The Journal of Practical Medicine >

2023 , Vol. 39 >Issue 22: 2979 - 2983

DOI: https://doi.org/10.3969/j.issn.1006-5725.2023.22.021

Medical Examination and Clinical Diagnosis

Deep learning convolutional neural network model trained from scratch algorithm in the evaluation of acute pulmonary thromboembolism

  • Runcai GUO ,
  • Lei WANG ,
  • Zhenguo HUANG ,
  • Linfeng XI ,
  • Shuai ZHANG ,
  • Min. LIU
Expand
  • *.Department of Radiology，China?Japan Friendship Hospital，Beijing 100029，China

Received date: 2023-08-11

  Online published: 2023-12-11

Fold

Abstract

Objective This research aimed to study the values of the deep learning convolutional neural network model trained from scratch（DL?CNN（fs）） in assessment of acute pulmonary thromboembolism （APE）. Methods A total of 214 patients with suspected APE who underwent computed tomography pulmonary angiography（CTPA） were retrospectively studied， including 137 patients with APE and 77 patients without APE. The presence or absence of APE was determined by the radiologists based on CTPA. The Qanadli score， Mastora score and other parameters on CTPA were measured by the radiologists. The clot volumes and distribution were measured by U?net model which was based on DL?CNN. The performance of DL?CNN（fs） in measuring clot distribution and clot burden was evaluated. The correlation between clot burden and Qanadli score， Mastora score and other CTPA parameters was calculated. Results Sensitivity， specificity and AUC of the central pulmonary artery clot distribution measured by DL?CNN（fs） were 100%， 16.8%， AUC = 0.584 （95%CI： 0.508 ~ 0.661）. Sensitivity， specificity and AUC of the peripheral pulmonary artery clot distribution were high （R1?R9， 60.8% ~ 95.2%，67.9% ~ 87.1%，0.740 ~ 0.844； L1?L10， 64.6% ~ 93.4%， 62.7% ~ 83.1%， 0.732 ~ 0.791）. Strong positive correlation was noted between clot volumes measured by DL?CNN （fs） model and Qanadli score （r = 0.867，P < 0.001）， as well as Mastora score （r = 0.854， P < 0.001）. Clot volumes measured by DL?CNN （fs） model were correlated with the right ventricular functional parameters（right ventricular diameter/left ventricular diameter， right ventricular area/left ventricular area，r = 0.549， 0.559， P < 0.01）. Conclusion The DL?CNN （fs） model has high value in detecting peripheral pulmonary embolism， and its diagnostic specificity for central pulmonary embolism needs to be further improved. The clot volumes from DL?CNN（fs） were correlated with metrics of pulmonary embolism and right ventricular function， which may help doctors to quickly evaluate the clot burden and risk stratification of acute pulmonary thromboembolism.

Key words： deep learning; convolution neural network; acute pulmonary thromboembolism; computed tomography pulmonary angiography

Cite this article

Runcai GUO , Lei WANG , Zhenguo HUANG , Linfeng XI , Shuai ZHANG , Min. LIU . Deep learning convolutional neural network model trained from scratch algorithm in the evaluation of acute pulmonary thromboembolism[J]. The Journal of Practical Medicine, 2023 , 39(22) : 2979 -2983 . DOI: 10.3969/j.issn.1006-5725.2023.22.021

