The TB Portals: an Open-Access, Web-Based Platform for Global Drug-Resistant-Tuberculosis Data Sharing and Analysis

Percent of lung involved in disease on chest X-ray predicts unfavorable treatment outcome in pulmonary tuberculosis

Radiology may better define tuberculosis (TB) severity and guide duration of treatment. We aimed to systematically study baseline chest X-rays (CXR) and their association with TB treatment outcome using real-world data. We used logistic regression to associate TB treatment outcomes with CXR findings, including percent of lung involved in disease (PLI), cavitation, and Timika score, alone or in combination with other clinical characteristics, stratifying by drug resistance status and HIV (n = 2,809). We fine-tuned convolutional neural nets (CNN) to automate PLI measurement from the CXR DICOM images (n = 5,261). PLI is the only CXR finding associated with unfavorable outcome across drug resistance and HIV subgroups [Rifampicin-susceptible disease without HIV, adjusted odds ratio (aOR) 1·11 (1·01, 1·22), P-value 0·025]. The most informed model of baseline characteristics tested predicts outcome with a validation mean area under the curve (AUC) of 0·769. PLI and Timika (AUC 0·656 and 0·655 respectively) predict unfavorable outcomes better than cavitary information (best AUC 0·591). The addition of PLI improves prediction compared to sex and age alone (AUC 0·680 and 0·627, respectively).PLI>25% provides a better separation of favorable and unfavorable outcomes compared to PLI>50%. The best performing ensemble of CNNs has an AUC 0·850 for PLI>25% and mean absolute error of 11·7% for the PLI value. PLI is better than cavitation for predicting unfavorable treatment outcome in pulmonary TB in non-clinical trial settings and it can be accurately and automatically predicted with CNNs.

One Sentence Summary

The percent of lung involved in disease improves prediction of unfavorable outcomes in pulmonary tuberculosis when added to clinical characteristics.

Large-Scale Study on AI's Impact on Identifying Chest Radiographs with No Actionable Disease in Outpatient Imaging

RATIONALE AND OBJECTIVES

Given the high volume of chest radiographs, radiologists frequently encounter heavy workloads. In outpatient imaging, a substantial portion of chest radiographs show no actionable findings. Automatically identifying these cases could improve efficiency by facilitating shorter reading workflows.

PURPOSE

A large-scale study to assess the performance of AI on identifying chest radiographs with no actionable disease (NAD) in an outpatient imaging population using comprehensive, objective, and reproducible criteria for NAD.

MATERIALS AND METHODS

The independent validation study includes 15000 patients with chest radiographs in posterior-anterior (PA) and lateral projections from an outpatient imaging center in the United States. Ground truth was established by reviewing CXR reports and classifying cases as NAD or actionable disease (AD). The NAD definition includes completely normal chest radiographs and radiographs with well-defined non-actionable findings. The AI NAD Analyzer1 (trained with 100 million multimodal images and fine-tuned on 1.3 million radiographs) utilizes a tandem system with image-level rule in and compartment-level rule out to provide case level output as NAD or potential actionable disease (PAD).

RESULTS

A total of 14057 cases met our eligibility criteria (age 56 ± 16.1 years, 55% women and 45% men). The prevalence of NAD cases in the study population was 70.7%. The AI NAD Analyzer correctly classified NAD cases with a sensitivity of 29.1% and a yield of 20.6%. The specificity was 98.9% which corresponds to a miss rate of 0.3% of cases. Significant findings were missed in 0.06% of cases, while no cases with critical findings were missed by AI.

CONCLUSION

In an outpatient population, AI can identify 20% of chest radiographs as NAD with a very low rate of missed findings. These cases could potentially be read using a streamlined protocol, thus improving efficiency and consequently reducing daily workload for radiologists.

An overview of next generation sequencing strategies and genomics tools used for tuberculosis research

Tuberculosis (TB) is a grave public health concern and is considered the foremost contributor to human mortality resulting from infectious disease. Due to the stringent clonality and extremely restricted genomic diversity, conventional methods prove inefficient for in-depth exploration of minor genomic variations and the evolutionary dynamics operating in Mycobacterium tuberculosis (M.tb) populations. Until now, the majority of reviews have primarily focused on delineating the application of whole-genome sequencing (WGS) in predicting antibiotic resistant genes, surveillance of drug resistance strains, and M.tb lineage classifications. Despite the growing use of next generation sequencing (NGS) and WGS analysis in TB research, there are limited studies that provide a comprehensive summary of there role in studying macroevolution, minor genetic variations, assessing mixed TB infections, and tracking transmission networks at an individual level. This highlights the need for systematic effort to fully explore the potential of WGS and its associated tools in advancing our understanding of TB epidemiology and disease transmission. We delve into the recent bioinformatics pipelines and NGS strategies that leverage various genetic features and simultaneous exploration of host-pathogen protein expression profile to decipher the genetic heterogeneity and host-pathogen interaction dynamics of the M.tb infections. This review highlights the potential benefits and limitations of NGS and bioinformatics tools and discusses their role in TB detection and epidemiology. Overall, this review could be a valuable resource for researchers and clinicians interested in NGS-based approaches in TB research.

Automated Pulmonary Tuberculosis Severity Assessment on Chest X-rays

According to the 2022 World Health Organization's Global Tuberculosis (TB) report, an estimated 10.6 million people fell ill with TB, and 1.6 million died from the disease in 2021. In addition, 2021 saw a reversal of a decades-long trend of declining TB infections and deaths, with an estimated increase of 4.5% in the number of people who fell ill with TB compared to 2020, and an estimated yearly increase of 450,000 cases of drug resistant TB. Estimating the severity of pulmonary TB using frontal chest X-rays (CXR) can enable better resource allocation in resource constrained settings and monitoring of treatment response, enabling prompt treatment modifications if disease severity does not decrease over time. The Timika score is a clinically used TB severity score based on a CXR reading. This work proposes and evaluates three deep learning-based approaches for predicting the Timika score with varying levels of explainability. The first approach uses two deep learning-based models, one to explicitly detect lesion regions using YOLOV5n and another to predict the presence of cavitation using DenseNet121, which are then utilized in score calculation. The second approach uses a DenseNet121-based regression model to directly predict the affected lung percentage and another to predict cavitation presence using a DenseNet121-based classification model. Finally, the third approach directly predicts the Timika score using a DenseNet121-based regression model. The best performance is achieved by the second approach with a mean absolute error of 13-14% and a Pearson correlation of 0.7-0.84 using three held-out datasets for evaluating generalization.

In silico drug design strategies for discovering novel tuberculosis therapeutics

INTRODUCTION

Tuberculosis remains a significant concern in global public health due to its intricate biology and propensity for developing antibiotic resistance. Discovering new drugs is a protracted and expensive endeavor, often spanning over a decade and incurring costs in the billions. However, computer-aided drug design (CADD) has surfaced as a nimbler and more cost-effective alternative. CADD tools enable us to decipher the interactions between therapeutic targets and novel drugs, making them invaluable in the quest for new tuberculosis treatments.

AREAS COVERED

In this review, the authors explore recent advancements in tuberculosis drug discovery enabled by in silico tools. The main objectives of this review article are to highlight emerging drug candidates identified through in silico methods and to provide an update on the therapeutic targets associated with Mycobacterium tuberculosis.

EXPERT OPINION

These in silico methods have not only streamlined the drug discovery process but also opened up new horizons for finding novel drug candidates and repositioning existing ones. The continued advancements in these fields hold great promise for more efficient, ethical, and successful drug development in the future.

