Comparative Study for Tuberculosis Detection by Using Deep Learning

Background: Tuberculosis (TB) is a bacterial disease that mainly affects the lungs, but it can also impact other parts of the body, such as the brain, bones, and kidneys. The disease is caused by a bacterium called Mycobacterium tuberculosis and spreads through the air when an infected person coughs or sneezes. TB can be inactive or active; in its active state, noticeable symptoms appear, and it can be transmitted to others. There are ongoing challenges in fighting TB, including resistance to medications, co-infections, and limited resources in areas heavily affected by the disease. These issues make it challenging to eradicate TB. Objective: Timely and precise diagnosis is essential for effective control, especially since TB often goes undetected and untreated, particularly in remote and under-resourced locations. Chest X-ray (CXR) images are commonly used to diagnose TB. However, difficulties can arise due to unusual findings on X-rays and a shortage of radiologists in high-infection areas. Method: To address these challenges, a computer-aided diagnosis (CAD) system that uses the vision transformer (ViT) technique has been developed to accurately identify TB in CXR images. This innovative hybrid CAD approach combines ViT with Principal Component Analysis (PCA) and machine learning (ML) techniques for TB classification, introducing a new method in this field. In the hybrid CAD system, ViT is used for deep feature extraction as a base model, PCA is used to reduce feature dimensions, and various ML methods are used to classify TB. This system allows for quickly identifying TB, enabling timely medical action and improving patient outcomes. Additionally, it streamlines the diagnostic process, reducing time and costs for patients and lessening the workload on healthcare professionals. The TB chest X-ray dataset was utilized to train and evaluate the proposed CAD system, which underwent pre-processing techniques like resizing, scaling, and noise removal to improve diagnostic accuracy. Results: The performance of our CAD model was assessed against existing models, yielding excellent results. The model achieved remarkable metrics: an average precision of 99.90%, recall of 99.52%, F1-score of 99.71%, accuracy of 99.84%, false negative rate (FNR) of 0.48%, specificity of 99.52%, and negative predictive value (NPV) of 99.90%. Conclusions: This evaluation highlights the superior performance of our model compared to the latest available classifiers.

Tuberculosis (TB) is one of the most common diseases in developing countries such as Indonesia. TB disease oftenly attacks the human lungs due to its high oxygen pressure. The basic characteristics of TB-infected lungs are in the form of wounds, which change its texture and shape. The common detection method is by comparing the X-ray thoracic image with the tuberculin skin test (TST) and fast acid staining methods. This diagnosis method is often constrained by the availability of radiologists in the health facilities. To overcome such situation, a computer-aided diagnosis (CAD) tool is required to assist the doctor read the X-ray images easily. In this paper, a complementary detection method is proposed by using a chest X-ray (CXR) image to assist the diagnosis process. In current method, the image is segmented to reduce unnecessary parts prior to preprocessing step. We use a texture-based feature approach for detection purpose because most of the common examination methods for abnormality detection on CXRs is by analyzing the change of textural (content) CXR. In our texture approach, we use texture-based statistical properties on the histogram’s intensity. Some features that are used in this approach including Mean, Standard Deviation, Smoothness, Entropy, Root Mean Square (RMS), Variance, Kurtosis, Skewness, and Inverse Difference Moment (IDM). As a result of simulation, it indicates that CXR images can be well segmented to localize the focus area, allowing to the features can be extracted from the CXR image for further detection process. The obtained accuracy is about 93.94% and 92.86%, respectively for Shenzhen-Chest X-ray dataset and Montgomery County-Chest X-ray dataset.

