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

Abstract

As SARS-CoV-2 has spread quickly throughout the world, the scientific community has spent major efforts on better understanding the characteristics of the virus and possible means to prevent, diagnose, and treat COVID-19. A valid approach presented in the literature is to develop an image-based method to support COVID-19 diagnosis using convolutional neural networks (CNN). Because the availability of radiological data is rather limited due to the novelty of COVID-19, several methodologies consider reduced datasets, which may be inadequate, biasing the model. Here, we performed an analysis combining six different databases using chest X-ray images from open datasets to distinguish images of infected patients while differentiating COVID-19 and pneumonia from ‘no-findings’ images. In addition, the performance of models created from fewer databases, which may imperceptibly overestimate their results, is discussed. Two CNN-based architectures were created to process images of different sizes (512 × 512, 768 × 768, 1024 × 1024, and 1536 × 1536). Our best model achieved a balanced accuracy (BA) of 87.7% in predicting one of the three classes (‘no-findings’, ‘COVID-19’, and ‘pneumonia’) and a specific balanced precision of 97.0% for ‘COVID-19’ class. We also provided binary classification with a precision of 91.0% for detection of sick patients (i.e., with COVID-19 or pneumonia) and 98.4% for COVID-19 detection (i.e., differentiating from ‘no-findings’ or ‘pneumonia’). Indeed, despite we achieved an unrealistic 97.2% BA performance for one specific case, the proposed methodology of using multiple databases achieved better and less inflated results than from models with specific image datasets for training. Thus, this framework is promising for a low-cost, fast, and noninvasive means to support the diagnosis of COVID-19.

Hybrid Deep‐Learning and Machine‐Learning Models for Predicting COVID‐19

“…They added some ultrasound images to their data set and argued that their models could be used for quick detection of COVID-19. Maior et al [ 11 ] discussed the effect of limited X-ray images for COVID-19 detection. They tried to resolve this problem by combining different data sets and used them for testing CNN models.…”

“…A lack of availability of many pictures of COVID-19 patients has made detailed studies about solutions for automatic detection of COVID-19 from X-ray (or chest CT) images rare. Moreover, labeling such images for deep-learning (DL) applications is not an easy job and seems expensive [ 10 , 11 ]. Small data sets of COVID-19 X-ray images have been announced for AI researchers to train machine-learning (ML) models to perform automatic COVID-19 diagnoses from X-ray images [ 12 ].…”

A Novel Weighted Consensus Machine Learning Model for COVID-19 Infection Classification Using CT Scan Images

“…Maior et al [38] performed an analysis on chest X-ray images combining six different databases from open datasets to determine images of infected patients while distinguishing COVID-19 and pneumonia from 'no-findings' images. Saba et al [39] proposed six models for the tissue characterization and classification of COVID-19 with pneumonia and achieved better results.…”

Redes Neurais Convolucionais para Classificação da COVID-19 em Imagens de Raio-x de Tórax

“…O aprendizado de máquina (ML -Machine Learning) faz parte da grande área da Inteligência Artificial, dentro dele têm-se o aprendizado profundo (DL -Deep Learning) com o propósito de automatizar a identificac ¸ão de padrões significativos nos dados, e desse modo, resolver problemas por meio de algoritmos. As Redes Neurais Convolucionais se enquadram nas técnicas de DL e são amplamente utilizadas em tarefas de reconhecimento de padrões de imagens, por apresentarem como característica a aptidão superior de aprendizagem de recursos [16].…”