颅脑CT影像深度学习预测脑出血破入脑室

彭琦; 陈星材; 刘静静; 吴毅; 胡荣; 粘永健

doi:10.16016/j.2097-0927.202206104

您当前的位置：

首页 >

文章列表页 >

颅脑CT影像深度学习预测脑出血破入脑室

神经科学 | 更新时间：2026-01-09

- 颅脑CT影像深度学习预测脑出血破入脑室
- Prediction of intraventricular hemorrhage based on deep learning of brain CT images
- 陆军军医大学学报 2023年45卷第2期页码：121-129
- 作者机构：
  
  1.400038 重庆，陆军军医大学(第三军医大学)生物医学工程与影像医学系数字医学教研室
  2.400038 重庆，陆军军医大学(第三军医大学)第一附属医院神经外科
- 作者简介：
  
  [粘永健, E-mail: yjnian@tmmu.edu.cn NIAN Yongjian, E-mail: yjnian@tmmu.edu.cn
- 基金信息：
  
  重庆市教委科学技术研究项目(KJQN202212804)
- DOI：10.16016/j.2097-0927.202206104
  中图分类号： R319;R743.34;R814.42
- 收稿：2022-06-16，
  
  修回：2022-07-18，
  
  纸质出版：2023-01-30
- 稿件说明：
移动端阅览
彭琦, 陈星材, 刘静静, 等. 颅脑CT影像深度学习预测脑出血破入脑室[J]. 陆军军医大学学报, 2023,45(2):121-129.

Qi PENG, Xingcai CHEN, Jingjing LIU, et al. Prediction of intraventricular hemorrhage based on deep learning of brain CT images[J]. Journal of Army Medical University, 2023, 45(2): 121-129.
彭琦, 陈星材, 刘静静, 等. 颅脑CT影像深度学习预测脑出血破入脑室[J]. 陆军军医大学学报, 2023,45(2):121-129. DOI： 10.16016/j.2097-0927.202206104.

Qi PENG, Xingcai CHEN, Jingjing LIU, et al. Prediction of intraventricular hemorrhage based on deep learning of brain CT images[J]. Journal of Army Medical University, 2023, 45(2): 121-129. DOI： 10.16016/j.2097-0927.202206104.

摘要

目的

探索深度学习技术在脑出血是否破入脑室自动分类方面的应用。

方法

收集2010年1月到2020年12月陆军军医大学第一附属医院神经外科收治的1 027例自发性脑出血患者的颅脑CT影像

将每层图像划分到正常、未破入脑室、破入脑室3个类别

利用DenseNet121、ResNet50、ResNet101、Swin-base、Vit-base与VGG16等6种典型的深度网络分别构建用于判断脑出血是否破入脑室的分类模型

并在内部数据集和外部数据集(CQ500)上分别进行测试。为增强深度学习网络的可解释性

利用EigenGradCAM方法制作热力图对深度模型的关注区域进行可视化。

结果

利用精确率、召回率、特异性、阴性预测值与F1值评价深度模型性能

VGG16模型在内部测试集上

正常组分别取得0.983、0.977、0.984、0.978与0.980

未破入脑室组分别取得0.917、0.902、0.965、0.958与0.909

破入脑室组分别取得0.877、0.911、0.966、0.976与0.894;外部测试集上

正常组分别取得0.967、0.870、0.985、0.938与0.916

未破入脑室组分别取得0.827、0.939、0.902、0.967与0.879

破入脑室组分别取得0.938、0.906、0.970、0.954与0.922;内部测试集和外部测试集的准确率分别为0.940、0.905。基于EigenGradCAM方法制作的热力图表明VGG16能够合理关注到相关区域。

结论

利用VGG16构建的深度模型在判断脑出血是否破入脑室方面取得了最优的预测性能

表明深度学习可以应用于脑室出血的判断。

Abstract

Objective

To explore the application of deep-learning technology in automatic classification of intraventricular hemorrhage.

Methods

The brain CT images of 1 027 patients with spontaneous ICH from the First Affiliated Hospital of Army Medical University from January 2010 to December 2020 were collected and retrospectively analyzed

which were subsequently divided into 3 types: normal

intracerebral hemorrhage with/without intraventricular extension.Six typical deep networks

including DenseNet121

ResNet101

ResNet50

Swin-base

Vit-base and VGG16

were used to construct classification models for identifying whether there was intraventricular extension of intracerebral hemorrhage.The performance of each model was assessed on both the internal and external data sets (CQ500) respectively.In order to enhance the interpretability of the deep learning networks

the EigenGradCAM method was adopted to generate heatmaps for visualization of the interested regions of the model.