PurposeTuberculosis (TB) is a severe bacterial infectious lung disease. Millions of people die or experience severe health complications due to TB each year. Accurate, automated, and effective detection of TB is key to curing and preventing person-to-person transmission. In this regard, deep learning (DL) and machine learning (ML) techniques applied to chest X-ray (CXR) images have proved effective. Here, we present our DL- and ML-based approach for TB detection using CXR images.Material and methodsWe implemented convolutional neural network (CNN)-based pre-trained DL models, such as DenseNet121, DenseNet169, DenseNet201, ResNet152, and VGG19, as feature extractors. ML models, including support vector machine (SVM), XGBoost, logistic regression, and a DL-based custom model, were used as classifiers. A total of 2,391 CXR images from three publicly available datasets were considered.ResultsWe found three models achieving the highest value in different evaluation metrics: accuracy (99.91%) with ResNet152 and SVM; recall (99.22%), precision (99.23%), and F1-score (99.22%) with DenseNet169 and the custom classifier; and area under the curve (99.99%) with DenseNet201 and the custom classifier. Among these models, we propose DenseNet169 with the custom classifier as the best performer for potential clinical application, as it reflected a high and well-balanced performance across all evaluation metrics.ConclusionsThis study evaluated pre-trained CNN-based DL and ML models on pre-processed CXR images for the detection of TB. The DenseNet169 model with a custom classifier stands out with its high and well-balanced performance, offering a significant contribution to the effective and automated detection of TB.

Tuberculosis(TBC) remains a major global health issue, with millions of new cases reported annually. Early and accurate diagnosis is essential, but manual interpretation of chest X-ray(CXR) images is limited by subjectivity and resource constrains. This study applies the MobileNetV2 architecture using transfer learning to classify tuberculosis from CXR images. The publicly available Tuberculosis Chest X-ray dataset containing 4200 images was divided into training (70%), validation (15%), and testing (15%). The pretrained MobileNetV2 model on ImageNet was used as the base network, with additional classification layers and training through the Adam optimizer and early stopping. The model achieved a validation accuracy above 99.84% after the second epoch maintained stable performance. Once the test set, model reached 99.84% accuracy, with precision 99.53% and recall 99.90% for the tuberculosis class. The result demonstrate that the transfer learning with MobileNetV2 provides a fast, efficient, and highly accurate method for tuberculosis detection. This model show potential for integration into Computer-Aided Diagnosis (CAD) system in low resource clinical settings.

Background Machine learning (ML) algorithm support vector machine (SVM) performed better than Thrombolysis in Myocardial Infarction (TIMI) score for ASIAN STEMI patients. However, Deep Learning (DL) effectiveness in the multiethnic ASIAN population has yet to be determined. DL has automatic learning of the feature from a given dataset without the need to conduct feature selection. However, the selected features by the algorithm is black box. Identifying features associated with mortality is essential to recognize characteristics of patients with high risk for better patient management. Purpose To develop a DL algorithm for in-hospital mortality in multiethnic STEMI patients using predictors identified from the SVM algorithm. To investigate DL performance constructed using predictors from SVM feature extraction and expert-recommended predictors. Methods We constructed four algorithms; a) DL and SVM algorithms with predictors identified from the SVM variable importance b) DL and SVM using predictors based on expert recommendation. We used registry data from the National Cardiovascular Disease Database of 11397 patient's. Fifty parameters including demographics, cardiovascular risk, medications and clinical variables were considered. The Area under the curve (AUC) is the performance evaluation metric. Algorithms were validated against the TIMI and tested using the same validation data. SVM variable importance with backward elimination was used to select and rank important variables. Results DL algorithms outperform SVM and TIMI on the validation dataset; i) DL with SVM selected predictors (15 predictors, AUC = 0.97), ii) DL with expert-recommended predictors (16 predictors, AUC = 0.96), iii) SVM with selected predictors (15 predictors, AUC = 0.92), iv) SVM with expert-recommended predictors (AUC = 0.89) and TIMI (AUC = 0.82). Common predictors across SVM feature selection, expert-recommendation and TIMI are: age, heart rate, Killip class, fasting blood glucose, systolic blood pressure, comorbid diseases and ST-elevation. SVM feature selection also identified diuretics, PCI and pharmacotherapy drugs as predictors that improve mortality prediction in STEMI patients. Our findings suggest that the TIMI score underestimates patients risk of mortality. DL algorithm using selected predictors classified 35% of nonsurvival patients as high risk (risk probabilities >50%) compared to only 12.7% nonsurvival patients by TIMI (score >5) (Figure below). Conclusions In the ASIAN population, patients with STEMI can be better classified using the DL algorithm compared to the ML and TIMI score. Combining ML feature selection with DL allows the identification of distinct factors in a unique ASIAN population for better mortality prediction than relying solely on an expert recommendation as it is a very subjective approach. Continuous validation on population-specific algorithms using DL and ML is needed before implementing in a real clinical setting. Funding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Technology Development Fund 1 TIMI performance on validation setDL performance on validation set

