Revisiting Transfer Learning Method for Tuberculosis Diagnosis.

Transfer learning (TL) has been proven to be a good strategy for solving domain-specific problems in many deep learning (DL) applications. Typically, in TL, a pre-trained DL model is used as a feature extractor and the extracted features are then fed to a newly trained classifier as the model head. In this study, we propose a new ensemble approach of transfer learning that uses multiple neural network classifiers at once in the model head. We compared the classification results of the proposed ensemble approach with the direct approach of several popular models, namely VGG-16, ResNet-50, and MobileNet, on two publicly available tuberculosis datasets, i.e., Montgomery County (MC) and Shenzhen (SZ) datasets. Moreover, we also compared the results when a fully pre-trained DL model was used for feature extraction versus the cases in which the features were obtained from a middle layer of the pre-trained DL model. Several metrics derived from confusion matrix results were used, namely the accuracy (ACC), sensitivity (SNS), specificity (SPC), precision (PRC), and F1-score. We concluded that the proposed ensemble approach outperformed the direct approach. Best result was achieved by ResNet-50 when the features were extracted from a middle layer with an accuracy of 91.2698% on MC dataset.Clinical Relevance- The proposed ensemble approach could increase the detection accuracy of 7-8% for Montgomery County dataset and 4-5% for Shenzhen dataset.

Machine and Deep Learning for Tuberculosis Detection on Chest X-Rays: Systematic Literature Review.

BACKGROUND: Tuberculosis (TB) was the leading infectious cause of mortality globally prior to COVID-19 and chest radiography has an important role in the detection, and subsequent diagnosis, of patients with this disease. The conventional experts reading has substantial within- and between-observer variability, indicating poor reliability of human readers. Substantial efforts have been made in utilizing various artificial intelligence-based algorithms to address the limitations of human reading of chest radiographs for diagnosing TB. OBJECTIVE: This systematic literature review (SLR) aims to assess the performance of machine learning (ML) and deep learning (DL) in the detection of TB using chest radiography (chest x-ray [CXR]). METHODS: In conducting and reporting the SLR, we followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. A total of 309 records were identified from Scopus, PubMed, and IEEE (Institute of Electrical and Electronics Engineers) databases. We independently screened, reviewed, and assessed all available records and included 47 studies that met the inclusion criteria in this SLR. We also performed the risk of bias assessment using Quality Assessment of Diagnostic Accuracy Studies version 2 (QUADAS-2) and meta-analysis of 10 included studies that provided confusion matrix results. RESULTS: Various CXR data sets have been used in the included studies, with 2 of the most popular ones being Montgomery County (n=29) and Shenzhen (n=36) data sets. DL (n=34) was more commonly used than ML (n=7) in the included studies. Most studies used human radiologist's report as the reference standard. Support vector machine (n=5), k-nearest neighbors (n=3), and random forest (n=2) were the most popular ML approaches. Meanwhile, convolutional neural networks were the most commonly used DL techniques, with the 4 most popular applications being ResNet-50 (n=11), VGG-16 (n=8), VGG-19 (n=7), and AlexNet (n=6). Four performance metrics were popularly used, namely, accuracy (n=35), area under the curve (AUC; n=34), sensitivity (n=27), and specificity (n=23). In terms of the performance results, ML showed higher accuracy (mean ~93.71%) and sensitivity (mean ~92.55%), while on average DL models achieved better AUC (mean ~92.12%) and specificity (mean ~91.54%). Based on data from 10 studies that provided confusion matrix results, we estimated the pooled sensitivity and specificity of ML and DL methods to be 0.9857 (95% CI 0.9477-1.00) and 0.9805 (95% CI 0.9255-1.00), respectively. From the risk of bias assessment, 17 studies were regarded as having unclear risks for the reference standard aspect and 6 studies were regarded as having unclear risks for the flow and timing aspect. Only 2 included studies had built applications based on the proposed solutions. CONCLUSIONS: Findings from this SLR confirm the high potential of both ML and DL for TB detection using CXR. Future studies need to pay a close attention on 2 aspects of risk of bias, namely, the reference standard and the flow and timing aspects. TRIAL REGISTRATION: PROSPERO CRD42021277155; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=277155.

The role of the mass vaccination programme in combating the COVID-19 pandemic: An LSTM-based analysis of COVID-19 confirmed cases.

The COVID-19 virus has impacted all facets of our lives. As a global response to this threat, vaccination programmes have been initiated and administered in numerous nations. The question remains, however, as to whether mass vaccination programmes result in a decrease in the number of confirmed COVID-19 cases. In this study, we aim to predict the future number of COVID-19 confirmed cases for the top ten countries with the highest number of vaccinations in the world. A well-known Deep Learning method for time series analysis, namely, the Long Short-Term Memory (LSTM) networks, is applied as the prediction method. Using three evaluation metrics, i.e., Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE), we found that the model built by using LSTM networks could give a good prediction of the future number and trend of COVID-19 confirmed cases in the considered countries. Two different scenarios are employed, namely: 'All Time', which includes all historical data; and 'Before Vaccination', which excludes data collected after the mass vaccination programme began. The average MAPE scores for the 'All Time' and 'Before Vaccination' scenarios are 5.977% and 10.388%, respectively. Overall, the results show that the mass vaccination programme has a positive impact on decreasing and controlling the spread of the COVID-19 disease in those countries, as evidenced by decreasing future trends after the programme was implemented.

Images with hidden information data set for information retrieval usage.

The main task in Optical Character Recognition (OCR) is to get and convert all the text characters on an image as a plain text data. However, if the image has low contrast and low exposure, an issue may occur. The characters may be hidden and can't be recovered completely. One solution that has been done and reported in 2017 is by applying histogram equalization as a pre-processing step in OCR. Here, we deliver a total of 30 sample data, some of which had been used on the research's experiment reported in 2017, and some others were added later.