Quantitative Analysis and Automated Lung Ultrasound Scoring for Evaluating COVID-19 Pneumonia With Neural Networks

被引:21
作者
Chen, Jiangang [1 ]
He, Chao [2 ]
Yin, Jintao [1 ]
Li, Jiawei [3 ]
Duan, Xiaoqian [1 ]
Cao, Yucheng [1 ]
Sun, Li [1 ]
Hu, Menghan [1 ]
Li, Wenfang [2 ]
Li, Qingli [1 ]
机构
[1] East China Normal Univ, Shanghai Key Lab Multidimens Informat Proc, Shanghai 200241, Peoples R China
[2] Naval Med Univ, Changzheng Hosp, Dept Emergency & Crit Care, Shanghai 200433, Peoples R China
[3] Fudan Univ, Shanghai Canc Ctr, Dept Med Ultrasound, Shanghai 200433, Peoples R China
基金
中国国家自然科学基金;
关键词
Automated scoring; COVID-19; pneumonia; lung ultrasound; quantitative analysis; EXTRAVASCULAR LUNG; B-LINES; WATER; CT;
D O I
10.1109/TUFFC.2021.3070696
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
As being radiation-free, portable, and capable of repetitive use, ultrasonography is playing an important role in diagnosing and evaluating the COVID-19 Pneumonia (PN) in this epidemic. By virtue of lung ultrasound scores (LUSS), lung ultrasound (LUS) was used to estimate the excessive lung fluid that is an important clinical manifestation of COVID-19 PN, with high sensitivity and specificity. However, as a qualitative method, LUSS suffered from large interobserver variations and requirement for experienced clinicians. Considering this limitation, we developed a quantitative and automatic lung ultrasound scoring system for evaluating the COVID-19 PN. A total of 1527 ultrasound images prospectively collected from 31 COVID-19 PN patients with different clinical conditions were evaluated and scored with LUSS by experienced clinicians. All images were processed via a series of computer-aided analysis, including curve-to-linear conversion, pleural line detection, region-of-interest (ROI) selection, and feature extraction. A collection of 28 features extracted from the ROI was specifically defined for mimicking the LUSS. Multilayer fully connected neural networks, support vector machines, and decision trees were developed for scoring LUS images using the fivefold cross validation. The model with 128 x 256 two fully connected layers gave the best accuracy of 87%. It is concluded that the proposed method could assess the ultrasound images by assigning LUSS automatically with high accuracy, potentially applicable to the clinics.
引用
收藏
页码:2507 / 2515
页数:9
相关论文
共 38 条
[31]   Lung Ultrasound forCOVID-19 Patchy Pneumonia: Extended or Limited Evaluations? [J].
Smargiassi, Andrea ;
Soldati, Gino ;
Torri, Elena ;
Mento, Federico ;
Milardi, Domenico ;
Del Giacomo, Paola ;
De Matteis, Giuseppe ;
Burzo, Maria Livia ;
Larici, Anna Rita ;
Pompili, Maurizio ;
Demi, Libertario ;
Inchingolo, Riccardo .
JOURNAL OF ULTRASOUND IN MEDICINE, 2021, 40 (03) :521-528
[32]   Proposal for International Standardization of the Use of Lung Ultrasound for Patients With COVID-19 A Simple, Quantitative, Reproducible Method [J].
Soldati, Gino ;
Smargiassi, Andrea ;
Inchingolo, Riccardo ;
Buonsenso, Danilo ;
Perrone, Tiziano ;
Briganti, Domenica Federica ;
Perlini, Stefano ;
Torri, Elena ;
Mariani, Alberto ;
Mossolani, Elisa Eleonora ;
Tursi, Francesco ;
Mento, Federico ;
Demi, Libertario .
JOURNAL OF ULTRASOUND IN MEDICINE, 2020, 39 (07) :1413-1419
[33]   Is There a Role for Lung Ultrasound During the COVID-19 Pandemic? [J].
Soldati, Gino ;
Smargiassi, Andrea ;
Inchingolo, Riccardo ;
Buonsenso, Danilo ;
Perrone, Tiziano ;
Briganti, Domenica Federica ;
Perlini, Stefano ;
Torri, Elena ;
Mariani, Alberto ;
Mossolani, Elisa Eleonora ;
Tursi, Francesco ;
Mento, Federico ;
Demi, Libertario .
JOURNAL OF ULTRASOUND IN MEDICINE, 2020, 39 (07) :1459-1462
[34]   Ultrasound assessment of lung aeration loss during a successful weaning trial predicts postextubation distress [J].
Soummer, Alexis ;
Perbet, Sebastien ;
Brisson, Helene ;
Arbelot, Charlotte ;
Constantin, Jean-Michel ;
Lu, Qin ;
Rouby, Jean-Jacques .
CRITICAL CARE MEDICINE, 2012, 40 (07) :2064-2072
[35]   Localizing B-Lines in Lung Ultrasonography by Weakly Supervised Deep Learning, In-Vivo Results [J].
van Sloun, Ruud J. G. ;
Demi, Libertario .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2020, 24 (04) :957-964
[36]   Estimation of extravascular lung water using the transpulmonary ultrasound dilution (TPUD) method: a validation study in neonatal lambs [J].
Vrancken, S. L. ;
Nusmeier, A. ;
Hopman, J. C. ;
Liem, K. D. ;
van der Hoeven, J. G. ;
Lemson, J. ;
van Heijst, A. F. ;
de Boode, W. P. .
JOURNAL OF CLINICAL MONITORING AND COMPUTING, 2016, 30 (06) :985-994
[37]   Diagnosis and Treatment Protocol for Novel Coronavirus Pneumonia (Trial Version 7) [J].
Wei, Pei-Fang .
CHINESE MEDICAL JOURNAL, 2020, 133 (09) :1087-1095
[38]   Using lung ultrasound to quantitatively evaluate pulmonary water content [J].
Zong, Hai-Feng ;
Guo, Guo ;
Liu, Jing ;
Bao, Lin-Lin ;
Yang, Chuan-Zhong .
PEDIATRIC PULMONOLOGY, 2020, 55 (03) :729-739