Automatic Pleural Line Extraction and COVID-19 Scoring From Lung Ultrasound Data

Abstract

Recent works highlighted the significant potential of lung ultrasound (LUS) imaging in the management of subjects affected by COVID-19. In general, the development of objective, fast, and accurate automatic methods for LUS data evaluation is still at an early stage. This is particularly true for COVID-19 diagnostic. In this article, we propose an automatic and unsupervised method for the detection and localization of the pleural line in LUS data based on the hidden Markov model and Viterbi Algorithm. The pleural line localization step is followed by a supervised classification procedure based on the support vector machine (SVM). The classifier evaluates the healthiness level of a patient and, if present, the severity of the pathology, i.e., the score value for each image of a given LUS acquisition. The experiments performed on a variety of LUS data acquired in Italian hospitals with both linear and convex probes highlight the effectiveness of the proposed method. The average overall accuracy in detecting the pleura is 84% and 94% for convex and linear probes, respectively. The accuracy of the SVM classification in correctly evaluating the severity of COVID-19 related pleural line alterations is about 88% and 94% for convex and linear probes, respectively. The results as well as the visualization of the detected pleural line and the predicted score chart, provide a significant support to medical staff for further evaluating the patient condition.

A narrative review on characterization of acute respiratory distress syndrome in COVID-19-infected lungs using artificial intelligence

“… FC-Densenet103, Unet, DenseNet, and DenseNet121-FPN. References References [ 137 ] [ 138 ] [ 139 ] [ 140 ] [ 141 ] [ 142 ] [ 143 ] [ 129 ] [ 144 ] [ 145 ] [ 146 ] [ 147 ] [ 148 ] [ 149 ] [ 150 ] [ 151 ] [ 152 ] [ 153 ] [ 154 ] [ 155 ] [ 156 ] [ 157 ] [ 158 ] [ 159 ] [ 160 ] [ 161 ] [ 162 ] [ 163 ] [ 164 ] [ 165 ] Classification Characteristics Characteristics Gray scale feature extraction and ML classifier, and model-based techniques. Resnet-50, CNN, SVM, ResNet101, VGG16, and VGG19.…”

“… Resnet-50, CNN, SVM, ResNet101, VGG16, and VGG19. References References [ 166 ] [ 167 ] [ 168 ] [ 169 ] [ 170 ] [ 148 ] [ 150 ] [ 151 ] [ 171 ] [ 152 ] [ 153 ] [ 157 ] [ 158 ] [ 159 ] [ 172 ] [ 173 ] [ 174 ] [ 175 ] Joint Segmentation and Classification Characteristics Characteristics They use the same characteristics as adapted by segmentation and classification domain for AI-based Non-ARDS. They use the same characteristics as adapted by segmentation and classification domain for AI-based ARDS.…”

“… They use the same characteristics as adapted by segmentation and classification domain for AI-based ARDS. References References [ 167 ] [ 169 ] [ 170 ] [ 148 ] [ 150 ] [ 151 ] [ 154 ] [ 156 ] [ 157 ] [ 158 ] [ 159 ] [ 162 ] …”

An integrated autoencoder-based hybrid CNN-LSTM model for COVID-19 severity prediction from lung ultrasound

“…Since the ultrasound dataset related to COVID-19 is severely limited and a considerable amount of annotated dataset is still publicly unavailable, very few research results have been reported so far on LUS considering the contemporary studies. Among them, in [ 7 , 17 ], LUS has been employed to detect specific patterns of the disease as well as the disease severity in terms of various scores. In this regard, both deep learning and machine learning techniques are implemented for automatic disease prediction in the current resource-con-strained environment.…”

“…On top of that, they published a subset of the dataset they utilized in the study, comprising a total of 60 videos, among which 58 videos are fully labeled at the frame level. In [ 17 ], an SVM-based classification model is proposed following the automatic localization of the pleural line by the hidden Markov Model and the Viterbi algorithm. Here, the authors utilized the dataset released by [ 7 ] and to deal with the limitation of available data, they limited the study on hospital-specific cases and deployed a machine learning model.…”