BackgroundMachine learning (ML) algorithm support vector machine (SVM) performed better than Thrombolysis in Myocardial Infarction (TIMI) score for ASIAN STEMI patients. However, Deep Learning (DL) effectiveness in the multiethnic ASIAN population has yet to be determined. DL has automatic learning of the feature from a given dataset without the need to conduct feature selection. However, the selected features by the algorithm is black box. Identifying features associated with mortality is essential to recognize characteristics of patients with high risk for better patient management.PurposeTo develop a DL algorithm for in-hospital mortality in multiethnic STEMI patients using predictors identified from the SVM algorithm. To investigate DL performance constructed using predictors from SVM feature extraction and expert-recommended predictors.MethodsWe constructed four algorithms; a) DL and SVM algorithms with predictors identified from the SVM variable importance b) DL and SVM using predictors based on expert recommendation. We used registry data from the National Cardiovascular Disease Database of 11397 patient's. Fifty parameters including demographics, cardiovascular risk, medications and clinical variables were considered. The Area under the curve (AUC) is the performance evaluation metric. Algorithms were validated against the TIMI and tested using the same validation data. SVM variable importance with backward elimination was used to select and rank important variables.ResultsDL algorithms outperform SVM and TIMI on the validation dataset; i) DL with SVM selected predictors (15 predictors, AUC = 0.97), ii) DL with expert-recommended predictors (16 predictors, AUC = 0.96), iii) SVM with selected predictors (15 predictors, AUC = 0.92), iv) SVM with expert-recommended predictors (AUC = 0.89) and TIMI (AUC = 0.82). Common predictors across SVM feature selection, expert-recommendation and TIMI are: age, heart rate, Killip class, fasting blood glucose, systolic blood pressure, comorbid diseases and ST-elevation. SVM feature selection also identified diuretics, PCI and pharmacotherapy drugs as predictors that improve mortality prediction in STEMI patients. Our findings suggest that the TIMI score underestimates patients risk of mortality. DL algorithm using selected predictors classified 35% of nonsurvival patients as high risk (risk probabilities >50%) compared to only 12.7% nonsurvival patients by TIMI (score >5) (Figure below).ConclusionsIn the ASIAN population, patients with STEMI can be better classified using the DL algorithm compared to the ML and TIMI score. Combining ML feature selection with DL allows the identification of distinct factors in a unique ASIAN population for better mortality prediction than relying solely on an expert recommendation as it is a very subjective approach. Continuous validation on population-specific algorithms using DL and ML is needed before implementing in a real clinical setting.Funding AcknowledgementType of funding sources: Public grant(s) – National budget only. Main funding source(s): Technology Development Fund 1TIMI performance on validation setDL performance on validation set

Purpose: Evaluation of the performance of a computer-aided diagnosis (CAD) system based on the quantified color distribution in strain elastography imaging to evaluate the malignancy of breast tumors. Methods: The database consisted of 31 malignant and 52 benign lesions. A radiologist who was blinded to the diagnosis performed the visual analysis of the lesions. After six months with no eye contact on the breast images, the same radiologist and other two radiologists manually drew the contour of the lesions in B-mode ultrasound, which was masked in the elastography image. In order to measure the amount of hard tissue in a lesion, we developed a CAD system able to identify the amount of hard tissue, represented by red color, and quantify its predominance in a lesion, allowing classification as soft, intermediate, or hard. The data obtained with the CAD system were compared with the visual analysis. We calculated the sensitivity, specificity, and area under the curve (AUC) for the classification using the CAD system from the manual delineation of the contour by each radiologist. Results: The performance of the CAD system for the most experienced radiologist achieved sensitivity of 70.97%, specificity of 88.46%, and AUC of 0.853. The system presented better performance compared with his visual diagnosis, whose sensitivity, specificity, and AUC were 61.29%, 88.46%, and 0.829, respectively. The system obtained sensitivity, specificity, and AUC of 67.70%, 84.60%, and 0.783, respectively, for images segmented by Radiologist 2, and 51.60%, 92.30%, and 0.771, respectively, for those segmented by the Resident. The intra-class correlation coefficient was 0.748. The inter-observer agreement of the CAD system with the different contours was good in all comparisons. Conclusions: The proposed CAD system can improve the radiologist performance for classifying breast masses, with excellent inter-observer agreement. It could be a promising tool for clinical use.