DeepPulmoTB: A benchmark dataset for multi-task learning of tuberculosis lesions in lung computerized tomography (CT)

Tuberculosis (TB) remains a significant global health challenge, characterized by high incidence and mortality rates on a global scale. With the rapid advancement of computer-aided diagnosis (CAD) tools in recent years, CAD has assumed an increasingly crucial role in supporting TB diagnosis. Nonetheless, the development of CAD for TB diagnosis heavily relies on well-annotated computerized tomography (CT) datasets. Currently, the available annotations in TB CT datasets are still limited, which in turn restricts the development of CAD tools for TB diagnosis to some extent. To address this limitation, we introduce DeepPulmoTB, a CT multi-task learning dataset explicitly designed for TB diagnosis. To demonstrate the advantages of DeepPulmoTB, we propose a novel multi-task learning model, DeepPulmoTBNet (DPTBNet), for the joint segmentation and classification of lesion tissues in CT images. The architecture of DPTBNet comprises two subnets: SwinUnetR for the segmentation task, and a lightweight multi-scale network for the classification task. Furthermore, to enhance the model's capacity to capture TB lesion features, we introduce an improved iterative optimization algorithm that refines feature maps by integrating probability maps obtained in previous iterations. Extensive experiments validate the effectiveness of DPTBNet and the practicality of the DeepPulmoTB dataset.

Integrative analysis of multimodal patient data identifies personalized predictors of tuberculosis treatment prognosis

Tuberculosis (TB) afflicted 10.6 million people in 2021, and its global burden is increasing due to multidrug-resistant TB (MDR-TB) and extensively resistant TB (XDR-TB). Here, we analyze multi-domain information from 5,060 TB patients spanning 10 countries with high burden of MDR-TB from the NIAID TB Portals database to determine predictors of TB treatment outcome. Our analysis revealed significant associations between radiological, microbiological, therapeutic, and demographic data modalities. Our machine learning model, built with 203 features across modalities outperforms models built using each modality alone in predicting treatment outcomes, with an accuracy of 83% and area under the curve of 0.84. Notably, our analysis revealed that the drug regimens Bedaquiline-Clofazimine-Cycloserine-Levofloxacin-Linezolid and Bedaquiline-Clofazimine-Linezolid-Moxifloxacin were associated with treatment success and failure, respectively, for MDR non-XDR-TB. Drug combinations predicted to be synergistic by the INDIGO algorithm performed better than antagonistic combinations. Our prioritized set of features predictive of treatment outcomes can ultimately guide the personalized clinical management of TB.

Tuberculosis Chest X-Ray Image Retrieval System Using Deep Learning Based Biomarker Predictions

The world health organization's global tuberculosis (TB) report for 2022 identifies TB, with an estimated 1.6 million, as a leading cause of death. The number of new cases has risen since 2020, particularly the number of new drug-resistant cases, estimated at 450,000 in 2021. This is concerning, as treatment of patients with drug resistant TB is complex and may not always be successful. The NIAID TB Portals program is an international consortium with a primary focus on patient centric data collection and analysis for drug resistant TB. The data includes images, their associated radiological findings, clinical records, and socioeconomic information. This work describes a TB Portals' Chest X-ray based image retrieval system which enables precision medicine. An input image is used to retrieve similar images and the associated patient specific information, thus facilitating inspection of outcomes and treatment regimens from comparable patients. Image similarity is defined using clinically relevant biomarkers: gender, age, body mass index (BMI), and the percentage of lung affected per sextant. The biomarkers are predicted using variations of the DenseNet169 convolutional neural network. A multi-task approach is used to predict gender, age and BMI incorporating transfer learning from an initial training on the NIH Clinical Center CXR dataset to the TB portals dataset. The resulting gender AUC, age and BMI mean absolute errors were 0.9854, 4.03years and 1.67 k g m 2 . For the percentage of sextant affected by lesions the mean absolute errors ranged between 7% to 12% with higher error values in the middle and upper sextants which exhibit more variability than the lower sextants. The retrieval system is currently available from https://rap.tbportals.niaid.nih.gov/find_similar_cxr.

The Tuberculosis Sentinel Research Network (TB-SRN) of the International epidemiology Databases to Evaluate AIDS (IeDEA): protocol for a prospective cohort study in Africa, Southeast Asia and Latin America

INTRODUCTION

Tuberculosis (TB) is a leading infectious cause of death globally. It is the most common opportunistic infection in people living with HIV, and the most common cause of their morbidity and mortality. Following TB treatment, surviving individuals may be at risk for post-TB lung disease. The TB Sentinel Research Network (TB-SRN) provides a platform for coordinated observational TB research within the International epidemiology Databases to Evaluate AIDS (IeDEA) consortium.

METHODS AND ANALYSIS

This prospective, observational cohort study will assess treatment and post-treatment outcomes of pulmonary TB (microbiologically confirmed or clinically diagnosed) among 2600 people aged ≥15 years, with and without HIV coinfection, consecutively enrolled at 16 sites in 11 countries, across 6 of IeDEA's global regions. Data regarding clinical and sociodemographic factors, mental health, health-related quality of life, pulmonary function, and laboratory and radiographic findings will be collected using standardised questionnaires and data collection tools, beginning from the initiation of TB treatment and through 12 months after the end of treatment. Data will be aggregated for proposed analyses.

ETHICS AND DISSEMINATION

Ethics approval was obtained at all implementing study sites, including the Vanderbilt University Medical Center Human Research Protections Programme. Participants will provide informed consent; for minors, this includes both adolescent assent and the consent of their parent or primary caregiver. Protections for vulnerable groups are included, in alignment with local standards and considerations at sites. Procedures for requesting use and analysis of TB-SRN data are publicly available. Findings from TB-SRN analyses will be shared with national TB programmes to inform TB programming and policy, and disseminated at regional and global conferences and other venues.

Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization

Features in images' backgrounds can spuriously correlate with the images' classes, representing background bias. They can influence the classifier's decisions, causing shortcut learning (Clever Hans effect). The phenomenon generates deep neural networks (DNNs) that perform well on standard evaluation datasets but generalize poorly to real-world data. Layer-wise Relevance Propagation (LRP) explains DNNs' decisions. Here, we show that the optimization of LRP heatmaps can minimize the background bias influence on deep classifiers, hindering shortcut learning. By not increasing run-time computational cost, the approach is light and fast. Furthermore, it applies to virtually any classification architecture. After injecting synthetic bias in images' backgrounds, we compared our approach (dubbed ISNet) to eight state-of-the-art DNNs, quantitatively demonstrating its superior robustness to background bias. Mixed datasets are common for COVID-19 and tuberculosis classification with chest X-rays, fostering background bias. By focusing on the lungs, the ISNet reduced shortcut learning. Thus, its generalization performance on external (out-of-distribution) test databases significantly surpassed all implemented benchmark models.

Recent Advances and Techniques for Identifying Novel Antibacterial Targets

BACKGROUND

With the emergence of drug-resistant bacteria, the development of new antibiotics is urgently required. Target-based drug discovery is the most frequently employed approach for the drug development process. However, traditional drug target identification techniques are costly and time-consuming. As research continues, innovative approaches for antibacterial target identification have been developed which enabled us to discover drug targets more easily and quickly.

METHODS

In this review, methods for finding drug targets from omics databases have been discussed in detail including principles, procedures, advantages, and potential limitations. The role of phage-driven and bacterial cytological profiling approaches is also discussed. Moreover, current article demonstrates the advancements being made in the establishment of computational tools, machine learning algorithms, and databases for antibacterial target identification.

RESULTS

Bacterial drug targets successfully identified by employing these aforementioned techniques are described as well.

CONCLUSION

The goal of this review is to attract the interest of synthetic chemists, biologists, and computational researchers to discuss and improve these methods for easier and quicker development of new drugs.

Predictive capabilities of baseline radiological findings for early and late disease outcomes within sensitive and multi-drug resistant tuberculosis cases

Purpose

This study compares performance of Timika Score to standardized, detailed radiologist observations of Chest X rays (CXR) for predicting early infectiousness and subsequent treatment outcome in drug sensitive (DS) or multi-drug resistant (MDR) tuberculosis cases. It seeks improvement in prediction of these clinical events through these additional observations.

Method

This is a retrospective study analyzing cases from the NIH/NIAID supported TB Portals database, a large, trans-national, multi-site cohort of primarily drug-resistant tuberculosis patients. We analyzed patient records with sputum microscopy readings, radiologist annotated CXR, and treatment outcome including a matching step on important covariates of age, gender, HIV status, case definition, Body Mass Index (BMI), smoking, drug use, and Timika Score across resistance type for comparison.

