Computer aided detection of tuberculosis on chest radiographs: An evaluation of the CAD4TB v6 system

A deep learning-based algorithm for pulmonary tuberculosis detection in chest radiography

In tuberculosis (TB), chest radiography (CXR) patterns are highly variable, mimicking pneumonia and many other diseases. This study aims to evaluate the efficacy of Google teachable machine, a deep neural network-based image classification tool, to develop algorithm for predicting TB probability of CXRs. The training dataset included 348 TB CXRs and 3806 normal CXRs for training TB detection. We also collected 1150 abnormal CXRs and 627 normal CXRs for training abnormality detection. For external validation, we collected 250 CXRs from our hospital. We also compared the accuracy of the algorithm to five pulmonologists and radiological reports. In external validation, the AI algorithm showed areas under the curve (AUC) of 0.951 and 0.975 in validation dataset 1 and 2. The accuracy of the pulmonologists on validation dataset 2 showed AUC range of 0.936-0.995. When abnormal CXRs other than TB were added, AUC decreased in both human readers (0.843-0.888) and AI algorithm (0.828). When combine human readers with AI algorithm, the AUC further increased to 0.862-0.885. The TB CXR AI algorithm developed by using Google teachable machine in this study is effective, with the accuracy close to experienced clinical physicians, and may be helpful for detecting tuberculosis by CXR.

Tuberculosis treatment-shortening

Tuberculosis (TB) presents a significant global health concern, with ∼10 million people developing TB and 1.3 million people dying from the disease each year. The standard treatment regimen for drug-susceptible TB was between 6 and 9 months until recently, presenting a prolonged therapeutic duration compared with other infectious diseases. This is a long time for patients to adhere to the medication, consequently increasing the risk of developing drug-resistant Mycobacterium tuberculosis - a significant challenge in TB management globally. Therefore, the primary objective of contemporary TB drug development research is to shorten the treatment duration. This review comprehensively explores the strategies aimed at shortening TB treatment.

Deep Learning-Based Classification and Semantic Segmentation of Lung Tuberculosis Lesions in Chest X-ray Images

We present a deep learning (DL) network-based approach for detecting and semantically segmenting two specific types of tuberculosis (TB) lesions in chest X-ray (CXR) images. In the proposed method, we use a basic U-Net model and its enhanced versions to detect, classify, and segment TB lesions in CXR images. The model architectures used in this study are U-Net, Attention U-Net, U-Net++, Attention U-Net++, and pyramid spatial pooling (PSP) Attention U-Net++, which are optimized and compared based on the test results of each model to find the best parameters. Finally, we use four ensemble approaches which combine the top five models to further improve lesion classification and segmentation results. In the training stage, we use data augmentation and preprocessing methods to increase the number and strength of lesion features in CXR images, respectively. Our dataset consists of 110 training, 14 validation, and 98 test images. The experimental results show that the proposed ensemble model achieves a maximum mean intersection-over-union (MIoU) of 0.70, a mean precision rate of 0.88, a mean recall rate of 0.75, a mean F1-score of 0.81, and an accuracy of 1.0, which are all better than those of only using a single-network model. The proposed method can be used by clinicians as a diagnostic tool assisting in the examination of TB lesions in CXR images.

C-reactive protein-based tuberculosis triage testing: a multi-country diagnostic accuracy study

Rationale

C-reactive protein (CRP)-based tuberculosis (TB) screening is recommended for people with HIV (PWH). However, its performance among people without HIV and in diverse settings is unknown.

Objectives

In a multi-country study, we aimed to determine whether CRP meets the minimum accuracy targets (sensitivity ≥90%, specificity ≥70%) for an effective TB triage test.

Methods/Measurements

Consecutive outpatient adults with cough ≥2 weeks from five TB endemic countries in Africa and Asia had baseline blood collected for point-of-care CRP testing and HIV and diabetes screening. Sputum samples were collected for Xpert MTB/RIF Ultra (Xpert) testing and culture. CRP sensitivity and specificity (5 mg/L cut-point) was determined in reference to sputum test results and compared by country, sex, and HIV and diabetes status. Variables affecting CRP performance were identified using a multivariate receiver operating characteristic (ROC) regression model.