The world is witnessing an unprecedented catastrophe as a result of the COVID-19 (Coronavirus Disease) epidemic, which has spread to approximately 216 nations and territories throughout the globe. A COVID-19 infection may progress to pneumonia, which can be diagnosed by CXR (Chest X-Ray) examination and should be treated as soon as possible after diagnosis. This work is intended to examine the use of Artificial Intelligence (AI) in speedy & precise diagnosis of COVID-19 pneumonia utilizing digital CXR pictures, as well as to construct a robust computer-aided application for automated classification of COVID-19 pneumonia from other pneumonia as well as normal images. In this research, we use a standard machine learning (ML) technique that is effective. The SVM (Support Vector Machine) classification technique was used in the development of the model. The purpose of this research has been to determine the role of machine learning, image processing, image segmentation, and feature extraction in fast or accurate identification of COVID19 chest X-ray or CT images. We assessed the performance of ML techniques on chest X-ray pictures as well as CT scans to COVID-19 diagnosis in this paper. The model's performance was assessed using relevant classification measures, such as accuracy, precision, recall, & F1 score, among others. The model is capable of identifying COVID-19 patients from CXRs with training accuracy of 100 percent. We believe this high-accuracy & reasonably fast Computer-Aided Diagnosis (CAD) technique might be extremely beneficial in the containment of the pandemic.

Deep learning has emerged as a promising technique for a variety of elements of infectious disease monitoring and detection, including tuberculosis. We built a deep convolutional neural network (CNN) model to assess the generalizability of the deep learning model using a publicly accessible tuberculosis dataset. This study was able to reliably detect tuberculosis (TB) from chest X-ray images by utilizing image preprocessing, data augmentation, and deep learning classification techniques. Four distinct deep CNNs (Xception, InceptionV3, InceptionResNetV2, and MobileNetV2) were trained, validated, and evaluated for the classification of tuberculosis and nontuberculosis cases using transfer learning from their pretrained starting weights. With an F1-score of 99 percent, InceptionResNetV2 had the highest accuracy. This research is more accurate than earlier published work. Additionally, it outperforms all other models in terms of reliability. The suggested approach, with its state-of-the-art performance, may be helpful for computer-assisted rapid TB detection.

