Mini-COVIDNet: Efficient Lightweight Deep Neural Network for Ultrasound Based Point-of-Care Detection of COVID-19

Abstract

Lung ultrasound (US) imaging has the potential to be an effective point-of-care test for detection of COVID-19, due to its ease of operation with minimal personal protection equipment along with easy disinfection. The current state-of-the-art deep learning models for detection of COVID-19 are heavy models that may not be easy to deploy in commonly utilized mobile platforms in point-of-care testing. In this work, we develop a lightweight mobile friendly efficient deep learning model for detection of COVID-19 using lung US images. Three different classes including COVID-19, pneumonia, and healthy were included in this task. The developed network, named as Mini-COVIDNet, was bench-marked with other lightweight neural network models along with state-of-the-art heavy model. It was shown that the proposed network can achieve the highest accuracy of 83.2% and requires a training time of only 24 min. The proposed Mini-COVIDNet has 4.39 times less number of parameters in the network compared to its next best performing network and requires a memory of only 51.29 MB, making the point-of-care detection of COVID-19 using lung US imaging plausible on a mobile platform. Deployment of these lightweight networks on embedded platforms shows that the proposed Mini-COVIDNet is highly versatile and provides optimal performance in terms of being accurate as well as having latency in the same order as other lightweight networks. The developed lightweight models are available at ht. tps://github.com/navchetan-awasthi/Mini-COVIDNet.

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

“…The results indicate that the use of hybrid models (CNN-LSTM) can be effective in learning spatiotemporal features, exceeding the performance of models with purely spatial approaches [ 39 , 129 ] and even human experts [ 62 ]. However, these results should be interpreted with parsimony.…”

“…In [ 39 ], the authors presented an efficient and lightweight network called Mini- COVIDNet based on MobileNets, with a focus on mobile devices. The network was trained on LUS images to classify them into three classes: bacterial pneumonia, COVID-19, and healthy.…”

“…Ultrasound (US) has advantages that can help fight COVID-19, as it is portable, radiation-free, easy to sterilize, has a low acquisition cost, allows the examination to be performed at the bedside, and can be used by the physician without the need to mobilize other professionals [ 38 ]. Moreover, due to the portability and low cost of US equipment, such devices enable rapid prototyping of systems that make intensive use of AI and computer vision (CV) techniques to aid in the diagnosis of COVID-19 [ 39 ]. However, despite the advantages presented in the use of LUS images for the diagnosis of pulmonary pathology and COVID-19, few studies are exploring Deep Learning (DL) techniques compared to the number of studies performed with other medical imaging techniques such as XR and CT [ 21 , 40 , 41 , 42 , 43 ].…”

Deep Learning Applications for COVID-19 Analysis: A State-of-the-Art Survey

“…Born et al [190] developed a frame-based CNN that correctly classifies COVID-19 from LUS datasets. Awasthi et al [191] established Mini-COVIDNet, a light weight deep neural network, based on COVID-19 detection using LUS video. Dastider et al [192] proposed an integrated autoencoder-based hybrid CNN-LSTM model that detects COVID-19 severity scores from LUS images very well.…”

Quantitative Analysis of Pleural Line and B-Lines in Lung Ultrasound Images for Severity Assessment of COVID-19 Pneumonia

“…Characteristics associated with the pleural line and B-lines are not combined to evaluate the lung conditions. Besides, automatic diagnostic systems based on deep learning have shown promises for fast and accurate diagnosis of COVID-19 pneumonia using the quantitative indices extracted from B-lines, the frame-level or video-level ultrasound images, or the combination of the images and clinical information as input [34][35][36][37], but these methods require a large number of annotated samples from patients of COVID-19 pneumonia, which are difficult to obtain.…”