ABSTRACT
Deep learning is a convenient method for doctors to classify pulmonary diseases such as COVID-19, viral pneumonia, bacterial pneumonia, and tuberculosis. However, such a task requires a dataset including samples of all these diseases and a more effective network to capture the features of images accurately. In this paper, we propose a five-classification pulmonary disease model, including the pre-processing of input data, feature extraction, and classifier. The main points of this model are as follows. Firstly, we present a new network named RED-CNN which is based on CNN architecture and constructed using the RED block. The RED block is composed of the Res2Net module, ECA module, and Double BlazeBlock module, which are capable of extracting more detailed information, providing cross-channel information, and enhancing the extraction of global information with strong feature extraction capability. Secondly, by merging two selected datasets, the Curated Chest X-Ray Image Dataset for COVID-19 and the tuberculosis (TB) chest X-ray database, we constructed a new dataset including five types of data: normal, COVID-19, viral pneumonia, bacterial pneumonia, and tuberculosis. In order to assess the efficiency of the proposed five-classification model, a series of experiments based on the new dataset were carried out and based on 5-fold cross validation, and the results of the accuracy, precision, recall, F1 value, and Jaccard scores of the proposed method were 91.796%, 92.062%, 91.796%, 91.892%, and 86.176%, respectively. Our proposed algorithm performs better than other classification algorithms.
ABSTRACT
Influenza A, influenza B, severe acute respiratory syndrome coronavirus 2, adenovirus, respiratory syncytial virus, Mycoplasma pneumoniae, and Chlamydophila pneumoniae are common pathogens that can cause severe pneumonia and other symptoms, resulting in acute lower respiratory tract infections. The objective of this study was to design and evaluate a sensitive and specific multiplex one-step reverse transcription PCR (RT-PCR)-dipstick chromatography method for simultaneous rapid detection of these seven pathogens. Streptavidin-coated blue latex particles were used to read out a positive signal. Based on the DNA-DNA hybridization of oligonucleotide sequences (Tag) for forward primer with the complementary oligonucleotide sequence (cTag) on the dipstick and biotin-streptavidin interactions, PCR products were able to be illuminated visually on the dipstick. The specificity and the limit of detection (LOD) were also evaluated. Moreover, the clinical performance of this method was compared with Sanger sequencing for 896 samples. No cross reaction with other pathogens was found, confirming the high specificity of this method. The LOD was 10 copies/µL for each of the tested pathogens, and the whole procedure took less than 40 min. Using 896 samples, the sensitivity and specificity were shown to be no lower than 94.5%. The positive predictive value was higher than 82.1%, and the negative predictive value was higher than 99.5%. The kappa value between the PCR-dipstick chromatography method and Sanger sequencing ranged from 0.869 to 0.940. In summary, our one-step RT-PCR-dipstick chromatography method is a sensitive and specific tool for rapidly detecting multiplex respiratory pathogens.