Results

2142 patients with tuberculosis infection (374 with poor outcome and 1768 with good treatment outcome) were retrospectively reviewed. Bayesian ANOVA demonstrates radiologist observations did not show greater predictive ability for baseline infectiousness (0.77 and 0.74 probability in DS and MDR respectively); however, the observations provided superior prediction of treatment outcome (0.84 and 0.63 probability in DS and MDR respectively). Estimated lung abnormal area and cavity were identified as important predictors underlying the Timika Score's performance.

Conclusions

Timika Score simplifies the usage of baseline CXR for prediction of early infectiousness of the case and shows comparable performance to using detailed, standardized radiologist observations. The score's utility diminishes for treatment outcome prediction and is exceeded by the usage of the detailed observations although prediction performance on treatment outcome decreases especially in MDR TB cases.

Lineage classification and antitubercular drug resistance surveillance of Mycobacterium tuberculosis by whole-genome sequencing in Southern India

IMPORTANCE

Studies mapping genetic heterogeneity of clinical isolates of M. tuberculosis for determining their strain lineage and drug resistance by whole-genome sequencing are limited in high tuberculosis burden settings. We carried out whole-genome sequencing of 242 M. tuberculosis isolates from drug-sensitive and drug-resistant tuberculosis patients, identified and collected as part of the TB Portals Program, to have a comprehensive insight into the genetic diversity of M. tuberculosis in Southern India. We report several genetic variations in M. tuberculosis that may confer resistance to antitubercular drugs. Further wide-scale efforts are required to fully characterize M. tuberculosis genetic diversity at a population level in high tuberculosis burden settings for providing precise tuberculosis treatment.

Weak Localization of Radiographic Manifestations in Pulmonary Tuberculosis from Chest X-ray: A Systematic Review

Pulmonary tuberculosis (PTB) is a bacterial infection that affects the lung. PTB remains one of the infectious diseases with the highest global mortalities. Chest radiography is a technique that is often employed in the diagnosis of PTB. Radiologists identify the severity and stage of PTB by inspecting radiographic features in the patient's chest X-ray (CXR). The most common radiographic features seen on CXRs include cavitation, consolidation, masses, pleural effusion, calcification, and nodules. Identifying these CXR features will help physicians in diagnosing a patient. However, identifying these radiographic features for intricate disorders is challenging, and the accuracy depends on the radiologist's experience and level of expertise. So, researchers have proposed deep learning (DL) techniques to detect and mark areas of tuberculosis infection in CXRs. DL models have been proposed in the literature because of their inherent capacity to detect diseases and segment the manifestation regions from medical images. However, fully supervised semantic segmentation requires several pixel-by-pixel labeled images. The annotation of such a large amount of data by trained physicians has some challenges. First, the annotation requires a significant amount of time. Second, the cost of hiring trained physicians is expensive. In addition, the subjectivity of medical data poses a difficulty in having standardized annotation. As a result, there is increasing interest in weak localization techniques. Therefore, in this review, we identify methods employed in the weakly supervised segmentation and localization of radiographic manifestations of pulmonary tuberculosis from chest X-rays. First, we identify the most commonly used public chest X-ray datasets for tuberculosis identification. Following that, we discuss the approaches for weakly localizing tuberculosis radiographic manifestations in chest X-rays. The weakly supervised localization of PTB can highlight the region of the chest X-ray image that contributed the most to the DL model's classification output and help pinpoint the diseased area. Finally, we discuss the limitations and challenges of weakly supervised techniques in localizing TB manifestations regions in chest X-ray images.

Combining Radiological and Genomic TB Portals Data for Drug Resistance Analysis

Tuberculosis (TB) drug resistance is a worldwide public health problem. It decreases the likelihood of a positive outcome for the individual patient and increases the likelihood of disease spread. Therefore, early detection of TB drug resistance is crucial for improving outcomes and controlling disease transmission. While drug-sensitive tuberculosis cases are declining worldwide because of effective treatment, the threat of drug-resistant tuberculosis is growing, and the success rate of drug-resistant tuberculosis treatment is only around 60%. The TB Portals program provides a publicly accessible repository of TB case data with an emphasis on collecting drug-resistant cases. The dataset includes multi-modal information such as socioeconomic/geographic data, clinical characteristics, pathogen genomics, and radiological features. The program is an international collaboration whose participants are typically under a substantial burden of drug-resistant tuberculosis, with data collected from standard clinical care provided to the patients. Consequentially, the TB Portals dataset is heterogenous in nature, with data representing multiple treatment centers in different countries and containing cross-domain information. This study presents the challenges and methods used to address them when working with this real-world dataset. Our goal was to evaluate whether combining radiological features derived from a chest X-ray of the host and genomic features from the pathogen can potentially improve the identification of the drug susceptibility type, drug-sensitive (DS-TB) or drug-resistant (DR-TB), and the length of the first successful drug regimen. To perform these studies, significantly imbalanced data needed to be processed, which included a much larger number of DR-TB cases than DS-TB, many more cases with radiological findings than genomic ones, and the sparse high dimensional nature of the genomic information. Three evaluation studies were carried out. First, the DR-TB/DS-TB classification model achieved an average accuracy of 92.4% when using genomic features alone or when combining radiological and genomic features. Second, the regression model for the length of the first successful treatment had a relative error of 53.5% using radiological features, 25.6% using genomic features, and 22.0% using both radiological and genomic features. Finally, the relative error of the third regression model predicting the length of the first treatment using the most common drug combination varied depending on the feature type used. When using radiological features alone, the relative error was 17.8%. For genomic features alone, the relative error increased to 19.9%. The model had a relative error of 19.0% when both radiological and genomic features were combined. Although combining radiological and genomic features did not improve upon the use of genomic features when classifying DR-TB/DS-TB, the combination of the two feature types improved the relative error of the predictive model for the length of the first successful treatment. Furthermore, the regression model trained on radiological features achieved the best performance when predicting the treatment length of the most common drug combination.

Computer-aided diagnosis using embedded ensemble deep learning for multiclass drug-resistant tuberculosis classification

Introduction

This study aims to develop a web application, TB-DRD-CXR, for the categorization of tuberculosis (TB) patients into subgroups based on their level of drug resistance. The application utilizes an ensemble deep learning model that classifies TB strains into five subtypes: drug sensitive tuberculosis (DS-TB), drug resistant TB (DR-TB), multidrug-resistant TB (MDR-TB), pre-extensively drug-resistant TB (pre-XDR-TB), and extensively drug-resistant TB (XDR-TB).

Methods

The ensemble deep learning model employed in the TB-DRD-CXR web application incorporates novel fusion techniques, image segmentation, data augmentation, and various learning rate strategies. The performance of the proposed model is compared with state-of-the-art techniques and standard homogeneous CNN architectures documented in the literature.

Results

Computational results indicate that the suggested method outperforms existing methods reported in the literature, providing a 4.0%-33.9% increase in accuracy. Moreover, the proposed model demonstrates superior performance compared to standard CNN models, including DenseNet201, NASNetMobile, EfficientNetB7, EfficientNetV2B3, EfficientNetV2M, and ConvNeXtSmall, with accuracy improvements of 28.8%, 93.4%, 2.99%, 48.0%, 4.4%, and 7.6% respectively.

Conclusion

The TB-DRD-CXR web application was developed and tested with 33 medical staff. The computational results showed a high accuracy rate of 96.7%, time-based efficiency (ET) of 4.16 goals/minutes, and an overall relative efficiency (ORE) of 100%. The system usability scale (SUS) score of the proposed application is 96.7%, indicating user satisfaction and a likelihood of recommending the TB-DRD-CXR application to others based on previous literature.

AutoPLP: A Padlock Probe Design Pipeline for Zoonotic Pathogens

Emergence of novel zoonotic infections among the human population has increased the burden on global healthcare systems to curb their spread. To meet the evolutionary agility of pathogens, it is essential to revamp the existing diagnostic methods for early detection and characterization of the pathogens at the molecular level. Padlock probes (PLPs), which can leverage the power of isothermal nucleic acid amplification techniques (NAAT) such as rolling circle amplification (RCA), are known for their high sensitivity and specificity in detecting a diverse pathogen panel of interest. However, due to the complexity involved in deciding the target regions for PLP design and the need for optimization of multiple experimental parameters, the applicability of RCA has been limited in point-of-care testing for pathogen detection. To address this gap, we have developed a novel and integrated PLP design pipeline named AutoPLP, which can automate the probe design process for a diverse pathogen panel of interest. The pipeline is composed of three modules which can perform sequence data curation, multiple sequence alignment, conservation analysis, filtration based on experimental parameters (T_m, GC content, and secondary structure formation), and in silico probe validation via potential cross-hybridization check with host genome. The modules can also take into account the backbone and restriction site information, appropriate combinations of which are incorporated along with the probe arms to design a complete probe sequence. The potential applications of AutoPLP are showcased through the design of PLPs for the detection of rabies virus and drug-resistant strains of Mycobacterium tuberculosis.