目的 基于计算机的胸腔X线影像疾病检测和分类目前存在误诊率高，准确率低的问题。本文在视觉Transformer（vision Transformer，ViT）预训练模型的基础上，通过迁移学习方法，实现胸腔X线影像辅助诊断，提高诊断准确率和效率。方法 选用带有卷积神经网络（convolutional neural network，CNN）的ViT模型，其在超大规模自然图像数据集中进行了预训练；通过微调模型结构，使用预训练的ViT模型参数初始化主干网络，并迁移至胸腔X线影像数据集中再次训练，实现疾病多标签分类。结果 在IU X-Ray数据集中对ViT迁移学习前、后模型平均AUC（area under ROC curve）得分进行对比分析实验。结果表明，预训练ViT模型平均AUC得分为0.774，与不使用迁移学习相比提升了0.208。并针对模型结构和数据预处理进行了消融实验，对ViT中的注意力机制进行可视化，进一步验证了模型有效性。最后使用Chest X-Ray14和CheXpert数据集训练微调后的ViT模型，平均AUC得分为0.839和0.806，与对比方法相比分别有0.014～0.031的提升。结论 与其他方法相比，ViT模型胸腔X线影像的多标签分类精确度更高，且迁移学习可以在降低训练成本的同时提升ViT模型的分类性能和泛化性。消融实验与模型可视化表明，包含CNN结构的ViT模型能重点关注有意义的区域，高效获取胸腔X线影像的视觉特征。;Objective The chest X-ray-relevant screening and diagnostic method is essential for radiology nowadays. Most of chest X-ray images interpretation is still restricted by clinical experience and challenged for misdiagnose and missed diagnoses. To detect and identify one or more potential diseases in images automatically，it is beneficial for improving diagnostic efficiency and accuracy using computer-based technique. Compared to natural images，multiple lesions are challenged to be detected and distinguished accurately in a single image because abnormal areas have a small proportion and complex representations in chest X-ray images. Current convolutional neural network（CNN）based deep learning models have been widely used in the context of medical imaging. The structure of the CNN convolution kernel has sensitive to local detail information，and it is possible to extract richer image features. However，the convolution kernel cannot be used to get global information，and the features-extracted are restricted of redundant information like its relevance of background， muscles，and bones. The model’s performance in multi-label classification tasks are affected to a certain extent. At present，the vision Transformer（ViT）model has achieved its priorities in computer vision-related tasks. The ViT can be used to capture information simultaneously and effectively for multiple regions of the entire image. However，it is required to use large-scale dataset training to achieve good performance. Due to some factors like patient privacy and manual annotate costs，the size of the chest X-ray image data set has been limited. To reduce the model's dependence on data scale and improve the performance of multi-label classification，we develop the CNN-based ViT pre-training model in terms of the transfer learning method for diagnosis-assisted of chest X-ray image and multi-label classification. Method The CNN-based ViT model is pre-trained on a huge scale ground truth dataset，and it is used to obtain the initial parameters of the model. The model structure is fine-tuned according to the features of chest X-ray dataset. A 1×1 convolution layer is used to convert the chest X-ray images channels between 1 to 3. The number of output nodes of the linear layer in the classifier is balanced from 1 000 to the number of chest X-ray classification labels，and the Sigmoid is used as an activation function. The parameters of the backbone network are initialized in terms of the pre-trained ViT model parameters，and it is trained in the chest X-ray dataset after that to complete multi-label classification. The experiment is configured of Python3. 7 and PyTorch1. 8 to construct the model and RTX3090 GPU for training. Stochastic gradient descent（SGD）optimizer，binary cross-entropy（BCE）loss function，an initial learning rate of 1E-3，the cosine annealing learning rate decay are used. For training，each image is scaled to a size of 512×512 pixels，and a 224×224 pixels area and it is then cropped in random as the model input，and data augmentation is performed randomly by some of the flipping，perspective transformation， shearing，translation，zooming，and changing brightness. For testing，the chest X-ray image is scaled to 256×256 pixels and center crop a 224×224 area to input the trained model. Result The experiment is performed on the IU X-Ray，which is a small-scale chest X-ray dataset. This model is evaluated in quantitative using the average of area under ROC curve （AUC）scores across all classification labels. The results show that the average AUC score of the pre-trained ViT model is 0. 774. The accuracy and training efficiency of the non-pre-trained ViT model is dropped significantly. The average AUC score is reached to 0. 566 only，which is 0. 208 lower. In addition，the attention mechanism heat map is generated based on the ViT model，which can strengthen the interpretability of the model. A series of ablation experiments are carried out for data augmentation，model structure，and batch size design. The fine-tuned ViT model is trained on the Chest-Ray14 and CheXpert dataset as well. The average AUC score is reached to 0. 839 and 0. 806，which is optimized by 0. 014 and 0. 031. Conclusion A pre-trained ViT model is used for the multi-label classification of chest X-ray images via transfer learning. The experimental results illustrate that the ViT has its stronger multi-label classification performance in chest Xray images，and its attention mechanism is beneficial for lesions precision-focused like the interior of the chest cavity and the heart. Transfer learning is potential to improve the classification performance and model generalization of the ViT in small-scale datasets，and the training cost is reduced greatly. Ablation experiments demonstrate that the incorporated model of CNN and Transformer has its priority beyond single-structure model. Data enhancement and the batch size cutting can improve the performance of the model，but smaller scale of batch is still interlinked to longer training span. To improve the model's ability，we predict that future research direction can be focused on the extraction for complex disease and highlevel semantic information，such as their small lesions，disease location，and severity.