Results

Among 2904 participants, of whom 613 (21%) had microbiologically-confirmed TB, CRP sensitivity was 84% (95% CI: 81-87%) and specificity was 61% (95% CI: 59-63%). CRP accuracy varied geographically, with higher sensitivity in African countries (≥91%) than Asian countries (64-82%). Sensitivity was higher among men than women (87% vs. 79%, difference +8%, 95% CI: 1-15%) and specificity was higher among people without HIV than PWH (64% vs. 45%, difference +19%, 95% CI: 13-25%). ROC regression identified country and measures of TB disease severity as predictors of CRP performance.

Conclusions

Overall, CRP did not achieve the minimum accuracy targets and its performance varied by setting and in some sub-groups, likely reflecting population differences in mycobacterial load.

AI for Detection of Tuberculosis: Implications for Global Health

Tuberculosis, which primarily affects developing countries, remains a significant global health concern. Since the 2010s, the role of chest radiography has expanded in tuberculosis triage and screening beyond its traditional complementary role in the diagnosis of tuberculosis. Computer-aided diagnosis (CAD) systems for tuberculosis detection on chest radiographs have recently made substantial progress in diagnostic performance, thanks to deep learning technologies. The current performance of CAD systems for tuberculosis has approximated that of human experts, presenting a potential solution to the shortage of human readers to interpret chest radiographs in low- or middle-income, high-tuberculosis-burden countries. This article provides a critical appraisal of developmental process reporting in extant CAD software for tuberculosis, based on the Checklist for Artificial Intelligence in Medical Imaging. It also explores several considerations to scale up CAD solutions, encompassing manufacturer-independent CAD validation, economic and political aspects, and ethical concerns, as well as the potential for broadening radiography-based diagnosis to other nontuberculosis diseases. Collectively, CAD for tuberculosis will emerge as a representative deep learning application, catalyzing advances in global health and health equity. Keywords: Computer-aided Diagnosis (CAD), Conventional Radiography, Thorax, Lung, Machine Learning Supplemental material is available for this article. © RSNA, 2024.

Diagnostic Accuracy of Computer-Aided Detection During Active Case Finding for Pulmonary Tuberculosis in Africa: A Systematic Review and Meta-analysis

Background

Computer-aided detection (CAD) may be a useful screening tool for tuberculosis (TB). However, there are limited data about its utility in active case finding (ACF) in a community-based setting, and particularly in an HIV-endemic setting where performance may be compromised.

Methods

We performed a systematic review and evaluated articles published between January 2012 and February 2023 that included CAD as a screening tool to detect pulmonary TB against a microbiological reference standard (sputum culture and/or nucleic acid amplification test [NAAT]). We collected and summarized data on study characteristics and diagnostic accuracy measures. Two reviewers independently extracted data and assessed methodological quality against Quality Assessment of Diagnostic Accuracy Studies-2 criteria. Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Diagnostic Test Accuracy Studies (PRISMA-DTA) guidelines were followed.

Results

Of 1748 articles reviewed, 5 met with the eligibility criteria and were included in this review. A meta-analysis revealed pooled sensitivity of 0.87 (95% CI, 0.78-0.96) and specificity of 0.74 (95% CI, 0.55-0.93), just below the World Health Organization (WHO)-recommended target product profile (TPP) for a screening test (sensitivity ≥0.90 and specificity ≥0.70). We found a high risk of bias and applicability concerns across all studies. Subgroup analyses, including the impact of HIV and previous TB, were not possible due to the nature of the reporting within the included studies.

Conclusions

This review provides evidence, specifically in the context of ACF, for CAD as a potentially useful and cost-effective screening tool for TB in a resource-poor HIV-endemic African setting. However, given methodological concerns, caution is required with regards to applicability and generalizability.

Computer-aided detection thresholds for digital chest radiography interpretation in tuberculosis diagnostic algorithms

Objectives

Use of computer-aided detection (CAD) software is recommended to improve tuberculosis screening and triage, but threshold determination is challenging if reference testing has not been performed in all individuals. We aimed to determine such thresholds through secondary analysis of the 2019 Lesotho national tuberculosis prevalence survey.

Methods

Symptom screening and chest radiographs were performed in participants aged ≥15 years; those symptomatic or with abnormal chest radiographs provided samples for Xpert MTB/RIF and culture testing. Chest radiographs were processed using CAD4TB version 7. We used six methodological approaches to deal with participants who did not have bacteriological test results to estimate pulmonary tuberculosis prevalence and assess diagnostic accuracy.