AI-based radiodiagnosis using chest X-rays: A review

Chest Radiograph or Chest X-ray (CXR) is a common, fast, non-invasive, relatively cheap radiological examination method in medical sciences. CXRs can aid in diagnosing many lung ailments such as Pneumonia, Tuberculosis, Pneumoconiosis, COVID-19, and lung cancer. Apart from other radiological examinations, every year, 2 billion CXRs are performed worldwide. However, the availability of the workforce to handle this amount of workload in hospitals is cumbersome, particularly in developing and low-income nations. Recent advances in AI, particularly in computer vision, have drawn attention to solving challenging medical image analysis problems. Healthcare is one of the areas where AI/ML-based assistive screening/diagnostic aid can play a crucial part in social welfare. However, it faces multiple challenges, such as small sample space, data privacy, poor quality samples, adversarial attacks and most importantly, the model interpretability for reliability on machine intelligence. This paper provides a structured review of the CXR-based analysis for different tasks, lung diseases and, in particular, the challenges faced by AI/ML-based systems for diagnosis. Further, we provide an overview of existing datasets, evaluation metrics for different[][15mm][0mm]Q5 tasks and patents issued. We also present key challenges and open problems in this research domain.

Deep Learning Detection of Active Pulmonary Tuberculosis at Chest Radiography Matched the Clinical Performance of Radiologists

Background The World Health Organization (WHO) recommends chest radiography to facilitate tuberculosis (TB) screening. However, chest radiograph interpretation expertise remains limited in many regions. Purpose To develop a deep learning system (DLS) to detect active pulmonary TB on chest radiographs and compare its performance to that of radiologists. Materials and Methods A DLS was trained and tested using retrospective chest radiographs (acquired between 1996 and 2020) from 10 countries. To improve generalization, large-scale chest radiograph pretraining, attention pooling, and semisupervised learning ("noisy-student") were incorporated. The DLS was evaluated in a four-country test set (China, India, the United States, and Zambia) and in a mining population in South Africa, with positive TB confirmed with microbiological tests or nucleic acid amplification testing (NAAT). The performance of the DLS was compared with that of 14 radiologists. The authors studied the efficacy of the DLS compared with that of nine radiologists using the Obuchowski-Rockette-Hillis procedure. Given WHO targets of 90% sensitivity and 70% specificity, the operating point of the DLS (0.45) was prespecified to favor sensitivity. Results A total of 165 754 images in 22 284 subjects (mean age, 45 years; 21% female) were used for model development and testing. In the four-country test set (1236 subjects, 17% with active TB), the receiver operating characteristic (ROC) curve of the DLS was higher than those for all nine India-based radiologists, with an area under the ROC curve of 0.89 (95% CI: 0.87, 0.91). Compared with these radiologists, at the prespecified operating point, the DLS sensitivity was higher (88% vs 75%, P < .001) and specificity was noninferior (79% vs 84%, P = .004). Trends were similar within other patient subgroups, in the South Africa data set, and across various TB-specific chest radiograph findings. In simulations, the use of the DLS to identify likely TB-positive chest radiographs for NAAT confirmation reduced the cost by 40%-80% per TB-positive patient detected. Conclusion A deep learning method was found to be noninferior to radiologists for the determination of active tuberculosis on digital chest radiographs. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by van Ginneken in this issue.

Drug-Resistant Tuberculosis Treatment Recommendation, and Multi-Class Tuberculosis Detection and Classification Using Ensemble Deep Learning-Based System

This research develops the TB/non-TB detection and drug-resistant categorization diagnosis decision support system (TB-DRC-DSS). The model is capable of detecting both TB-negative and TB-positive samples, as well as classifying drug-resistant strains and also providing treatment recommendations. The model is developed using a deep learning ensemble model with the various CNN architectures. These architectures include EfficientNetB7, mobileNetV2, and Dense-Net121. The models are heterogeneously assembled to create an effective model for TB-DRC-DSS, utilizing effective image segmentation, augmentation, and decision fusion techniques to improve the classification efficacy of the current model. The web program serves as the platform for determining if a patient is positive or negative for tuberculosis and classifying several types of drug resistance. The constructed model is evaluated and compared to current methods described in the literature. The proposed model was assessed using two datasets of chest X-ray (CXR) images collected from the references. This collection of datasets includes the Portal dataset, the Montgomery County dataset, the Shenzhen dataset, and the Kaggle dataset. Seven thousand and eight images exist across all datasets. The dataset was divided into two subsets: the training dataset (80%) and the test dataset (20%). The computational result revealed that the classification accuracy of DS-TB against DR-TB has improved by an average of 43.3% compared to other methods. The categorization between DS-TB and MDR-TB, DS-TB and XDR-TB, and MDR-TB and XDR-TB was more accurate than with other methods by an average of 28.1%, 6.2%, and 9.4%, respectively. The accuracy of the embedded multiclass model in the web application is 92.6% when evaluated with the test dataset, but 92.8% when evaluated with a random subset selected from the aggregate dataset. In conclusion, 31 medical staff members have evaluated and utilized the online application, and the final user preference score for the web application is 9.52 out of a possible 10.

Embedded AMIS-Deep Learning with Dialog-Based Object Query System for Multi-Class Tuberculosis Drug Response Classification

A person infected with drug-resistant tuberculosis (DR-TB) is the one who does not respond to typical TB treatment. DR-TB necessitates a longer treatment period and a more difficult treatment protocol. In addition, it can spread and infect individuals in the same manner as regular TB, despite the fact that early detection of DR-TB could reduce the cost and length of TB treatment. This study provided a fast and effective classification scheme for the four subtypes of TB: Drug-sensitive tuberculosis (DS-TB), drug-resistant tuberculosis (DR-TB), multidrug-resistant tuberculosis (MDR-TB), and extensively drug-resistant tuberculosis (XDR-TB). The drug response classification system (DRCS) has been developed as a classification tool for DR-TB subtypes. As a classification method, ensemble deep learning (EDL) with two types of image preprocessing methods, four convolutional neural network (CNN) architectures, and three decision fusion methods have been created. Later, the model developed by EDL will be included in the dialog-based object query system (DBOQS), in order to enable the use of DRCS as the classification tool for DR-TB in assisting medical professionals with diagnosing DR-TB. EDL yields an improvement of 1.17-43.43% over the existing methods for classifying DR-TB, while compared with classic deep learning, it generates 31.25% more accuracy. DRCS was able to increase accuracy to 95.8% and user trust to 95.1%, and after the trial period, 99.70% of users were interested in continuing the utilization of the system as a supportive diagnostic tool.

Contrastive self-supervised learning from 100 million medical images with optional supervision

Purpose

Building accurate and robust artificial intelligence systems for medical image assessment requires the creation of large sets of annotated training examples. However, constructing such datasets is very costly due to the complex nature of annotation tasks, which often require expert knowledge (e.g., a radiologist). To counter this limitation, we propose a method to learn from medical images at scale in a self-supervised way.

Approach

Our approach, based on contrastive learning and online feature clustering, leverages training datasets of over 100,000,000 medical images of various modalities, including radiography, computed tomography (CT), magnetic resonance (MR) imaging, and ultrasonography (US). We propose to use the learned features to guide model training in supervised and hybrid self-supervised/supervised regime on various downstream tasks.

