An efficient mixture of deep and machine learning models for COVID-19 diagnosis in chest X-ray images

Abstract

A newly emerged coronavirus (COVID-19) seriously threatens human life and health worldwide. In coping and fighting against COVID-19, the most critical step is to effectively screen and diagnose infected patients. Among them, chest X-ray imaging technology is a valuable imaging diagnosis method. The use of computer-aided diagnosis to screen X-ray images of COVID-19 cases can provide experts with auxiliary diagnosis suggestions, which can reduce the burden of experts to a certain extent. In this study, we first used conventional transfer learning methods, using five pre-trained deep learning models, which the Xception model showed a relatively ideal effect, and the diagnostic accuracy reached 96.75%. In order to further improve the diagnostic accuracy, we propose an efficient diagnostic method that uses a combination of deep features and machine learning classification. It implements an end-to-end diagnostic model. The proposed method was tested on two datasets and performed exceptionally well on both of them. We first evaluated the model on 1102 chest X-ray images. The experimental results show that the diagnostic accuracy of Xception + SVM is as high as 99.33%. Compared with the baseline Xception model, the diagnostic accuracy is improved by 2.58%. The sensitivity, specificity and AUC of this model reached 99.27%, 99.38% and 99.32%, respectively. To further illustrate the robustness of our method, we also tested our proposed model on another dataset. Finally also achieved good results. Compared with related research, our proposed method has higher classification accuracy and efficient diagnostic performance. Overall, the proposed method substantially advances the current radiology based methodology, it can be very helpful tool for clinical practitioners and radiologists to aid them in diagnosis and follow-up of COVID-19 cases.

COVIDC: An expert system to diagnose COVID-19 and predict its severity using chest CT scans: Application in radiology

“…Most of the machine learning studies involved in COVID-19 diagnosis have used pure deep learning strategies or transfer learning with a customized fully connected layer to be fine-tuned. However, to train deep neural networks from scratch or to fine-tune the parameters of the customized fully connected layers on the top of a pre-trained model, we need an extensive amount of data and high-performance computational resources, which is mostly impractical [ 50 ]. Therefore, we have proposed a different machine learning-based approach for the preliminary diagnosis of COVID-19 and its severity prediction using digital chest CT images.…”

COVID-19 Detection from Chest X-ray Images Using Feature Fusion and Deep Learning

“…Wang et al [ 41 ] have developed a transfer learning method (Xception model) using deep learning models for diagnosing COVID-19. The proposed method showed 96.75% diagnostics accuracy.…”

Convolutional neural network model based on radiological images to support COVID-19 diagnosis: Evaluating database biases

“…Wang et al . [ 42 ] is another example of binary classification with few databases, in addition to the limitation of performing one test analysis adopting images already used in the training phase. Hemdan, Shouman and Karar [ 43 ] used a single database for both classes, but the extremely limited data quantity reduced the generalization of their results.…”

“…These authors evaluated several models also using transfer learning considering one database for COVID-19 and another database for 'no-finding' patients with the former work also presenting the problem of highly unbalanced classes. Wang et al [42] is • Use of DA after train/test split.…”