Hepatic cystic echinococcosis (HCE), a life-threatening liver disease, has 5 subtypes, i.e., single-cystic, polycystic, internal capsule collapse, solid mass, and calcified subtypes. And each subtype has different treatment methods. An accurate diagnosis is the prerequisite for effective HCE treatment. However, clinicians with less diagnostic experience often make misdiagnoses of HCE and confuse its 5 subtypes in clinical practice. Computer-aided diagnosis (CAD) techniques can help clinicians to improve their diagnostic performance. This paper aims to propose an efficient CAD system that automatically differentiates 5 subtypes of HCE from the ultrasound images. The proposed CAD system adopts the concept of deep transfer learning and uses a pre-trained convolutional neural network (CNN) named VGG19 to extract deep CNN features from the ultrasound images. The proven classifier models, k - nearest neighbor (KNN) and support vecter machine (SVM) models, are integrated to classify the extracted deep CNN features. 3 distinct experiments with the same deep CNN features but different classifier models (softmax, KNN, SVM) are performed. The experiments followed 10 runs of the five-fold cross-validation process on a total of 1820 ultrasound images and the results were compared using Wilcoxon signed-rank test. The overall classification accuracy from low to high was 90.46 ± 1.59% for KNN classifier, 90.92 ± 2.49% for transfer learned VGG19, and 92.01 ± 1.48% for SVM, indicating SVM classifiers with deep CNN features achieved the best performance (P < 0.05). Other performance measures used in the study are specificity, sensitivity, precision, F1-score, and area under the curve (AUC). In addition, the paper addresses a practical aspect by evaluating the system with smaller training data to demonstrate the capability of the proposed classification system. The observations of the study imply that transfer learning is a useful technique when the availability of medical images is limited. The proposed classification system by using deep CNN features and SVM classifier is potentially helpful for clinicians to improve their HCE diagnostic performance in clinical practice.

Handwriting analysis is useful in a wide range of applications such as medical diagnostics. Artificial Intelligence (AI) methods have a vital role in assessing abnormalities using handwriting. This paper presents and evaluates an efficient handwriting-based Computer-Aided Diagnosis (CAD) system for Parkinson’s diagnosis as one of the most common neurodegenerative diseases. The research objective is to improve the performance of the CAD system in Parkinson’s diagnosis. The research strategy is using efficient AI methods. In the developed CAD system, the Gray-Level Co-occurrence Matrix (GLCM) is employed as a feature extraction method. The Firefly Algorithm (FA) is then applied to extracted features to select the most relevant features. The Support Vector Machine (SVM), k -Nearest Neighbor (kNN), and Ensemble algorithms are used to classify the results. The performance of the proposed CAD system is evaluated using MATLAB R2021b and a templated handwritten dataset collected at Botucatu Medical School, São Paulo State University, Brazil. The evaluation's findings show that the suggested method works well. The suggested CAD system performs best when the Meander handwritten exam, GLCM feature extraction method, FA feature selection algorithm, and SVM classification algorithm are used attaining an accuracy of 96%. The accuracy results in this study show that the proposed method can be considered a noninvasive accessible diagnostic method.