Results

We highlight a number of advantages of this strategy on challenging image assessment problems in radiography, CT, and MR: (1) significant increase in accuracy compared to the state-of-the-art (e.g., area under the curve boost of 3% to 7% for detection of abnormalities from chest radiography scans and hemorrhage detection on brain CT); (2) acceleration of model convergence during training by up to 85% compared with using no pretraining (e.g., 83% when training a model for detection of brain metastases in MR scans); and (3) increase in robustness to various image augmentations, such as intensity variations, rotations or scaling reflective of data variation seen in the field.

Conclusions

The proposed approach enables large gains in accuracy and robustness on challenging image assessment problems. The improvement is significant compared with other state-of-the-art approaches trained on medical or vision images (e.g., ImageNet).

AI-Assisted Tuberculosis Detection and Classification from Chest X-Rays Using a Deep Learning Normalization-Free Network Model

Tuberculosis (TB) is an airborne disease caused by Mycobacterium tuberculosis. It is imperative to detect cases of TB as early as possible because if left untreated, there is a 70% chance of a patient dying within 10 years. The necessity for supplementary tools has increased in mid to low-income countries due to the rise of automation in healthcare sectors. The already limited resources are being heavily allocated towards controlling other dangerous diseases. Modern digital radiography (DR) machines, used for screening chest X-rays of potential TB victims are very practical. Coupled with computer-aided detection (CAD) with the aid of artificial intelligence, radiologists working in this field can really help potential patients. In this study, progressive resizing is introduced for training models to perform automatic inference of TB using chest X-ray images. ImageNet fine-tuned Normalization-Free Networks (NFNets) are trained for classification and the Score-Cam algorithm is utilized to highlight the regions in the chest X-Rays for detailed inference on the diagnosis. The proposed method is engineered to provide accurate diagnostics for both binary and multiclass classification. The models trained with this method have achieved 96.91% accuracy, 99.38% AUC, 91.81% sensitivity, and 98.42% specificity on a multiclass classification dataset. Moreover, models have also achieved top-1 inference metrics of 96% accuracy and 98% AUC for binary classification. The results obtained demonstrate that the proposed method can be used as a secondary decision tool in a clinical setting for assisting radiologists.

Integrative analysis of clinical health records, imaging and pathogen genomics identifies personalized predictors of disease prognosis in tuberculosis

Tuberculosis (TB) afflicts over 10 million people every year and its global burden is projected to increase dramatically due to multidrug-resistant TB (MDR-TB). The Covid-19 pandemic has resulted in reduced access to TB diagnosis and treatment, reversing decades of progress in disease management globally. It is thus crucial to analyze real-world multi-domain information from patient health records to determine personalized predictors of TB treatment outcome and drug resistance. We conduct a retrospective analysis on electronic health records of 5060 TB patients spanning 10 countries with high burden of MDR-TB including Ukraine, Moldova, Belarus and India available on the NIAID-TB portals database. We analyze over 200 features across multiple host and pathogen modalities representing patient social demographics, disease presentations as seen in cChest X rays and CT scans, and genomic records with drug susceptibility features of the pathogen strain from each patient. Our machine learning model, built with diverse data modalities outperforms models built using each modality alone in predicting treatment outcomes, with an accuracy of 81% and AUC of 0.768. We determine robust predictors across countries that are associated with unsuccessful treatmentclinical outcomes, and validate our predictions on new patient data from TB Portals. Our analysis of drug regimens and drug interactions suggests that synergistic drug combinations and those containing the drugs Bedaquiline, Levofloxacin, Clofazimine and Amoxicillin see more success in treating MDR and XDR TB. Features identified via chest imaging such as percentage of abnormal volume, size of lung cavitation and bronchial obstruction are associated significantly with pathogen genomic attributes of drug resistance. Increased disease severity was also observed in patients with lower BMI and with comorbidities. Our integrated multi-modal analysis thus revealed significant associations between radiological, microbiological, therapeutic, and demographic data modalities, providing a deeper understanding of personalized responses to aid in the clinical management of TB.

Reliable Sarcoidosis Detection Using Chest X-rays with EfficientNets and Stain-Normalization Techniques

Sarcoidosis is frequently misdiagnosed as tuberculosis (TB) and consequently mistreated due to inherent limitations in radiological presentations. Clinically, to distinguish sarcoidosis from TB, physicians usually employ biopsy tissue diagnosis and blood tests; this approach is painful for patients, time-consuming, expensive, and relies on techniques prone to human error. This study proposes a computer-aided diagnosis method to address these issues. This method examines seven EfficientNet designs that were fine-tuned and compared for their abilities to categorize X-ray images into three categories: normal, TB-infected, and sarcoidosis-infected. Furthermore, the effects of stain normalization on performance were investigated using Reinhard's and Macenko's conventional stain normalization procedures. This procedure aids in improving diagnostic efficiency and accuracy while cutting diagnostic costs. A database of 231 sarcoidosis-infected, 563 TB-infected, and 1010 normal chest X-ray images was created using public databases and information from several national hospitals. The EfficientNet-B4 model attained accuracy, sensitivity, and precision rates of 98.56%, 98.36%, and 98.67%, respectively, when the training X-ray images were normalized by the Reinhard stain approach, and 97.21%, 96.9%, and 97.11%, respectively, when normalized by Macenko's approach. Results demonstrate that Reinhard stain normalization can improve the performance of EfficientNet -B4 X-ray image classification. The proposed framework for identifying pulmonary sarcoidosis may prove valuable in clinical use.

A Highly Sensitive and Specific Detection Method for Mycobacterium tuberculosis Fluoroquinolone Resistance Mutations Utilizing the CRISPR-Cas13a System

Objectives

CRISPR-Cas13a system-based nucleic acid detection methods are reported to have rapid and sensitive DNA detection. However, the screening strategy for crRNAs that enables CRISPR-Cas13a single-base resolution DNA detection of human pathogens remains unclear.

Methods

A combined rational design and target mutation-anchoring CRISPR RNA (crRNA) screening strategy was proposed.

Results

A set of crRNAs was found to enable the CRISPR-Cas13 system to dramatically distinguish fluroquinolone resistance mutations in clinically isolated Mycobacterium tuberculosis strains from the highly homologous wild type, with a signal ratio ranging from 8.29 to 38.22 in different mutation sites. For the evaluation of clinical performance using genomic DNA from clinically isolated M. tuberculosis, the specificity and sensitivity were 100 and 91.4%, respectively, compared with culture-based phenotypic assays.

Conclusion

These results demonstrated that the CRISPR-Cas13a system has potential for use in single nucleotide polymorphism (SNP) detection after tuning crRNAs. We believe this crRNA screening strategy will be used extensively for early drug resistance monitoring and guidance for clinical treatment.

Evaluating Explainable Artificial Intelligence for X-ray Image Analysis

The lack of justification of the results obtained by artificial intelligence (AI) algorithms has limited their usage in the medical context. To increase the explainability of the existing AI methods, explainable artificial intelligence (XAI) is proposed. We performed a systematic literature review, based on the guidelines proposed by Kitchenham and Charters, of studies that applied XAI methods in X-ray-image-related tasks. We identified 141 studies relevant to the objective of this research from five different databases. For each of these studies, we assessed the quality and then analyzed them according to a specific set of research questions. We determined two primary purposes for X-ray images: the detection of bone diseases and lung diseases. We found that most of the AI methods used were based on a CNN. We identified the different techniques to increase the explainability of the models and grouped them depending on the kind of explainability obtained. We found that most of the articles did not evaluate the quality of the explainability obtained, causing problems of confidence in the explanation. Finally, we identified the current challenges and future directions of this subject and provide guidelines to practitioners and researchers to improve the limitations and the weaknesses that we detected.

Gene evolutionary trajectories in Mycobacterium tuberculosis reveal temporal signs of selection

Genetic differences between different Mycobacterium tuberculosis complex (MTBC) strains determine their ability to transmit within different host populations, their latency times, and their drug resistance profiles. Said differences usually emerge through de novo mutations and are maintained or discarded by the balance of evolutionary forces. Using a dataset of ∼5,000 strains representing global MTBC diversity, we determined the past and present selective forces that have shaped the current variability observed in the pathogen population. We identified regions that have evolved under changing types of selection since the time of the MTBC common ancestor. Our approach highlighted striking differences in the genome regions relevant for host–pathogen interaction and, in particular, suggested an adaptive role for the sensor protein of two-component systems. In addition, we applied our approach to successfully identify potential determinants of resistance to drugs administered as second-line tuberculosis treatments.