Results

The performance of the models was evaluated based on precision

recall rate

specificity

negative predictive value (NPV) and F1 value.On the internal test set of VGG16 model

the normal group achieved 0.983

0.977

0.984

0.978 and 0.980

respectively; the intracerebral hemorrhage without intraventricular extension group achieved 0.917

0.902

0.965

0.958 and 0.909;and the intraventricular extension of intracerebral hemorrhage group obtained 0.877

0.911

0.966

0.976 and 0.894

respectively.Meanwhile

on the external test set of VGG16 model

the normal group reached 0.967

0.870

0.985

0.938 and 0.916;the intracerebral hemorrhage without intraventricular extension group reached 0.827

0.939

0.902

0.967 and 0.879;and the intraventricular extension of intracerebral hemorrhage group achieved 0.938

0.906

0.970

0.954 and 0.922.The accuracy (ACC) of internal and external test sets was 0.940 and 0.905

respectively.Finally

the heatmaps generated by EigenGradCAM method showed the VGG16 could reasonably focus on the relevant areas.

Conclusion

The VGG16 achieved the best predictive performance for identifying whether there is an intraventricular extension in intracerebral hemorrhage or not

indicating that deep learning can be effectively applied to the judgement of intraventricular hemorrhage.

关键词

Keywords

references

ABDELMALIK P A, ZIAI W C. Spontaneous intraventricular hemorrhage: when should intraventriculartPA be considered?[J]. Semin Respir Crit Care Med, 2017, 38(6): 745-759. DOI: 10.1055/s-0037-1607991.

CHAN E, ANDERSON C S, WANG X, et al . Significance of intraventricular hemorrhage in acute intracerebral hemorrhage: intensive blood pressure reduction in acute cerebral hemorrhage trial results[J ] . Stroke, 2015, 46(3): 653-658. DOI: 10.1161/STROKEAHA.114. 008470.

TRIFAN G, ARSHI B, TESTAI F D. Intraventricular hemorrhage severity as a predictor of outcome in intracerebral hemorrhage[J]. Front Neurol, 2019, 10: 217. DOI: 10.3389/fneur.2019.00217.

HEMPHILL J C 3rd, BONOVICH D C, BESMERTIS L, et al . The ICH score: a simple, reliable grading scale for intracerebral hemorrhage[J ] . Stroke, 2001, 32(4): 891-897. DOI: 10.1161/01.str.32.4.891.

CHILAMKURTHY S, GHOSH R, TANAMALA S, et al . Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study[J ] . Lancet, 2018, 392(10162): 2388-2396. DOI: 10.1016/S0140-6736(18)31645-3.

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]. Proceedings of International Conference on Learn Represention, San Diego, USA, 2015: 1-14.

HUANG G, LIU Z, VAN DER MAATEN L, et al . Densely connected convolutional networks[C ] //, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA. IEEE, 2017: 2261-2269. DOI: 10.1109/CVPR.2017.243.

HE K M, ZHANG X Y, REN S Q, et al . Deep residual learning for image recognition[C ] , Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA. IEEE, 2016: 770-778. DOI: 10.1109/CVPR.2016.90.[LinkOut ]

DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al . An image is worth 16x16 words: Transformers for image recognition at scale. arXiv: 2010.11929v2[cs. CV ] , 2021. https://arxiv.org/abs/2010.11929.

LIU Z, LIN Y T, CAO Y, et al . Swin transformer: hierarchical vision transformer using shifted windows[C ] . Proceedings of IEEE/CVF International Conference on Computer Vision, Montreal, Canada, IEEE, 2021: 9992-10002. DOI: 10.1109/ICCV48922.2021.00986.

柏树令, 应大君. 系统解剖学[M]. 9版. 北京: 人民卫生出版社, 2018: 403.

BAI S L, YING D J. Systematic anatomy[M]. 9th edition, Beijing: People's Health Publishing House, 2018: 403.

GARTON T, HUA Y, XIANG J M, et al . Challenges for intraventricular hemorrhage research and emerging therapeutic targets[J ] . Expert Opin Ther Targets, 2017, 21(12): 1111-1122. DOI: 10.1080/14728222.2017.1397628.

XIA D Y, JIANG X C, LI Z B, et al . External ventricular drainage combined with continuous lumbar drainage in the treatment of ventricular hemorrhage[J ] . Ther Clin Risk Manag, 2019, 15: 677-682. DOI: 10.2147/TCRM.S207750.

