Chest x-ray findings in tuberculosis patients identified by passive and active case finding: A retrospective study

Superimposed Pulmonary Tuberculosis (PTB) in a 26-Year-Old Female with No Underlying Co-Morbidities Recovering from COVID-19-Case Report

Tuberculosis before the COVID-19 pandemic is said to have killed more people globally than any other communicable disease and is ranked the 13th cause of death, according to the WHO. Tuberculosis also still remains highly endemic, especially in LIMCs with a high burden of people living with HIV/AIDS, in which it is the leading cause of mortality. Given the risk factors associated with COVID-19, the cross similarities between tuberculosis and COVID-19 symptoms, and the paucity of data on how both diseases impact each other, there is a need to generate more information on COVID-19-TB co-infection. In this case report, we present a young female patient of reproductive age with no underlying comorbidities recovering from COVID-19, who later presented with pulmonary tuberculosis. It describes the series of investigations performed and treatments given during the follow-up. There is a need for more surveillance for possible COVID-19-TB co-infection cases and further research to understand the impact of COVID-19 on tuberculosis and vice versa, especially in LMICs.

Proposing a novel multi-instance learning model for tuberculosis recognition from chest X-ray images based on CNNs, complex networks and stacked ensemble

Mycobacterium Tuberculosis (TB) is an infectious bacterial disease. In 2018, about 10 million people has been diagnosed with tuberculosis (TB) worldwide. Early diagnosis of TB is necessary for effective treatment, higher survival rate, and preventing its further transmission. The gold standard for tuberculosis diagnosis is sputum culture. Nevertheless, posterior-anterior chest radiographs (CXR) is an effective central method with low cost and a relatively low radiation dose for screening TB with immediate results. TB diagnosis from CXR is a challenging task requiring high level of expertise due to the diverse presentation of the disease. Significant intra-class variation and inter-class similarity in CXR images makes TB diagnosis from CXR a more challenging task. The main aim of this study is tuberculosis recognition from CXR images for reducing the disease burden. For this purpose, a novel multi-instance classification model is proposed in this study which is based on CNNs, complex networks and stacked ensemble (CCNSE). A main advantage of CCNSE is not requiring an accurate lung segmentation to localize the suspicious regions. Several overlapping patches are extracted from each CXR image. Features describing each patch are obtained by CNNs and then the feature vectors are clustered. Local complex networks (LCN) and global ones (GCN) of the cluster representatives are formed and feature engineering on LCN (GCN) generates other features at image-level (patch-level and image-level). Global clustering on these feature sets is performed for all patches. Each patch is assigned the purity score of its corresponding cluster. Patch-level features and purity scores are aggregated for each image. Finally, the images are classified with a proposed stacked ensemble classifier to normal and TB classes. Two datasets are used in this study including Montgomery County CXR set (MC) and Shenzhen dataset (SZ). MC/SZ includes 138/662 chest X-rays (CXR) from which 80 and 58/326 and 336 images belong to normal/TB classes, respectively. The experimental results show that the proposed method with AUC of 99.00 ± 0.28/98.00 ± 0.16 for MC/SZ and accuracy of 99.26 ± 0.40/99.22 ± 0.32 for MC/SZ with fivefold cross validation strategy is superior than the compared ones for diagnosis of TB from CXR images. The proposed method can be used as a computer-aided diagnosis system to reduce the manual time, effort and dependency to specialist's expertise level.

Cascaded deep learning classifiers for computer-aided diagnosis of COVID-19 and pneumonia diseases in X-ray scans

Computer-aided diagnosis (CAD) systems are considered a powerful tool for physicians to support identification of the novel Coronavirus Disease 2019 (COVID-19) using medical imaging modalities. Therefore, this article proposes a new framework of cascaded deep learning classifiers to enhance the performance of these CAD systems for highly suspected COVID-19 and pneumonia diseases in X-ray images. Our proposed deep learning framework constitutes two major advancements as follows. First, complicated multi-label classification of X-ray images have been simplified using a series of binary classifiers for each tested case of the health status. That mimics the clinical situation to diagnose potential diseases for a patient. Second, the cascaded architecture of COVID-19 and pneumonia classifiers is flexible to use different fine-tuned deep learning models simultaneously, achieving the best performance of confirming infected cases. This study includes eleven pre-trained convolutional neural network models, such as Visual Geometry Group Network (VGG) and Residual Neural Network (ResNet). They have been successfully tested and evaluated on public X-ray image dataset for normal and three diseased cases. The results of proposed cascaded classifiers showed that VGG16, ResNet50V2, and Dense Neural Network (DenseNet169) models achieved the best detection accuracy of COVID-19, viral (Non-COVID-19) pneumonia, and bacterial pneumonia images, respectively. Furthermore, the performance of our cascaded deep learning classifiers is superior to other multi-label classification methods of COVID-19 and pneumonia diseases in previous studies. Therefore, the proposed deep learning framework presents a good option to be applied in the clinical routine to assist the diagnostic procedures of COVID-19 infection.

Tuberculosis: Diagnostic Challenges in Rural Africa

Tuberculosis (TB) remains among the top 10 infectious diseases with highest mortality globally since the 1990s despite effective chemotherapy. Among 10 million patients that fell ill with tuberculosis in the year 2017, 36 % were undiagnosed or detected and not reported; the number goes as high as 55 % in Tanzania, showing that the diagnosis of TB is a big challenge in the developing countries. There have been great advancements in TB diagnostics with introduction of the molecular tests such as Xpert MTB/RIF, loop-mediated isothermal amplification, lipoarabinomannan urine strip test, and molecular line-probe assays. However, most of the hospitals in Tanzania still rely on the TB score chart in children, the WHO screening questions in adults, acid-fast bacilli and chest x-ray for the diagnosis of TB. Xpert MTB/RIF has been rolled-out but remains a challenge in settings where the samples for testing must be transported over many kilometers. Imaging by sonography - nowadays widely available even in rural settings of Tanzania - has been shown to be a useful tool in the diagnosis of extrapulmonary tuberculosis. Despite all the efforts and new diagnostics, 30-50 % of patients in high-burden TB countries are still empirically treated for tuberculosis. More efforts need to be placed if we are to reduce the death toll by 90 % until 2030.