Patterns of genomic interrelatedness of publicly available samples in the TB portals database

The TB Portals program is an international collaboration for the collection and dissemination of tuberculosis data from patient cases focused on drug resistance. The central database is a patient-oriented resource containing both patient and pathogen clinical and genomic information. Herein we provide a summary of the pathogen genomic data available through the TB Portals and show one potential application by examining patterns of genomic pairwise distances. Distributions of pairwise distances highlight overall patterns of genome variability within and between Mycobacterium tuberculosis phylogenomic lineages. Closely related isolates (based on whole-genome pairwise distances and time between sample collection dates) from different countries were identified as potential evidence of international transmission of drug-resistant tuberculosis. These high-level views of genomic relatedness provide information that can stimulate hypotheses for further and more detailed research.

The COMBAT-TB Workbench: Making Powerful Mycobacterium tuberculosis Bioinformatics Accessible

Whole-genome sequencing (WGS) is a powerful method for detecting drug resistance, genetic diversity, and transmission dynamics of Mycobacterium tuberculosis. Implementation of WGS in public health microbiology laboratories is impeded by a lack of user-friendly, automated, and semiautomated pipelines. We present the COMBAT-TB Workbench, a modular, easy-to-install application that provides a web-based environment for Mycobacterium tuberculosis bioinformatics. The COMBAT-TB Workbench is built using two main software components: the IRIDA platform for its web-based user interface and data management capabilities and the Galaxy bioinformatics workflow platform for workflow execution. These components are combined into a single easy-to-install application using Docker container technology. We implemented two workflows, for M. tuberculosis sample analysis and phylogeny, in Galaxy. Building our workflows involved updating some Galaxy tools (Trimmomatic, snippy, and snp-sites) and writing new Galaxy tools (snp-dists, TB-Profiler, tb_variant_filter, and TB Variant Report). The irida-wf-ga2xml tool was updated to be able to work with recent versions of Galaxy and was further developed into IRIDA plugins for both workflows. In the case of the M. tuberculosis sample analysis, an interface was added to update the metadata stored for each sequence sample with results gleaned from the Galaxy workflow output. Data can be loaded into the COMBAT-TB Workbench via the web interface or via the command line IRIDA uploader tool. The COMBAT-TB Workbench application deploys IRIDA, the COMBAT-TB IRIDA plugins, the MariaDB database, and Galaxy using Docker containers (https://github.com/COMBAT-TB/irida-galaxy-deploy).

IMPORTANCE While the reduction in the cost of WGS is making sequencing more affordable in lower- and middle-income countries (LMICs), public health laboratories in these countries seldom have access to bioinformaticians and system support engineers adept at using the Linux command line and complex bioinformatics software. The COMBAT-TB Workbench provides an open-source, modular, easy-to-deploy and -use environment for managing and analyzing M. tuberculosis WGS data and thereby makes WGS usable in practice in the LMIC context.

Demographic Reporting in Publicly Available Chest Radiograph Data Sets: Opportunities for Mitigating Sex and Racial Disparities in Deep Learning Models

OBJECTIVE

Data sets with demographic imbalances can introduce bias in deep learning models and potentially amplify existing health disparities. We evaluated the reporting of demographics and potential biases in publicly available chest radiograph (CXR) data sets.

METHODS

We reviewed publicly available CXR data sets available on February 1, 2021, with >100 CXRs and performed a thorough search of various repositories, including Radiopaedia and Kaggle. For each data set, we recorded the total number of images and whether the data set reported demographic variables (age, race or ethnicity, sex, insurance status) in aggregate and on an image-level basis.

RESULTS

Twenty-three CXR data sets were included (range, 105-371,858 images). Most data sets reported demographics in some form (19 of 23; 82.6%) and on an image level (17 of 23; 73.9%). The majority reported age (19 of 23; 82.6%) and sex (18 of 23; 78.2%), but a minority reported race or ethnicity (2 of 23; 8.7%) and insurance status (1 of 23; 4.3%). Of the 13 data sets with sex distribution readily available, the average breakdown was 55.2% male subjects, ranging from 47.8% to 69.7% male representation. Of these, 8 (61.5%) overrepresented male subjects and 5 (38.5%) overrepresented female subjects.

DISCUSSION

Although most publicly available CXR data sets report age and sex on an image-basis level, few report race or ethnicity and insurance status. Furthermore, these data sets frequently underrepresent one of the sexes, more frequently the female sex. We recommend that data sets report standard demographic variables, and when possible, balance demographic representation to mitigate bias. Furthermore, for researchers using these data sets, we recommend that attention be paid to balancing demographic labels in addition to disease labels, as well as developing training methods that can account for these imbalances.

Generalization Challenges in Drug-Resistant Tuberculosis Detection from Chest X-rays

Classification of drug-resistant tuberculosis (DR-TB) and drug-sensitive tuberculosis (DS-TB) from chest radiographs remains an open problem. Our previous cross validation performance on publicly available chest X-ray (CXR) data combined with image augmentation, the addition of synthetically generated and publicly available images achieved a performance of 85% AUC with a deep convolutional neural network (CNN). However, when we evaluated the CNN model trained to classify DR-TB and DS-TB on unseen data, significant performance degradation was observed (65% AUC). Hence, in this paper, we investigate the generalizability of our models on images from a held out country's dataset. We explore the extent of the problem and the possible reasons behind the lack of good generalization. A comparison of radiologist-annotated lesion locations in the lung and the trained model's localization of areas of interest, using GradCAM, did not show much overlap. Using the same network architecture, a multi-country classifier was able to identify the country of origin of the X-ray with high accuracy (86%), suggesting that image acquisition differences and the distribution of non-pathological and non-anatomical aspects of the images are affecting the generalization and localization of the drug resistance classification model as well. When CXR images were severely corrupted, the performance on the validation set was still better than 60% AUC. The model overfitted to the data from countries in the cross validation set but did not generalize to the held out country. Finally, we applied a multi-task based approach that uses prior TB lesions location information to guide the classifier network to focus its attention on improving the generalization performance on the held out set from another country to 68% AUC.

Bridging gaps between images and data: a systematic update on imaging biobanks

BACKGROUND AND OBJECTIVE

The systematic collection of medical images combined with imaging biomarkers and patient non-imaging data is the core concept of imaging biobanks, a key element for fuelling the development of modern precision medicine. Our purpose is to review the existing image repositories fulfilling the criteria for imaging biobanks.

METHODS

Pubmed, Scopus and Web of Science were searched for articles published in English from January 2010 to July 2021 using a combination of the terms: "imaging" AND "biobanks" and "imaging" AND "repository". Moreover, the Community Research and Development Information Service (CORDIS) database ( https://cordis.europa.eu/projects ) was searched using the terms: "imaging" AND "biobanks", also including collections, projects, project deliverables, project publications and programmes.

RESULTS

Of 9272 articles retrieved, only 54 related to biobanks containing imaging data were finally selected, of which 33 were disease-oriented (61.1%) and 21 population-based (38.9%). Most imaging biobanks were European (26/54, 48.1%), followed by American biobanks (20/54, 37.0%). Among disease-oriented biobanks, the majority were focused on neurodegenerative (9/33, 27.3%) and oncological diseases (9/33, 27.3%). The number of patients enrolled ranged from 240 to 3,370,929, and the imaging modality most frequently involved was MRI (40/54, 74.1%), followed by CT (20/54, 37.0%), PET (13/54, 24.1%), and ultrasound (12/54, 22.2%). Most biobanks (38/54, 70.4%) were accessible under request.

CONCLUSIONS

Imaging biobanks can serve as a platform for collecting, sharing and analysing medical images integrated with imaging biomarkers, biological and clinical data. A relatively small proportion of current biobanks also contain images and can thus be classified as imaging biobanks.

KEY POINTS

• Imaging biobanks are a powerful tool for large-scale collection and processing of medical images integrated with imaging biomarkers and patient non-imaging data. • Most imaging biobanks retrieved were European, disease-oriented and accessible under user request. • While many biobanks have been developed so far, only a relatively small proportion of them are imaging biobanks.