Results

Among 17 070 participants, 5214 (31%) had their tuberculosis status determined; 142 had tuberculosis. Prevalence estimates varied between methodological approaches (0.83-2.72%). Using multiple imputation to estimate tuberculosis status for those eligible but not tested, and assuming those not eligible for testing were negative, a CAD4TBv7 threshold of 13 had a sensitivity of 89.7% (95% CI 84.6-94.8) and a specificity of 74.2% (73.6-74.9), close to World Health Organization (WHO) target product profile criteria. Assuming all those not tested were negative produced similar results.

Conclusions

This is the first study to evaluate CAD4TB in a community screening context employing a range of approaches to account for unknown tuberculosis status. The assumption that those not tested are negative - regardless of testing eligibility status - was robust. As threshold determination must be context specific, our analytically straightforward approach should be adopted to leverage prevalence surveys for CAD threshold determination in other settings with a comparable proportion of eligible but not tested participants.

Active close contact investigation of tuberculosis through computer-aided detection and stool Xpert MTB/RIF among people living in Oromia Region, Ethiopia (CADOOL Study): protocol for a prospective, cross-sectional study

INTRODUCTION

Pulmonary tuberculosis (TB) is an infectious disease with high incidence in low-income countries (LICs); it remains one of the infectious diseases with the highest mortality in the world, especially in LICs. It is crucial to recognise and diagnose TB as soon as possible, but microbiological tests on sputum are not always sensitive enough. New methods for an early diagnosis of TB are needed. In this study, we will investigate the role of two different tests to detect TB in Ethiopia (where the prevalence of TB is high): molecular search for TB in stool samples with Xpert assay and detection of pulmonary TB signs on chest X-rays with CAD4TB technology.

METHODS AND ANALYSIS

A prospective diagnostic test accuracy study during TB active contact investigation will be conducted. In the referral hospital in Southwest Shoa Zone, Oromia Region, Ethiopia, patients with pulmonary TB and a sputum sample positive for Mycobacterium tuberculosis and household contacts of at least 4 years of age will be enrolled, with a target sample size of 231 patients. Trained staff will label household contacts as 'possible TB' cases or not according to their symptoms; when TB is possible, a stool Xpert and computer-aided detection on chest X-ray will be performed, alongside standard diagnostic methods, assessing the diagnostic accuracy of CAD4TB compared with Xpert MTB/RIF during TB contact investigation and the accuracy of stool Xpert compared with sputum Xpert.

ETHICS AND DISSEMINATION

This study has been approved by the Oromia Health Bureau Research Ethics Committee (ref no BFO/MBTFH/1-16/100023). All information obtained will be kept confidential. Selected investigators will have access to data, while international partners will sign a dedicated data protection agreement. Eligible participants will receive brief information about the study before being asked to participate and they will provide written informed consent. Results will be disseminated through peer-reviewed journals.

TRIAL REGISTRATION NUMBER

NCT05818059.

Homogenization of multi-institutional chest x-ray images in various data transformation schemes

Purpose

Although there are several options for improving the generalizability of learned models, a data instance-based approach is desirable when stable data acquisition conditions cannot be guaranteed. Despite the wide use of data transformation methods to reduce data discrepancies between different data domains, detailed analysis for explaining the performance of data transformation methods is lacking.

Approach

This study compares several data transformation methods in the tuberculosis detection task with multi-institutional chest x-ray (CXR) data. Five different data transformations, including normalization, standardization with and without lung masking, and multi-frequency-based (MFB) standardization with and without lung masking were implemented. A tuberculosis detection network was trained using a reference dataset, and the data from six other sites were used for the network performance comparison. To analyze data harmonization performance, we extracted radiomic features and calculated the Mahalanobis distance. We visualized the features with a dimensionality reduction technique. Through similar methods, deep features of the trained networks were also analyzed to examine the models' responses to the data from various sites.

Results

From various numerical assessments, the MFB standardization with lung masking provided the highest network performance for the non-reference datasets. From the radiomic and deep feature analyses, the features of the multi-site CXRs after MFB with lung masking were found to be well homogenized to the reference data, whereas the others showed limited performance.

Conclusions

Conventional normalization and standardization showed suboptimal performance in minimizing feature differences among various sites. Our study emphasizes the strengths of MFB standardization with lung masking in terms of network performance and feature homogenization.