The chest digital tomosynthesis(CDT) is recently developed medical device that has several advantage for diagnosing lung disease. For example, CDT provides depth information with relatively low radiation dose compared to computed tomography (CT). However, a major problem with CDT is the image artifacts associated with data incompleteness resulting from limited angle data acquisition in CDT geometry. For this reason, the sensitivity of lung disease was not clear compared to CT. In this study, to improve sensitivity of lung disease detection in CDT, we developed computer aided diagnosis (CAD) systems based on machine learning. For design CAD systems, we used 100 cases of lung nodules cropped images and 100 cases of normal lesion cropped images acquired by lung man phantoms and proto type CDT. We used machine learning techniques based on support vector machine and Gabor filter. The Gabor filter was used for extracting characteristics of lung nodules and we compared performance of feature extraction of Gabor filter with various scale and orientation parameters. We used 3, 4, 5 scales and 4, 6, 8 orientations. After extracting features, support vector machine (SVM) was used for classifying feature of lesions. The linear, polynomial and Gaussian kernels of SVM were compared to decide the best SVM conditions for CDT reconstruction images. The results of CAD system with machine learning showed the capability of automatically lung lesion detection. Furthermore detection performance was the best when Gabor filter with 5 scale and 8 orientation and SVM with Gaussian kernel were used. In conclusion, our suggested CAD system showed improving sensitivity of lung lesion detection in CDT and decide Gabor filter and SVM conditions to achieve higher detection performance of our developed CAD system for CDT.

Tuberculosis (TB) is one of the major global health threats especially in developing countries. Although newly diagnosed TB patients can be recovered with high cure rate, many curable TB patients in the developing countries are obliged to die because of delayed diagnosis, partly by the lack of radiography and radiologists. Therefore, developing a computer-aided diagnosis (CAD) system for TB screening can contribute to early diagnosis of TB, which results in prevention of deaths from TB. Currently, most CAD algorithms adopt carefully designed morphological features distinguishing different lesion types to improve screening performances. However, such engineered features cannot be guaranteed to be the best descriptors for TB screening. Deep learning has become a majority in machine learning society. Especially in computer vision fields, it has been verified that deep convolutional neural networks (CNN) is a very promising algorithm for various visual tasks. Since deep CNN enables end-to-end training from feature extraction to classification, it does not require objective-specific manual feature engineering. In this work, we designed CAD system based on deep CNN for automatic TB screening. Based on large-scale chest X-rays (CXRs), we achieved viable TB screening performance of 0.96, 0.93 and 0.88 in terms of AUC for three real field datasets, respectively, by exploiting the effect of transfer learning.

Coronavirus (COVID-19) was first observed in Wuhan, China, and quickly propagated worldwide. It is considered the supreme crisis of the present era and one of the most crucial hazards threatening worldwide health. Therefore, the early detection of COVID-19 is essential. The common way to detect COVID-19 is the reverse transcription-polymerase chain reaction (RT-PCR) test, although it has several drawbacks. Computed tomography (CT) scans can enable the early detection of suspected patients, however, the overlap between patterns of COVID-19 and other types of pneumonia makes it difficult for radiologists to diagnose COVID-19 accurately. On the other hand, deep learning (DL) techniques and especially the convolutional neural network (CNN) can classify COVID-19 and non-COVID-19 cases. In addition, DL techniques that use CT images can deliver an accurate diagnosis faster than the RT-PCR test, which consequently saves time for disease control and provides an efficient computer-aided diagnosis (CAD) system. The shortage of publicly available datasets of CT images, makes the CAD system’s design a challenging task. The CAD systems in the literature are based on either individual CNN or two-fused CNNs; one used for segmentation and the other for classification and diagnosis. In this article, a novel CAD system is proposed for diagnosing COVID-19 based on the fusion of multiple CNNs. First, an end-to-end classification is performed. Afterward, the deep features are extracted from each network individually and classified using a support vector machine (SVM) classifier. Next, principal component analysis is applied to each deep feature set, extracted from each network. Such feature sets are then used to train an SVM classifier individually. Afterward, a selected number of principal components from each deep feature set are fused and compared with the fusion of the deep features extracted from each CNN. The results show that the proposed system is effective and capable of detecting COVID-19 and distinguishing it from non-COVID-19 cases with an accuracy of 94.7%, AUC of 0.98 (98%), sensitivity 95.6%, and specificity of 93.7%. Moreover, the results show that the system is efficient, as fusing a selected number of principal components has reduced the computational cost of the final model by almost 32%.