Machine Learning Based on Computed Tomography Pulmonary Angiography in Evaluating Pulmonary Artery Pressure in Patients with Pulmonary Hypertension
Background: Right heart catheterization is the gold standard for evaluating hemodynamic parameters of pulmonary circulation, especially pulmonary artery pressure (PAP) for diagnosis of pulmonary hypertension (PH). However, the invasive and costly nature of RHC limits its widespread application in da...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/12/4/1297 |
| _version_ | 1797620296340996096 |
|---|---|
| author | Nan Zhang Xin Zhao Jie Li Liqun Huang Haotian Li Haiyu Feng Marcos A. Garcia Yunshan Cao Zhonghua Sun Senchun Chai |
| author_facet | Nan Zhang Xin Zhao Jie Li Liqun Huang Haotian Li Haiyu Feng Marcos A. Garcia Yunshan Cao Zhonghua Sun Senchun Chai |
| author_sort | Nan Zhang |
| collection | DOAJ |
| description | Background: Right heart catheterization is the gold standard for evaluating hemodynamic parameters of pulmonary circulation, especially pulmonary artery pressure (PAP) for diagnosis of pulmonary hypertension (PH). However, the invasive and costly nature of RHC limits its widespread application in daily practice. Purpose: To develop a fully automatic framework for PAP assessment via machine learning based on computed tomography pulmonary angiography (CTPA). Materials and Methods: A machine learning model was developed to automatically extract morphological features of pulmonary artery and the heart on CTPA cases collected between June 2017 and July 2021 based on a single center experience. Patients with PH received CTPA and RHC examinations within 1 week. The eight substructures of pulmonary artery and heart were automatically segmented through our proposed segmentation framework. Eighty percent of patients were used for the training data set and twenty percent for the independent testing data set. PAP parameters, including mPAP, sPAP, dPAP, and TPR, were defined as ground-truth. A regression model was built to predict PAP parameters and a classification model to separate patients through mPAP and sPAP with cut-off values of 40 mm Hg and 55 mm Hg in PH patients, respectively. The performances of the regression model and the classification model were evaluated by analyzing the intraclass correlation coefficient (ICC) and the area under the receiver operating characteristic curve (AUC). Results: Study participants included 55 patients with PH (men 13; age 47.75 ± 14.87 years). The average dice score for segmentation increased from 87.3% ± 2.9 to 88.2% ± 2.9 through proposed segmentation framework. After features extraction, some of the AI automatic extractions (AAd, RVd, LAd, and RPAd) achieved good consistency with the manual measurements. The differences between them were not statistically significant (t = 1.222, <i>p</i> = 0.227; t = −0.347, <i>p</i> = 0.730; t = 0.484, <i>p</i> = 0.630; t = −0.320, <i>p</i> = 0.750, respectively). The Spearman test was used to find key features which are highly correlated with PAP parameters. Correlations between pulmonary artery pressure and CTPA features show a high correlation between mPAP and LAd, LVd, LAa (r = 0.333, <i>p</i> = 0.012; r = −0.400, <i>p</i> = 0.002; r = −0.208, <i>p</i> = 0.123; r = −0.470, <i>p</i> = 0.000; respectively). The ICC between the output of the regression model and the ground-truth from RHC of mPAP, sPAP, and dPAP were 0.934, 0.903, and 0.981, respectively. The AUC of the receiver operating characteristic curve of the classification model of mPAP and sPAP were 0.911 and 0.833. Conclusions: The proposed machine learning framework on CTPA enables accurate segmentation of pulmonary artery and heart and automatic assessment of the PAP parameters and has the ability to accurately distinguish different PH patients with mPAP and sPAP. Results of this study may provide additional risk stratification indicators in the future with non-invasive CTPA data. |
| first_indexed | 2024-03-11T08:39:09Z |
| format | Article |
