A Novel Lightweight Approach to COVID-19 Diagnostics Based on Chest X-ray Images

Abstract

Background: This paper presents a novel lightweight approach based on machine learning methods supporting COVID-19 diagnostics based on X-ray images. The presented schema offers effective and quick diagnosis of COVID-19. Methods: Real data (X-ray images) from hospital patients were used in this study. All labels, namely those that were COVID-19 positive and negative, were confirmed by a PCR test. Feature extraction was performed using a convolutional neural network, and the subsequent classification of samples used Random Forest, XGBoost, LightGBM and CatBoost. Results: The LightGBM model was the most effective in classifying patients on the basis of features extracted from X-ray images, with an accuracy of 1.00, a precision of 1.00, a recall of 1.00 and an F1-score of 1.00. Conclusion: The proposed schema can potentially be used as a support for radiologists to improve the diagnostic process. The presented approach is efficient and fast. Moreover, it is not excessively complex computationally.

Influence of augmentation on the performance of double ResNet-based model for chest X-rays classification

“…The method was evaluated on a pre-prepared hospital dataset available at https://github.com/UTP-WTIiE/Xray_data.git and previously described and used in [ 9 ]. Images from this dataset are anonymized, realistic data.…”

“…The images were provided in a raw form, without masks. The dataset was introduced and described in [ 9 ]. Each model in this research was evaluated using 4 validation metrics as follows: accuracy ( Eq.…”

Advances in Musculoskeletal Imaging and Their Applications

“…Study [30] introduces an innovative and lightweight machine learning-based approach aimed at facilitating the diagnosis of COVID-19 through the analysis of X-ray images. The proposed method offers a rapid and effective means of diagnosing COVID-19 based on medical imaging.…”

Distributed Red Fox Optimized CatBoost Algorithm for Medical Anomaly Detection

“…CatBoost [7] is a gradient boosting decision tree (GBDT) variant that is highly scalable and robust for medical anomaly detection and capable of handling a wide range of medical data features to improve detection accuracy and efficiency. Empirical studies have shown that CatBoost exhibits higher accuracy and a lower false alarm rate than other algorithms in arrhythmia detection and lung X-ray image lesion detection and is able to quickly and accurately identify new crown lesions [8] .…”