Differentiating between drug-sensitive and drug-resistant tuberculosis with machine learning for clinical and radiological features

Background

Tuberculosis (TB) drug resistance is a worldwide public health problem that threatens progress made in TB care and control. Early detection of drug resistance is important for disease control, with discrimination between drug-resistant TB (DR-TB) and drug-sensitive TB (DS-TB) still being an open problem. The objective of this work is to investigate the relevance of readily available clinical data and data derived from chest X-rays (CXRs) in DR-TB prediction and to investigate the possibility of applying machine learning techniques to selected clinical and radiological features for discrimination between DR-TB and DS-TB. We hypothesize that the number of sextants affected by abnormalities such as nodule, cavity, collapse and infiltrate may serve as a radiological feature for DR-TB identification, and that both clinical and radiological features are important factors for machine classification of DR-TB and DS-TB.

Methods

We use data from the NIAID TB Portals program (https://tbportals.niaid.nih.gov), 1,455 DR-TB cases and 782 DS-TB cases from 11 countries. We first select three clinical features and 26 radiological features from the dataset. Then, we perform Pearson's chi-squared test to analyze the significance of the selected clinical and radiological features. Finally, we train machine classifiers based on different features and evaluate their ability to differentiate between DR-TB and DS-TB.

Results

Pearson's chi-squared test shows that two clinical features and 23 radiological features are statistically significant regarding DR-TB vs. DS-TB. A ten-fold cross-validation using a support vector machine shows that automatic discrimination between DR-TB and DS-TB achieves an average accuracy of 72.34% and an average AUC value of 78.42%, when combing all 25 statistically significant features.

Conclusions

Our study suggests that the number of affected lung sextants can be used for predicting DR-TB, and that automatic discrimination between DR-TB and DS-TB is possible, with a combination of clinical features and radiological features providing the best performance.

Tuberculosis drug resistance profiling based on machine learning: A literature review

Tuberculosis (TB), caused by Mycobacterium tuberculosis (MTB), is one of the top 10 causes of death worldwide. Drug-resistant tuberculosis (DR-TB) poses a major threat to the World Health Organization's "End TB" strategy which has defined its target as the year 2035. In 2019, there were close to 0.5 million cases of DRTB, of which 78% were resistant to multiple TB drugs. The traditional culture-based drug susceptibility test (DST - the current gold standard) often takes multiple weeks and the necessary laboratory facilities are not readily available in low-income countries. Whole genome sequencing (WGS) technology is rapidly becoming an important tool in clinical and research applications including transmission detection or prediction of DR-TB. For the latter, many tools have recently been developed using curated database(s) of known resistance conferring mutations. However, documenting all the mutations and their effect is a time-taking and a continuous process and therefore Machine Learning (ML) techniques can be useful for predicting the presence of DR-TB based on WGS data. This can pave the way to an earlier detection of drug resistance and consequently more efficient treatment when compared to the traditional DST.

On the Influence of the Quality of Databases of X-Ray Images of Patients with Tuberculosis on the Diagnostics of Deceases

The reliability of the training samples used for training convolutional neural networks applied for diagnostics of lung diseases has been investigated. By the example of the Kaggle database, it has been shown that the sample containing 3500 roentgenograms of healthy people and 3500 roentgenograms of patients with tuberculosis is very inhomogeneous. When training by using different parts of the sample and recognizing its different parts, the results obtained are significantly different.

Drug Discovery for Mycobacterium tuberculosis Using Structure-Based Computer-Aided Drug Design Approach

Developing new, more effective antibiotics against resistant Mycobacterium tuberculosis that inhibit its essential proteins is an appealing strategy for combating the global tuberculosis (TB) epidemic. Finding a compound that can target a particular cavity in a protein and interrupt its enzymatic activity is the crucial objective of drug design and discovery. Such a compound is then subjected to different tests, including clinical trials, to study its effectiveness against the pathogen in the host. In recent times, new techniques, which involve computational and analytical methods, enhanced the chances of drug development, as opposed to traditional drug design methods, which are laborious and time-consuming. The computational techniques in drug design have been improved with a new generation of software used to develop and optimize active compounds that can be used in future chemotherapeutic development to combat global tuberculosis resistance. This review provides an overview of the evolution of tuberculosis resistance, existing drug management, and the design of new anti-tuberculosis drugs developed based on the contributions of computational techniques. Also, we show an appraisal of available software and databases on computational drug design with an insight into the application of this software and databases in the development of anti-tubercular drugs. The review features a perspective involving machine learning, artificial intelligence, quantum computing, and CRISPR combination with available computational techniques as a prospective pathway to design new anti-tubercular drugs to combat resistant tuberculosis.

A new nomenclature for the livestock-associated Mycobacterium tuberculosis complex based on phylogenomics

Background:  The bacteria that compose the Mycobacterium tuberculosis complex (MTBC) cause tuberculosis (TB) in humans and in different animals, including livestock. Much progress has been made in understanding the population structure of the human-adapted members of the MTBC by combining phylogenetics with genomics. Accompanying the discovery of new genetic diversity, a body of operational nomenclature has evolved to assist comparative and molecular epidemiological studies of human TB. By contrast, for the livestock-associated MTBC members, Mycobacterium bovis, M. caprae and M. orygis, there has been a lack of comprehensive nomenclature to accommodate new genetic diversity uncovered by emerging phylogenomic studies. We propose to fill this gap by putting forward a new nomenclature covering the main phylogenetic groups within M. bovis, M. caprae and M. orygis. Methods:  We gathered a total of 8,736 whole-genome sequences (WGS) from public sources and 39 newly sequenced strains, and selected a subset of 829 WGS, representative of the worldwide diversity of M. bovis, M. caprae and M. orygis. We used phylogenetics and genetic diversity patterns inferred from WGS to define groups. Results:  We propose to divide M. bovis, M. caprae and M. orygis in three main phylogenetic lineages, which we named La1, La2 and La3, respectively. Within La1, we identified several monophyletic groups, which we propose to classify into eight sublineages (La1.1-La1.8). These sublineages differed in geographic distribution, with some being geographically restricted and others globally widespread, suggesting different expansion abilities. To ease molecular characterization of these MTBC groups by the community, we provide phylogenetically informed, single nucleotide polymorphisms that can be used as barcodes for genotyping. These markers were implemented in KvarQ and TB-Profiler, which are platform-independent, open-source tools. Conclusions:  Our results contribute to an improved classification of the genetic diversity within the livestock-associated MTBC, which will benefit future molecular epidemiological and evolutionary studies.

Advancing TB research using digitized programmatic data

The use of real-world data from national TB care programs has great potential to answer key research questions in TB control and is now opportune due to increasing digital data collection and storage. We summarize an expert stakeholder workshop conducted on this topic in October 2019, with perspectives from academics, national TB program officers, and data managers. We discuss challenges and opportunities in the use of TB programmatic data for research and describe digital data availability in two large, high TB burden countries, Brazil and South Africa. From this, we posit that with a standardized data collection set, improved data management, and greater collaboration, more TB programmatic data can be used for research with measurable public health impact.

Artificial intelligence and machine learning assisted drug delivery for effective treatment of infectious diseases

In the era of antimicrobial resistance, the prevalence of multidrug-resistant microorganisms that resist conventional antibiotic treatment has steadily increased. Thus, it is now unquestionable that infectious diseases are significant global burdens that urgently require innovative treatment strategies. Emerging studies have demonstrated that artificial intelligence (AI) can transform drug delivery to promote effective treatment of infectious diseases. In this review, we propose to evaluate the significance, essential principles, and popular tools of AI in drug delivery for infectious disease treatment. Specifically, we will focus on the achievements and key findings of current research, as well as the applications of AI on drug delivery throughout the whole antimicrobial treatment process, with an emphasis on drug development, treatment regimen optimization, drug delivery system and administration route design, and drug delivery outcome prediction. To that end, the challenges of AI in drug delivery for infectious disease treatments and their current solutions and future perspective will be presented and discussed.

