2021
DOI: 10.3390/s21165486
|View full text |Cite
|
Sign up to set email alerts
|

Pulmonary COVID-19: Learning Spatiotemporal Features Combining CNN and LSTM Networks for Lung Ultrasound Video Classification

Abstract: Deep Learning is a very active and important area for building Computer-Aided Diagnosis (CAD) applications. This work aims to present a hybrid model to classify lung ultrasound (LUS) videos captured by convex transducers to diagnose COVID-19. A Convolutional Neural Network (CNN) performed the extraction of spatial features, and the temporal dependence was learned using a Long Short-Term Memory (LSTM). Different types of convolutional architectures were used for feature extraction. The hybrid model (CNN-LSTM) h… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
26
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
9
1

Relationship

0
10

Authors

Journals

citations
Cited by 42 publications
(26 citation statements)
references
References 119 publications
(119 reference statements)
0
26
0
Order By: Relevance
“…As explorations of the role of deep learning in LUS for COVID-19 patients are still underway (e.g., [101][102][103][104]), we believe that in the near future, more research implementing deep learning applications for ultrasound imaging of COVID-19 will be available. These future studies, in combi-nation with the pioneering studies described herein, are expected to provide impactful point-of-care solutions to combat the COVID-19 pandemic.…”
Section: Discussionmentioning
confidence: 99%
“…As explorations of the role of deep learning in LUS for COVID-19 patients are still underway (e.g., [101][102][103][104]), we believe that in the near future, more research implementing deep learning applications for ultrasound imaging of COVID-19 will be available. These future studies, in combi-nation with the pioneering studies described herein, are expected to provide impactful point-of-care solutions to combat the COVID-19 pandemic.…”
Section: Discussionmentioning
confidence: 99%
“…Hybrid DL algorithms combining backbone CNNs with other units such as the long short-term memory (LSTM) were introduced to improve the model performance. Barros et al tailored a hybrid CNN-LSTM model to classify LUS videos by extracting spatial features with CNNs and then learning the temporal dependence via LSTM [ 87 ]. Their hybrid model reached a higher accuracy of 93% and sensitivity of 97% for COVID-19 cases, compared to other primitive spatial-based models.…”
Section: Machine Learning In Covid-19 Lusmentioning
confidence: 99%
“…It was built using MATLAB deep learning toolbox and was built from the ground up. The weights of the CNN and LSTM layers were trained at the same time rather than separately or using via transfer learning as the case in [29]. This will allow us to efficiently optimize the number of layers, filters, and LSTM unit numbers which would not be possible with vanilla CNN networks such as VGG16, GoogleNet, AlexNet…etc.…”
Section: The Cnn-lstm Hybrid Architecturementioning
confidence: 99%