| id | doaj.art-e0ad11a2726d4451898eae3c450bdf70 |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-11T08:39:09Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-e0ad11a2726d4451898eae3c450bdf702023-11-16T21:17:35ZengMDPI AGJournal of Clinical Medicine2077-03832023-02-01124129710.3390/jcm12041297Machine Learning Based on Computed Tomography Pulmonary Angiography in Evaluating Pulmonary Artery Pressure in Patients with Pulmonary HypertensionNan Zhang0Xin Zhao1Jie Li2Liqun Huang3Haotian Li4Haiyu Feng5Marcos A. Garcia6Yunshan Cao7Zhonghua Sun8Senchun Chai9Department of Radiology, Beijing Anzhen Hospital, Capital Medical University, 2nd Anzhen Road, Chaoyang District, Beijing 100029, ChinaSchool of Automation, Beijing Institute of Technology, No. 5 Zhongguancun South Street, Haidian District, Beijing 100081, ChinaDepartment of Pulmonary and Critical Care Medicine, Beijing Anzhen Hospital, Capital Medical University, 2nd Anzhen Road, Chaoyang District, Beijing 100029, ChinaSchool of Automation, Beijing Institute of Technology, No. 5 Zhongguancun South Street, Haidian District, Beijing 100081, ChinaSchool of Automation, Beijing Institute of Technology, No. 5 Zhongguancun South Street, Haidian District, Beijing 100081, ChinaSchool of Automation, Beijing Institute of Technology, No. 5 Zhongguancun South Street, Haidian District, Beijing 100081, ChinaSchool of Automation, Beijing Institute of Technology, No. 5 Zhongguancun South Street, Haidian District, Beijing 100081, ChinaDepartment of Cardiology, Gansu Provincial Hospital, No. 204, Donggang West Road, Chengguan District, Lanzhou 730099, ChinaDiscipline of Medical Radiation Science, Curtin Medical School, Curtin University, Perth 6102, AustraliaSchool of Automation, Beijing Institute of Technology, No. 5 Zhongguancun South Street, Haidian District, Beijing 100081, ChinaBackground: Right heart catheterization is the gold standard for evaluating hemodynamic parameters of pulmonary circulation, especially pulmonary artery pressure (PAP) for diagnosis of pulmonary hypertension (PH). However, the invasive and costly nature of RHC limits its widespread application in daily practice. Purpose: To develop a fully automatic framework for PAP assessment via machine learning based on computed tomography pulmonary angiography (CTPA). Materials and Methods: A machine learning model was developed to automatically extract morphological features of pulmonary artery and the heart on CTPA cases collected between June 2017 and July 2021 based on a single center experience. Patients with PH received CTPA and RHC examinations within 1 week. The eight substructures of pulmonary artery and heart were automatically segmented through our proposed segmentation framework. Eighty percent of patients were used for the training data set and twenty percent for the independent testing data set. PAP parameters, including mPAP, sPAP, dPAP, and TPR, were defined as ground-truth. A regression model was built to predict PAP parameters and a classification model to separate patients through mPAP and sPAP with cut-off values of 40 mm Hg and 55 mm Hg in PH patients, respectively. The performances of the regression model and the classification model were evaluated by analyzing the intraclass correlation coefficient (ICC) and the area under the receiver operating characteristic curve (AUC). Results: Study participants included 55 patients with PH (men 13; age 47.75 ± 14.87 years). The average dice score for segmentation increased from 87.3% ± 2.9 to 88.2% ± 2.9 through proposed segmentation framework. After features extraction, some of the AI automatic extractions (AAd, RVd, LAd, and RPAd) achieved good consistency with the manual measurements. The differences between them were not statistically significant (t = 1.222, <i>p</i> = 0.227; t = −0.347, <i>p</i> = 0.730; t = 0.484, <i>p</i> = 0.630; t = −0.320, <i>p</i> = 0.750, respectively). The Spearman test was used to find key features which are highly correlated with PAP parameters. Correlations between pulmonary artery pressure and CTPA features