References

1 PALM V， RENGIER F， RAJIAH P， et al. Acute Pulmonary Embolism： Imaging Techniques， Findings， Endovascular Treatment and Differential Diagnoses［J］. Rofo，2020，192（1）：38-49.
2 QANADLI S D， HAJJAM M EL， VIEILLARD-BARON A， et al. New CT index to quantify arterial obstruction in pulmonary embolism： comparison with angiographic index and echocardiography［J］. AJR Am J Roentgenol，2001，176（6）：1415-1120.
3 MASTORA I， REMY-JARDIN M， MASSON P， et al. Severity of acute pulmonary embolism： evaluation of a new spiral CT angiographic score in correlation with echocardiographic data［J］. Eur Radiol，2003，13（1）：29-35.
4 CURRIE G. Intelligent Imaging： Anatomy of Machine Learning and Deep Learning［J］. J Nucl Med Technol，2019，47（4）：273-281.
5 REA G， SVERZELLATI N， BOCCHINO M， et al. Sica G. Beyond Visual Interpretation： Quantitative Analysis and Artificial Intelligence in Interstitial Lung Disease Diagnosis "Expanding Horizons in Radiology"［J］. Diagnostics （Basel），2023，13（14）：2333.
6 WANG H， WANG L， LEE E H， et al. Decoding COVID-19 pneumonia： comparison of deep learning and radiomics CT image signatures［J］. Eur J Nucl Med Mol Imaging，2021，48（5）：1478-1486.
7 CHANG C C， TANG E K， WEI Y F， et al. Clinical radiomics-based machine learning versus three-dimension convolutional neural network analysis for differentiation of thymic epithelial tumors from other prevascularmediastinal tumors on chest computed tomography scan［J］. Front Oncol，2023，13：1105100.
8 LIU W， LIU M， GUO X， et al. Evaluation of acute pulmonary embolism and clot burden on CTPA with deep learning［J］. Eur Radiol，2020，30（6）：3567-3575.
9 KONSTANTINIDES S V， MEYER G， BECATTINI C， et al. 2019 ESC Guidelines for the diagnosis and management of acute pulmonary embolism developed in collaboration with the European Respiratory Society （ERS）［J］. Eur Heart J，2020，41（4）：543-603.
10 GLOROT X， BENGIO Y. Understanding the difficulty of training deep feedforward neural networks［J］. JMLR Workshop and Conference Proceedings， 2010， 9：249-256.
11 陆威.CT肺动脉造影对急性肺栓塞严重程度的评估价值［J］.临床放射学杂志，2023，42（7）：1103-1107.
12 黄月薇，陈小菊，黄小华，等. CT肺血管成像右心功能参数评估肺栓塞严重程度的风险因素研究［J］. 实用放射学杂志，2021，37（7）：1060-1064.
13 MANDREKAR J N. Receiver operating characteristic curve in diagnostic test assessment［J］. J Thorac Oncol，2010，5（9）：1315-1316.
14 VENKATESH S K， WANG S C. Central clot score at computed tomography as a predictor of 30-day mortality after acute pulmonary embolism［J］. Ann Acad Med Singap， 2010，39（6）：442-447.
15 FURLAN A， AGHAYEV A， CHANG C C， et al. Short-term mortality in acute pulmonary embolism： clot burden and signs of right heart dysfunction at CT pulmonary angiography［J］. Radiology，2012，265（1）：283-293.
16 张凡涛，罗涛. 中高危急性肺血栓栓塞症患者CTPA检查中Qanadli指数的预后意义［J］. 放射学实践，2020，35（12）：1537-1541.
17 SHEN C， YU N， WEN L， et al. Risk stratification of acute pulmonary embolism based on the clot volume and right ventricular dysfunction on CT pulmonary angiography［J］. Clin Respir J，2019，13（11）：674-682.
18 RODRIGUES A C， GUIMARAES L， GUIMARAES J F， et al. Relationship of clot burden and echocardiographic severity of right ventricular dysfunction after acute pulmonary embolism［J］. Int J Cardiovasc Imaging，2015，31（3）：509-515.
19 杨波，施婷艳，茅杰熙，等. MSCTPA右心功能参数与急性肺栓塞严重程度的相关性分析［J］. 医学影像学杂志， 2023， 33（1）：141-144.
20 ABDELWAHAB H W， ARAFA S， BONDOK K， et al. Relationship between clot burden in pulmonary computed tomography angiography and different parameters of right cardiac dysfunction in acute pulmonary embolism［J］. Cardiovasc J Afr，2020，31（1）：21-24.
Options
Outlines

/

〈 〉