Computer-Aided Detection for Chest Radiography to Improve the Quality of Tuberculosis Diagnosis in Vietnam's District Health Facilities: An Implementation Study

In Vietnam, chest radiography (CXR) is used to refer people for GeneXpert (Xpert) testing to diagnose tuberculosis (TB), demonstrating high yield for TB but a wide range of CXR abnormality rates. In a multi-center implementation study, computer-aided detection (CAD) was integrated into facility-based TB case finding to standardize CXR interpretation. CAD integration was guided by a programmatic framework developed for routine implementation. From April through December 2022, 24,945 CXRs from TB-vulnerable populations presenting to district health facilities were evaluated. Physicians interpreted all CXRs in parallel with CAD (qXR 3.0) software, for which the selected TB threshold score was ≥0.60. At three months, there was 47.3% concordance between physician and CAD TB-presumptive CXR results, 7.8% of individuals who received CXRs were referred for Xpert testing, and 858 people diagnosed with Xpert-confirmed TB per 100,000 CXRs. This increased at nine months to 76.1% concordant physician and CAD TB-presumptive CXRs, 9.6% referred for Xpert testing, and 2112 people with Xpert-confirmed TB per 100,000 CXRs. Our programmatic CAD-CXR framework effectively supported physicians in district facilities to improve the quality of referral for diagnostic testing and increase TB detection yield. Concordance between physician and CAD CXR results improved with training and was important to optimize Xpert testing.

Computer-aided diagnostic accuracy of pulmonary tuberculosis on chest radiography among lower respiratory tract symptoms patients

Even though the Gaza Strip is a low pulmonary tuberculosis (TB) burden region, it is well-known that TB is primarily a socioeconomic problem associated with overcrowding, poor hygiene, a lack of fresh water, and limited access to healthcare, which is the typical case in the Gaza Strip. Therefore, this study aimed at assessing the accuracy of the automatic software computer-aided detection for tuberculosis (CAD4TB) in diagnosing pulmonary TB on chest radiography and compare the CAD4TB software reading with the results of geneXpert. Using a census sampling method, the study was conducted in radiology departments in the Gaza Strip hospitals between 1 December 2022 and 31 March 2023. A digital X-ray, printer, and online X-ray system backed by CAD4TBv6 software were used to screen patients with lower respiratory tract symptoms. GeneXpert analysis was performed for all patients having a score > 40. A total of 1,237 patients presenting with lower respiratory tract symptoms participated in this current study. Chest X-ray readings showed that 7.8% (n = 96) were presumptive for TB. The CAD4TBv6 scores showed that 11.8% (n = 146) of recruited patients were presumptive for TB. GeneXpert testing on sputum samples showed that 6.2% (n = 77) of those with a score > 40 on CAD4TB were positive for pulmonary TB. Significant differences were found in chest X-ray readings, CAD4TBv6 scores, and GeneXpert results among sociodemographic and health status variables (P-value < 0.05). The study showed that the incidence rate of TB in the Gaza Strip is 3.5 per 100,000 population in the Gaza strip. The sensitivity of the CAD4TBv6 score and the symptomatic review for tuberculosis with a threshold score of >40 is 80.2%, and the specificity is 94.0%. The positive Likelihood Ratio is 13.3%, Negative Likelihood Ratio is 0.2 with 7.8% prevalence. Positive Predictive Value is 52.7%, Negative Predictive Value is 98.3%, and accuracy is 92.9%. In a resource-limited country with a high burden of neglected disease, combining chest X-ray readings by CAD4TB and symptomatology is extremely valuable for screening a population at risk. CAD4TB is noticeably more efficient than other methods for TB screening and early diagnosis in people who would otherwise go undetected.

Improving TB control: efficiencies of case-finding interventions in Nigeria

SETTING

KNCV Nigeria implements seven key TB case-finding interventions. It was critical to evaluate the efficiency of these interventions in terms of TB yield to direct future prioritisation in the country.

OBJECTIVES

To compare the efficiency of active case-finding (ACF) interventions for TB in Nigeria.

DESIGN

Data from the 2020-2022 implementing period were analysed retrospectively. Intervention efficiencies were analysed using the number needed to screen (NNS), the number needed to test (NNT) and the true screen-positive (TSP) rate.

