盈, 李大军. 基于改进的FCM模糊聚类的颅内出血CT图像分割研究[J]. 中国医疗设备, 2018, 33:16-20.]
[6] Cho J, Park KS, Karki M, Lee E, Ko S, Kim JK, Lee D, Choe J, Son J, Kim M, Lee S, Lee J, Yoon C, Park S. Improving sensitivity on identification and delineation of intracranial hemorrhage lesion using cascaded deep learning models[J]. J Digit Imaging, 2019, 32:450-461.
[7] Scherer M, Cordes J, Younsi A, Sahin YA, Götz M, Möhlenbruch M, Stock C, Bösel J, Unterberg A, Maier-Hein K, Orakcioglu B. Development and validation of an automatic segmentation algorithm for quantification of intracerebral hemorrhage[J]. Stroke, 2016, 47:2776-2782.
[8] Wang RZ, Chang JB, Feng M. Prospects for precious diagnosis, assessment, prediction and treatment of hemorrhagic stroke[J].Zhongguo Xian Dai Shen Jing Ji Bing Za Zhi, 2019, 19:618-621.[王任直, 常健博, 冯铭. 出血性卒中精准诊断、评估、预测及治疗展望[J]. 中国现代神经疾病杂志, 2019, 19:618-621.]
[9] Yushkevich PA, Piven J, Hazlett HC, Smith RG, Ho S, Gee JC, Gerig G. User-guided 3D active contour segmentation of anatomical structures:significantly improved efficiency and reliability[J]. Neuroimage, 2006, 31:1116-1128.
[10] Kothari RU, Brott T, Broderick JP, Barsan WG, Sauerbeck LR, Zuccarello M, Khoury J. The ABCs of measuring intracerebral hemorrhage volumes[J]. Stroke, 1996, 27:1304-1305.
[11] Huttner HB, Steiner T, Hartmann M, Köhrmann M, Juettler E, Mueller S, Wikner J, Meyding-Lamade U, Schramm P, Schwab S, Schellinger PD. Comparison of ABC/2 estimation technique to computer-assisted planimetric analysis in warfarin-related intracerebral parenchymal hemorrhage[J]. Stroke, 2006, 37:404-408.
[12] Wang CW, Juan CJ, Liu YJ, Hsu HH, Liu HS, Chen CY, Hsueh CJ, Lo CP, Kao HW, Huang GS. Volume-dependent overestimation of spontaneous intracerebral hematoma volume by the ABC/2 formula[J]. Acta Radiol, 2009, 50:306-311.
[13] Morrison MA, Payabvash S, Chen Y, Avadiappan S, Shah M, Zou X, Hess CP, Lupo JM. A user-guided tool for semi -automated cerebral microbleed detection and volume segmentation:evaluating vascular injury and data labelling for machine learning[J]. Neuroimage Clin, 2018, 20:498-505.
[14] Prakash KN, Zhou S, Morgan TC, Hanley DF, Nowinski WL. Segmentation and quantification of intra-ventricular/cerebral hemorrhage in CT scans by modified distance regularized level set evolution technique[J]. Int J Comput Assist Radiol Surg, 2012, 7:785-798.
[15] Li YH, Zhang L, Hu QM, Li HW, Jia FC, Wu JH. Automatic subarachnoid space segmentation and hemorrhage detection in clinical head CT scans[J]. Int J Comput Assist Radiol Surg, 2012, 7:507-516.
[16] Chang PD, Kuoy E, Grinband J, Weinberg BD, Thompson M, Homo R, Chen J, Abcede H, Shafie M, Sugrue L, Filippi CG, Su MY, Yu W, Hess C, Chow D. Hybrid 3D/2D convolutional neural network for hemorrhage evaluation on head CT[J].AJNR Am J Neuroradiol, 2018, 39:1609-1616.
[17] Prasad K, Mendelow AD, Gregson B. Surgery for primary supratentorial intracerebral haemorrhage[J]. Cochrane Database Syst Rev, 2008, (8):CD000200.
[18] Tang Y, Yin F, Fu D, Gao X, Lv Z, Li X. Efficacy and safety of minimal invasive surgery treatment in hypertensive intracerebral hemorrhage:a systematic review and Meta-analysis[J]. BMC Neurol, 2018, 18:136.
[19] Mendelow AD, Gregson BA, Rowan EN, Murray GD, Gholkar A, Mitchell PM; STICH Ⅱ Investigators. Early surgery versus initial conservative treatment in patients with spontaneous supratentorial lobar intracerebral haematomas (STICH Ⅱ):a randomised trial[J]. Lancet, 2013, 382:397-408.
[20] Hanley DF, Thompson RE, Rosenblum M, Yenokyan G, Lane K, McBee N, Mayo SW, Bistran-Hall AJ, Gandhi D, Mould WA, Ullman N, Ali H, Carhuapoma JR, Kase CS, Lees KR, Dawson J, Wilson A, Betz JF, Sugar EA, Hao Y, Avadhani R, Caron JL, Harrigan MR, Carlson AP, Bulters D, LeDoux D, Huang J, Cobb C, Gupta G, Kitagawa R, Chicoine MR, Patel H, Dodd R, Camarata PJ, Wolfe S, Stadnik A, Money PL, Mitchell P, Sarabia R, Harnof S, Barzo P, Unterberg A, Teitelbaum JS, Wang W, Anderson CS, Mendelow AD, Gregson B, Janis S, Vespa P, Ziai W, Zuccarello M, Awad IA; MISTIE Ⅲ Investigators. Efficacy and safety of minimally invasive surgery with thrombolysis in intracerebral haemorrhage evacuation(MISTIE Ⅲ):a randomised, controlled, open-label, blinded endpoint phase 3 trial[J]. Lancet, 2019, 393:1021-1032.
[21] Gross BA, Jankowitz BT, Friedlander RM. Cerebral intraparenchymal hemorrhage:a review[J]. JAMA, 2019, 321:1295-1303.