show a high correlation between mPAP and LAd, LVd, LAa (r = 0.333, <i>p</i> = 0.012; r = −0.400, <i>p</i> = 0.002; r = −0.208, <i>p</i> = 0.123; r = −0.470, <i>p</i> = 0.000; respectively). The ICC between the output of the regression model and the ground-truth from RHC of mPAP, sPAP, and dPAP were 0.934, 0.903, and 0.981, respectively. The AUC of the receiver operating characteristic curve of the classification model of mPAP and sPAP were 0.911 and 0.833. Conclusions: The proposed machine learning framework on CTPA enables accurate segmentation of pulmonary artery and heart and automatic assessment of the PAP parameters and has the ability to accurately distinguish different PH patients with mPAP and sPAP. Results of this study may provide additional risk stratification indicators in the future with non-invasive CTPA data.https://www.mdpi.com/2077-0383/12/4/1297artificial intelligencepulmonary hypertensioncomputed tomographyartery pressurediagnosisautomatic assessment |
| spellingShingle | Nan Zhang Xin Zhao Jie Li Liqun Huang Haotian Li Haiyu Feng Marcos A. Garcia Yunshan Cao Zhonghua Sun Senchun Chai Machine Learning Based on Computed Tomography Pulmonary Angiography in Evaluating Pulmonary Artery Pressure in Patients with Pulmonary Hypertension Journal of Clinical Medicine artificial intelligence pulmonary hypertension computed tomography artery pressure diagnosis automatic assessment |
| title | Machine Learning Based on Computed Tomography Pulmonary Angiography in Evaluating Pulmonary Artery Pressure in Patients with Pulmonary Hypertension |
| title_full | Machine Learning Based on Computed Tomography Pulmonary Angiography in Evaluating Pulmonary Artery Pressure in Patients with Pulmonary Hypertension |
| title_fullStr | Machine Learning Based on Computed Tomography Pulmonary Angiography in Evaluating Pulmonary Artery Pressure in Patients with Pulmonary Hypertension |
| title_full_unstemmed | Machine Learning Based on Computed Tomography Pulmonary Angiography in Evaluating Pulmonary Artery Pressure in Patients with Pulmonary Hypertension |
| title_short | Machine Learning Based on Computed Tomography Pulmonary Angiography in Evaluating Pulmonary Artery Pressure in Patients with Pulmonary Hypertension |
| title_sort | machine learning based on computed tomography pulmonary angiography in evaluating pulmonary artery pressure in patients with pulmonary hypertension |
| topic | artificial intelligence pulmonary hypertension computed tomography artery pressure diagnosis automatic assessment |
| url | https://www.mdpi.com/2077-0383/12/4/1297 |
| work_keys_str_mv | AT nanzhang machinelearningbasedoncomputedtomographypulmonaryangiographyinevaluatingpulmonaryarterypressureinpatientswithpulmonaryhypertension AT xinzhao machinelearningbasedoncomputedtomographypulmonaryangiographyinevaluatingpulmonaryarterypressureinpatientswithpulmonaryhypertension AT jieli machinelearningbasedoncomputedtomographypulmonaryangiographyinevaluatingpulmonaryarterypressureinpatientswithpulmonaryhypertension AT liqunhuang machinelearningbasedoncomputedtomographypulmonaryangiographyinevaluatingpulmonaryarterypressureinpatientswithpulmonaryhypertension AT haotianli machinelearningbasedoncomputedtomographypulmonaryangiographyinevaluatingpulmonaryarterypressureinpatientswithpulmonaryhypertension AT haiyufeng machinelearningbasedoncomputedtomographypulmonaryangiographyinevaluatingpulmonaryarterypressureinpatientswithpulmonaryhypertension AT marcosagarcia machinelearningbasedoncomputedtomographypulmonaryangiographyinevaluatingpulmonaryarterypressureinpatientswithpulmonaryhypertension AT yunshancao machinelearningbasedoncomputedtomographypulmonaryangiographyinevaluatingpulmonaryarterypressureinpatientswithpulmonaryhypertension AT zhonghuasun machinelearningbasedoncomputedtomographypulmonaryangiographyinevaluatingpulmonaryarterypressureinpatientswithpulmonaryhypertension AT senchunchai machinelearningbasedoncomputedtomographypulmonaryangiographyinevaluatingpulmonaryarterypressureinpatientswithpulmonaryhypertension |