ABSTRACT
Early-stage detection of Coronavirus Disease 2019 (COVID-19) is crucial for patient medical attention. Since lungs are the most affected organs, monitoring them constantly is an effective way to observe sickness evolution. The most common technique for lung-imaging and evaluation is Computed Tomography (CT). However, its costs and effects over human health has made Lung Ultrasound (LUS) a good alternative. LUS does not expose the patient to radiation and minimizes the risk of contamination. Also, there is evidence of a relation between different artifacts on LUS and lung's diseases coming from the pleura, whose abnormalities are related with most acute respiratory disorders. However, LUS often requires an expert clinical interpretation that may increase diagnosis time or decrease diagnosis performance. This paper describes and compares machine learning classification methods namely Naive Bayes (NB) Support Vector Machine (SVM), K-Nearest Neighbor (K-NN) and Random Forest (RF) over several LUS images. They obtain a classification between lung images with COVID-19, pneumonia, and healthy patients, using image's features previously extracted from Gray Level Co-Occurrence Matrix (GLCM) and histogram's statistics. Furthermore, this paper compares the above classic methods with different Convolutional Neural Networks (CNN) that classifies the images in order to identify these lung's diseases.
ABSTRACT
Deep Learning has been used for several applications including the analysis of medical images. Some transfer learning works show that an improvement in performance is obtained if a pre-trained model on ImageNet is transferred to a new task. Taking into account this, we propose a method that uses a pre-trained model on ImageNet to fine-tune it for Covid-19 detection. After the fine-tuning process, the units that produce a variance equal to zero are removed from the model. Finally, we test the features of the penultimate layer in different classifiers removing those that are less important according to the f-test. The results produce models with fewer units than the transferred model. Also, we study the attention of the neural network for classification. Noise and metadata printed in medical images can bias the performance of the neural network and it obtains poor performance when the model is tested on new data. We study the bias of medical images when raw and masked images are used for training deep models using a transfer learning strategy. Additionally, we test the performance on novel data in both models: raw and masked data. Author
ABSTRACT
Early-stage detection of Coronavirus Disease 2019 (COVID-19) is crucial for patient medical attention. Since lungs are the most affected organs, monitoring them constantly is an effective way to observe sickness evolution. The most common technique for lung-imaging and evaluation is Computed Tomography (CT). However, its costs and effects over human health has made Lung Ultrasound (LUS) a good alternative. LUS does not expose the patient to radiation and minimizes the risk of contamination. Also, there is evidence of a relation between different artifacts on LUS and lung’s diseases coming from the pleura, whose abnormalities are related with most acute respiratory disorders. However, LUS often requires an expert clinical interpretation that may increase diagnosis time or decrease diagnosis performance. This paper describes and compares machine learning classification methods namely Naive Bayes (NB) Support Vector Machine (SVM), K-Nearest Neighbor (K-NN) and Random Forest (RF) over several LUS images. They obtain a classification between lung images with COVID-19, pneumonia, and healthy patients, using image’s features previously extracted from Gray Level Co-Occurrence Matrix (GLCM) and histogram’s statistics. Furthermore, this paper compares the above classic methods with different Convolutional Neural Networks (CNN) that classifies the images in order to identify these lung’s diseases. © 2022 SPIE.