选择文件类型/文献管理软件名称

选择包含的内容

2 基于卷积神经网络的自发性脑出血血肿分割方法的一致性评价

Consistency evaluation of an automatic segmentation for quantification of intracerebral hemorrhage using convolution neural network

RichHTML

PDF

可视化

被引次数

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]	刘笑宇, 常健博, 张笑, 魏俊吉. 继发性脑积水发病机制研究进展[J]. 中国现代神经疾病杂志, 2023, 23(6): 490-495.
[2]	张磊, 张涛. 脑电双频指数与自发性脑出血患者预后相关性分析[J]. 中国现代神经疾病杂志, 2023, 23(6): 515-521.
[3]	韩国庆, 蒲珂, 李庆国. 儿童脑海绵状血管瘤临床特点及发病机制研究进展[J]. 中国现代神经疾病杂志, 2023, 23(5): 393-397.
[4]	巫嘉陵, 韩建达. 医疗人工智能：知识引导与数据挖掘联合驱动[J]. 中国现代神经疾病杂志, 2023, 23(1): 1-4.
[5]	王旭, 李琼阁, 赵澄, 单艺, 卢洁. 直立位X线对腰椎滑脱诊断效能分析[J]. 中国现代神经疾病杂志, 2022, 22(8): 675-679.
[6]	王志平, 张义森, 曲丽莹. 蛛网膜下腔出血CT分布对颅内动脉瘤检出的价值[J]. 中国现代神经疾病杂志, 2022, 22(7): 621-627.
[7]	秦寒枝, 储爱琴, 孙建, 张振伟, 王忠丽, 牛朝诗. 急性脑出血术后应激性溃疡危险因素分析及列线图预测模型构建[J]. 中国现代神经疾病杂志, 2022, 22(5): 414-421.
[8]	徐伟, 谢之易, 王泽旭, 马潞, 游潮, 胡鑫. 核因子E2相关因子2对脑出血继发性损伤调控机制研究进展[J]. 中国现代神经疾病杂志, 2022, 22(10): 836-840.
[9]	杨翀, 李旭东, 吕良福, 袁恒杰, 张毅. 大数据模型预测动脉瘤夹闭术后动脉瘤性蛛网膜下腔出血患者预后临床研究：模型建立与评价[J]. 中国现代神经疾病杂志, 2022, 22(10): 841-849.
[10]	王伟, 崇立娟, 余苗, 孟闫凯, 徐凯. 伴脑白质疏松症的超急性期高血压脑出血血肿不稳定CT征象分析[J]. 中国现代神经疾病杂志, 2022, 22(10): 850-856.
[11]	高永涛, 陈小兵. 脑室铸型神经内镜手术疗效分析[J]. 中国现代神经疾病杂志, 2022, 22(10): 865-870.
[12]	赵顺忠, 杨彦龙, 杨阳, 鲁华山, 朱宗远, 张明浩, 李立宏. 自发性小脑出血术后远期预后影响因素分析[J]. 中国现代神经疾病杂志, 2022, 22(10): 871-878.
[13]	贾俊丽, 王勤周, 戴廷军, 崔谊, 徐广润. ACVRL1基因变异的遗传性出血性毛细血管扩张症致脑出血一例[J]. 中国现代神经疾病杂志, 2022, 22(10): 887-891.
[14]	陈亦豪, 常健博, 魏俊吉, 冯铭, 王任直. 脑卒中大型医学数据库应用及研究进展[J]. 中国现代神经疾病杂志, 2021, 21(3): 141-146.
[15]	井奚月, 乔婕, 么秀华, 徐立霞, 闫华. ZFNet模型在胶质瘤MRI诊断中的应用[J]. 中国现代神经疾病杂志, 2021, 21(3): 156-161.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

2 基于卷积神经网络的自发性脑出血血肿分割方法的一致性评价

Consistency evaluation of an automatic segmentation for quantification of intracerebral hemorrhage using convolution neural network

RichHTML

PDF

可视化

被引次数

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