收稿日期: 2023-10-11
网络出版日期: 2024-01-24
基金资助
四川省科技计划项目(2023YFQ0006);电子科技大学中央高校基本科研业务费项目(ZYGX2020ZB038)
Deep learning technology for quality control of echocardiography images
Received date: 2023-10-11
Online published: 2024-01-24
目的 探讨深度学习技术在超声心动图图像质量控制中应用的可行性和价值。 方法 选取四川省人民医院2015~2022年间收集的180 985张超声心动图图像建立实验数据集，训练了超声心动图标准切面图像质量评价方法所建立的两个任务模型，包括7类切面（6类标准切面和其他切面）的智能识别和6类标准切面的质量评分。将模型在测试集上的预测结果与超声医师标注结果进行比较，评估两个模型的准确性、可行性以及运行的时效性。 结果 标准切面识别模型的总体分类准确率为98.90%，精确度为98.17%，召回率为98.18%，F1值为98.17%，分类结果接近专家识别水平；6种标准切面质量评分模型的平均PLCC为0.933，平均SROCC为0.929，平均RMSE为7.95，平均MAE为4.83，预测结果与专家评分一致性强。在3090 GPU上部署后，单帧推理时间小于20毫秒，满足实时需求。 结论 超声心动图标准切面图像质量评价方法能够提供客观、准确的评价结果，促进超声心动图图像质量控制管理朝实时、客观、智能化方向发展。
李欣雨 , 吴洋 , 张红梅 , 尹立雪 , 彭博 , 谢盛华 . 深度学习技术在超声心动图图像质量控制中的应用[J]. 实用医学杂志, 2024 , 40(1) : 108 -113 . DOI: 10.3969/j.issn.1006-5725.2024.01.019
Objective To Explore the feasibility and value of deep learning technology for quality control of echocardiography images. Methods A total of 180985 echocardiography images collected from Sichuan Provincial People's Hospital between 2015 and 2022 were selected to establish the experimental dataset. Two task models of the echocardiography standard views quality assessment method were trained， including intelligent recognition of seven types of views （six standard views and other views） and quality scoring of six standard views. The predictions of the models on the test set were compared with the results of the sonographer's annotation to assess the accuracy， feasibility， and timeliness of the runs of the two models. Results The overall classification accuracy of the standard views recognition model was 98.90%， the precision was 98.17%， the recall was 98.18% and the F1 value was 98.17%， with the classification results close to the expert recognition level； the average PLCC of the six standard views quality scoring models was 0.933， the average SROCC was 0.929， the average RMSE was 7.95 and the average MAE was 4.83， and the prediction results were in strong agreement with the expert scores. The single-frame inference time after deployment on the 3090 GPU was less than 20 ms， meeting real-time requirements. Conclusion The echocardiography standard views quality assessment method can provide objective and accurate quality assessment results， promoting the development of echocardiography image quality control management towards real-time， objective， and intelligent.
| 1 | ZHOU J， DU M， CHANG S， et al. Artificial intelligence in echocardiography： detection， functional evaluation， and disease diagnosis［J］. Cardiovasc Ultrasound， 2021， 19（1）： 1-11. |
| 2 | LIAO Z， GIRGIS H， ABDI A， et al. On modelling label uncertainty in deep neural networks： Automatic estimation of intra-observer variability in 2d echocardiography quality assessment［J］. IEEE Trans Med Imaging， 2020， 39（6）： 1868-1883. |
| 3 | JAFARI M H， GIRGIS H， VAN WOUDENBERG N， et al. Cardiac point-of-care to cart-based ultrasound translation using constrained CycleGAN［J］. Int J Comput Assist Radiol Surg， 2020， 15（5）： 877-886. |
| 4 | 张勇， 鲁晓， 李昕， 等. 超声医学图像及报告质量管理系统设计与应用［J］. 中国卫生质量管理， 2022， 29（4）： 73-76. |
| 5 | DONG J， LIU S， LIAO Y， et al. A generic quality control framework for fetal ultrasound cardiac four-chamber planes［J］. IEEE J Biomed Health Inform， 2020， 24（4）： 931-942. |
| 6 | ZAMZMI G， RAJARAMAN S， HSU L Y， et al. Real-time echocardiography image analysis and quantification of cardiac indices［J］. Med Image Anal， 2022， 80： 102438. |
| 7 | ZHANG J， GAJJALA S， AGRAWAL P， et al. Fully automated echocardiogram interpretation in clinical practice： feasibility and diagnostic accuracy［J］. Circulation， 2018， 138（16）： 1623-1635. |
| 8 | HUANG K C， HUANG C S， SU M Y， et al. Artificial intelligence aids cardiac image quality assessment for improving precision in strain measurements［J］. Cardiovasc Imaging， 2021， 14（2）： 335-345. |
| 9 | ABDI A H， LUONG C， TSANG T， et al. Automatic quality assessment of echocardiograms using convolutional neural networks： feasibility on the apical four-chamber view［J］. IEEE Trans Med Imaging， 2017， 36（6）： 1221-1230. |
| 10 | LUONG C， LIAO Z， ABDI A， et al. Automated estimation of echocardiogram image quality in hospitalized patients［J］. Int J Cardiovasc Imaging， 2021， 37： 229-239. |
| 11 | GAUDET J， WAECHTER J， MCLAUGHLIN K， et al. Focused critical care echocardiography： development and evaluation of an image acquisition assessment tool［J］. Crit Care Med， 2016， 44（6）： 329-335. |
| 12 | LI J， XIA X， LI W， et al. Next-vit： Next generation vision transformer for efficient deployment in realistic industrial scenarios［J］. arXiv e-prints， 2022. doi： 10.48550/arXiv.2207.05501 . |
| 13 | CHOU P Y， LIN C H， KAO W C. A novel plug-in module for fine-grained visual classification［J］. arXiv e-prints， 2022. doi： 10.48550/arXiv.2202.03822 . |
| 14 | KHOSLA P， TETERWAK P， WANG C， et al. Supervised contrastive learning［J］. Adv Neural Inf Process Syst， 2020， 33： 18661-18673. |
| 15 | YANG S， WU T， SHI S， et al. Maniqa： Multi-dimension attention network for no-reference image quality assessment［C］. IEEE Conference on Computer Vision and Pattern Recognition， 2022. doi： 10.48550/arXiv.2204.08958 . |
| 16 | SHEN Y T， CHEN L， YUE W W， et al. Artificial intelligence in ultrasound［J］. Eur J Radiol， 2021， 139： 109717. |
| 17 | ZHANG Z， ZHU Y， LIU M， et al. Artificial Intelligence-Enhanced Echocardiography for Systolic Function Assessment［J］. J Clin Med， 2022， 11（10）： 2893. |
| 18 | 罗刚， 泮思林， 乔思波， 等. 深度学习技术在胎儿超声心动图图像自动识别中的应用［J］. 实用医学杂志， 2022， 38（14）： 1830-1833. |
| 19 | SEHLY A， JALTOTAGE B， HE A， et al. Artificial Intelligence in Echocardiography： The Time is Now［J］. Rev Cardiovasc Med， 2022， 23（8）： 256. |
| 20 | FERRAZ S， COIMBRA M， PEDROSA J. Assisted probe guidance in cardiac ultrasound： A review［J］. Front Cardiovasc Med， 2023， 10： 1056055. |
/
| 〈 |
|
〉 |