ZHAO X J, CHEN K X, WU G, et al . Deep learning shows good reliability for automatic segmentation and volume measurement of brain hemorrhage, intraventricular extension, and peripheral edema[J ] . Eur Radiol, 2021, 31(7): 5012-5020. DOI: 10.1007/s00330-020-07558-2.

ZHU D Q, CHEN Q, XIANG Y L, et al . Predicting intraventricular hemorrhage growth with a machine learning-based, radiomics-clinical model[J ] . Aging, 2021, 13(9): 12833-12848. DOI: 10.18632/aging.202954.

WONG A, BAIG S, CHEN Z J, et al . Abstract 97: development and validation of A deep machine learning tool for automated intraventricular hemorrhage segmentation and volume measurement using 3d convolutional neural networks[J ] . Stroke, 2022, 53(Suppl_1): 97-100. DOI: 10.1161/str.53.suppl_1.97.

王霁雯, 林雨, 熊建华, 等. 基于深度学习的自发性脑出血CT影像分割算法精准计算病灶体积的应用探讨[J]. 中华放射学杂志, 2019, 53(11): 941-945. DOI: 10.3760/cma.j.issn.1005?1201.2019.11.003.

WANG J W, LIN Y, XIONG J H, et al . Evaluation of spontaneous intracerebral hemorrhage by using CT image segmentation and volume assessment based on deep learning[J ] . Chin J Radiol, 2019, 53(11): 941-945. DOI: 10.3760/cma.j.issn.1005?1201.2019.11.003.

YE H, GAO F, YIN Y B, et al . Precise diagnosis of intracranial hemorrhage and subtypes using a three-dimensional joint convolutional and recurrent neural network[J ] . Eur Radiol, 2019, 29(11): 6191-6201. DOI: 10.1007/s00330-019-06163-2.

WANG X Y, SHEN T, YANG S, et al . A deep learning algorithm for automatic detection and classification of acute intracranial hemorrhages in head CT scans[J ] . Neuroimage Clin, 2021, 32: 102785. DOI: 10.1016/j.nicl.2021.102785.

LEE H, YUNE S, MANSOURI M, et al . An explainable deep-learning algorithm for the detection of acute intracranial haemorrhage from small datasets[J ] . Nat Biomed Eng, 2019, 3(3): 173-182. DOI: 10.1038/s41551-018-0324-9.

CHO J, PARK K S, KARKI M, et al . Improving sensitivity on identification and delineation of intracranial hemorrhage lesion using cascaded deep learning models[J ] . J Digit Imaging, 2019, 32(3): 450-461. DOI: 10 .1007/s10278-018-00172-1.

KUO W, HÄNE C, MUKHERJEE P, et al . Expert-level detection of acute intracranial hemorrhage on head computed tomography using deep learning[J ] . Proc Natl Acad Sci USA, 2019, 116(45): 22737-22745. DOI: 10.1073/pnas.1908021116.

LI J Q, FU G H, CHEN Y D, et al . A multi-label classification model for full slice brain computerised tomography image[J ] . BMC Bioinformatics, 2020, 21(Suppl 6): 200. DOI: 10.1186/s12859-020-3503-0.

BURDUJA M, IONESCU R T, VERGA N. Accurate and efficient intracranial hemorrhage detection and subtype classification in 3D CT scans with convolutional and long short-term memory neural networks[J]. Sensors (Basel), 2020, 20(19): 5611. DOI: 10.3390/s20195611.

PHAPHUANGWITTAYAKUL A, GUO Y, YING F L, et al . An optimal deep learning framework for multi-type hemorrhagic lesions detection and quantification in head CT images for traumatic brain injury[J ] . Appl Intell (Dordr), 2022, 52(7): 7320-7338. DOI: 10.1007/s10489-021-02782-9.

NGUYEN N T, TRAN D Q, NGUYEN N T, et al . A CNN-LSTM architecture for detection of intracranial hemorrhage on CT scans[J ] . medRxiv, 2020, DOI: 10.1101/2020.04.17.20070193.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

融合深度学习、临床与影像组学特征的综合模型提升非小细胞肺癌EGFR突变预测效能

基于CT影像的3D ResNet18模型在肺结核耐药性识别中的预测性能研究

深度学习和磁共振图像辅助脑胶质瘤基因分型的研究进展

基于小波变换和CNN-Transformer的超声甲状腺结节分割算法研究

基于深度学习的MRI影像女性尿控解剖元件及相关结构的自动分割