Identifying Drug-Resistant Tuberculosis in Chest Radiographs: Evaluation of CNN Architectures and Training Strategies

Tuberculosis (TB) is a serious infectious disease that mainly affects the lungs. Drug resistance to the disease makes it more challenging to control. Early diagnosis of drug resistance can help with decision making resulting in appropriate and successful treatment. Chest X-rays (CXRs) have been pivotal to identifying tuberculosis and are widely available. In this work, we utilize CXRs to distinguish between drug-resistant and drug-sensitive tuberculosis. We incorporate Convolutional Neural Network (CNN) based models to discriminate the two types of TB, and employ standard and deep learning based data augmentation methods to improve the classification. Using labeled data from NIAID TB Portals and additional non-labeled sources, we were able to achieve an Area Under the ROC Curve (AUC) of up to 85% using a pretrained InceptionV3 network.

Evolution and emergence of multidrug-resistant Mycobacterium tuberculosis in Chisinau, Moldova

The evolution and emergence of drug-resistant tuberculosis (TB) has been studied extensively in some contexts, but the ecological drivers of these two processes remain poorly understood. This study sought to describe the joint evolutionary and epidemiological histories of a novel multidrug-resistant Mycobacterium tuberculosis strain recently identified in the capital city of the Republic of Moldova (MDR Ural/4.2), where genomic surveillance of drug-resistant M. tuberculosis has been limited thus far. Using whole genome sequence data and Bayesian phylogenomic methods, we reconstruct the stepwise acquisition of drug resistance mutations in the MDR Ural/4.2 strain, estimate its historical bacterial population size over time, and infer the migration history of this strain between Eastern European countries. We infer that MDR Ural/4.2 likely evolved (via acquisition of rpoB S450L, which confers resistance to rifampin) in the early 1990s, during a period of social turmoil following Moldovan independence from the Soviet Union. This strain subsequently underwent substantial population size expansion in the early 2000s, at a time when national guidelines encouraged inpatient treatment of TB patients. We infer exportation of this strain and its isoniazid-resistant ancestral precursor from Moldova to neighbouring countries starting as early as 1985. Our findings suggest temporal and ecological associations between specific public health practices, including inpatient hospitalization of drug-resistant TB cases from the early 2000s until 2013, and the evolution of drug-resistant M. tuberculosis in Moldova. These findings underscore the need for regional coordination in TB control and expanded genomic surveillance efforts across Eastern Europe.

Improving tuberculosis surveillance by detecting international transmission using publicly available whole genome sequencing data

IntroductionImproving the surveillance of tuberculosis (TB) is especially important for multidrug-resistant (MDR) and extensively drug-resistant (XDR) TB. The large amount of publicly available whole genome sequencing (WGS) data for TB gives us the chance to re-use data and to perform additional analyses at a large scale.AimWe assessed the usefulness of raw WGS data of global MDR/XDR Mycobacterium tuberculosis isolates available from public repositories to improve TB surveillance.MethodsWe extracted raw WGS data and the related metadata of M. tuberculosis isolates available from the Sequence Read Archive. We compared this public dataset with WGS data and metadata of 131 MDR- and XDR M. tuberculosis isolates from Germany in 2012 and 2013.ResultsWe aggregated a dataset that included 1,081 MDR and 250 XDR isolates among which we identified 133 molecular clusters. In 16 clusters, the isolates were from at least two different countries. For example, Cluster 2 included 56 MDR/XDR isolates from Moldova, Georgia and Germany. When comparing the WGS data from Germany with the public dataset, we found that 11 clusters contained at least one isolate from Germany and at least one isolate from another country. We could, therefore, connect TB cases despite missing epidemiological information.ConclusionWe demonstrated the added value of using WGS raw data from public repositories to contribute to TB surveillance. Comparing the German with the public dataset, we identified potential international transmission events. Thus, using this approach might support the interpretation of national surveillance results in an international context.

Genomic analyses of Mycobacterium tuberculosis from human lung resections reveal a high frequency of polyclonal infections

Polyclonal infections occur when at least two unrelated strains of the same pathogen are detected in an individual. This has been linked to worse clinical outcomes in tuberculosis, as undetected strains with different antibiotic resistance profiles can lead to treatment failure. Here, we examine the amount of polyclonal infections in sputum and surgical resections from patients with tuberculosis in the country of Georgia. For this purpose, we sequence and analyse the genomes of Mycobacterium tuberculosis isolated from the samples, acquired through an observational clinical study (NCT02715271). Access to the lung enhanced the detection of multiple strains (40% of surgery cases) as opposed to just using a sputum sample (0-5% in the general population). We show that polyclonal infections often involve genetically distant strains and can be associated with reversion of the patient's drug susceptibility profile over time. In addition, we find different patterns of genetic diversity within lesions and across patients, including mutational signatures known to be associated with oxidative damage; this suggests that reactive oxygen species may be acting as a selective pressure in the granuloma environment. Our results support the idea that the magnitude of polyclonal infections in high-burden tuberculosis settings is underestimated when only testing sputum samples.

A Permissioned Blockchain Network for Security and Sharing of De-identified Tuberculosis Research Data in Brazil

BACKGROUND

Tuberculosis (TB) is an infectious disease and is among the top 10 causes of death in the world, and Brazil is part of the top 30 high TB burden countries. Data collection is an essential practice in health studies, and the adoption of electronic data capture (EDC) systems can positively increase the experience of data acquisition and analysis. Also, data-sharing capabilities are crucial to the construction of efficient and effective evidence-based decision-making tools for managerial and operational actions in TB services. Data must be held secure and traceable, as well as available and understandable, for authorized parties.

OBJECTIVES

In this sense, this work aims to propose a blockchain-based approach to build a reusable, decentralized, and de-identified dataset of TB research data, while increasing transparency, accountability, availability, and integrity of raw data collected in EDC systems.

METHODS

After identifying challenges and gaps, a solution was proposed to tackle them, considering its relevance for TB studies. Data security issues are being addressed by a blockchain network and a lightweight and practical governance model. Research Electronic Data Capture (REDCap) and KoBoToolbox are used as EDC systems in TB research. Mechanisms to de-identify data and aggregate semantics to data are also available.

RESULTS

A permissioned blockchain network was built using Kaleido platform. An integration engine integrates the EDC systems with the blockchain network, performing de-identification and aggregating meaning to data. A governance model addresses operational and legal issues for the proper use of data. Finally, a management system facilitates the handling of necessary metadata, and additional applications are available to explore the blockchain and export data.

CONCLUSIONS

Research data are an important asset not only for the research where it was generated, but also to underpin studies replication and support further investigations. The proposed solution allows the delivery of de-identified databases built in real time by storing data in transactions of a permissioned network, including semantic annotations, as data are being collected in TB research. The governance model promotes the correct use of the solution.

Radiologist observations of computed tomography (CT) images predict treatment outcome in TB Portals, a real-world database of tuberculosis (TB) cases

The TB Portals program provides a publicly accessible repository of TB case data containing multi-modal information such as case clinical characteristics, pathogen genomics, and radiomics. The real-world resource contains over 3400 TB cases, primarily drug resistant cases, and CT images with radiologist annotations are available for many of these cases. The breadth of data collected offers a patient-centric view into the etiology of the disease including the temporal context of the available imaging information. Here, we analyze a cohort of new TB cases with available radiologist observations of CTs taken around the time of initial registration of the case into the database and with available follow up to treatment outcome of cured or died. Follow up ranged from 5 weeks to a little over 2 years consistent with the longest treatment regimens for drug resistant TB and cases were registered within the years 2008 to 2019. The radiologist observations were incorporated into machine learning pipelines to test various class balancing strategies on the performance of predictive models. The modeling results support that the radiologist observations are predictive of treatment outcome. Moreover, inferential statistical analysis identifies markers of TB disease spread as having an association with poor treatment outcome including presence of radiologist observations in both lungs, swollen lymph nodes, multiple cavities, and large cavities. While the initial results are promising, further data collection is needed to incorporate methods to mitigate potential confounding such as including additional model covariates or matching cohorts on covariates of interest (e.g. demographics, BMI, comorbidity, TB subtype, etc.). Nonetheless, the preliminary results highlight the utility of the resource for hypothesis generation and exploration of potential biomarkers of TB disease severity and support these additional data collection efforts.