RESULTS

Across the interventions, 21,704,669 persons were screened for TB, 1,834,447 (8.5%) were presumed to have TB (7.7% pre-diagnostic drop-out rate) and 122,452 were diagnosed with TB (TSP rate of 7.2%). The average TSP rate of interventions that used both the WHO four-symptom screen (W4SS) and portable digital X-ray (PDX) screening algorithm was significantly higher (22.6%) than those that employed the former alone (7.0%; OR 3.9, 95% CI 3.74-3.98; P < 0.001). The average NNT for interventions with W4SS/PDX screening was 4 (range: 4-5), while that of W4SS-only screening was 14 (range: 11-22).

CONCLUSIONS

Interventions using the PDX in addition to W4SS for TB screening were more efficient in terms of TB case yield than interventions that used symptom-based TB screening only.

Benchmarking the diagnostic test accuracy of certified AI products for screening pulmonary tuberculosis in digital chest radiographs: Preliminary evidence from a rapid review and meta-analysis

BACKGROUND AND OBJECTIVE

The global market for AI systems used in lung tuberculosis (TB) detection has expanded significantly in recent years. Verifying their performance across diverse settings is crucial before medical organisations can invest in them and pursue safe, wide-scale deployment. The goal of this research was to synthesise the clinical evidence for the diagnostic accuracy of certified AI products designed for screening TB in chest X-rays (CXRs) compared to a microbiological reference standard.

METHODS

Four databases were searched between June to September 2022. Data concerning study methodology, system characteristics, and diagnostic accuracy metrics was extracted and summarised. Study bias was evaluated using QUADAS-2 and by examining sources of funding. Forest plots for diagnostic odds ratio (DOR) and summary receiver operating characteristic (SROC) curves were constructed for the AI products individually and collectively.

RESULTS

10 out of 3642 studies satisfied the review criteria however only 8 were subject to meta-analysis following bias assessment. Three AI products were evaluated with a 95 % confidence interval producing the following pooled estimates for accuracy rankings: qXR v2 (sensitivity of 0.944 [0.887-0.973], specificity of 0.692 [0.549-0.805], DOR of 3.63 [3.17-4.09], Lunit INSIGHT CXR v3.1 (sensitivity of 0.853 [0.787-0.901], specificity of 0.646 [0.627-0.665], DOR of 2.37 [1.96-2.78]), and CAD4TB v3.07 (sensitivity of 0.917 [0.848-0.956], specificity of 0.371 [0.336-0.408], DOR of 1.91 [1.4-2.47]). Overall, the products had a sensitivity of 0.903 (0.859-0.934), specificity of 0.526 (0.409-0.641), and DOR of 2.31 (1.78-2.84).

CONCLUSION

Current publicly available evidence indicates considerable variability in the diagnostic accuracy of available AI products although overall they have high sensitivity and modest specificity which is improving with time. These preliminary results are limited by the small number of studies and poor coverage for low TB burden settings. More research is needed to expand the clinical evidence base for the performance of AI products.

Tuberculosis prevalence after 4 years of population-wide systematic TB symptom screening and universal testing and treatment for HIV in the HPTN 071 (PopART) community-randomised trial in Zambia and South Africa: A cross-sectional survey (TREATS)

BACKGROUND

Tuberculosis (TB) prevalence remains persistently high in many settings, with new or expanded interventions required to achieve substantial reductions. The HIV Prevention Trials Network (HPTN) 071 (PopART) community-randomised trial randomised 14 communities to receive the "PopART" intervention during 2014 to 2017 (7 arm A and 7 arm B communities) and 7 communities to receive standard-of-care (arm C). The intervention was delivered door-to-door by community HIV care providers (CHiPs) and included universal HIV testing, facilitated linkage to HIV care at government health clinics, and systematic TB symptom screening. The Tuberculosis Reduction through Expanded Anti-retroviral Treatment and Screening (TREATS) study aimed to measure the impact of delivering the PopART intervention on TB outcomes, in communities with high HIV and TB prevalence.

METHODS AND FINDINGS

The study population of the HPTN 071 (PopART) trial included individuals aged ≥15 years living in 21 urban and peri-urban communities in Zambia and South Africa, with a total population of approximately 1 million and an adult HIV prevalence of around 15% at the time of the trial. Two sputum samples for TB testing were provided to CHiPs by individuals who reported ≥1 TB suggestive symptom (a cough for ≥2 weeks, unintentional weight loss ≥1.5 kg in the last month, or current night sweats) or that a household member was currently on TB treatment. Antiretroviral therapy (ART) was offered universally at clinics in arm A and according to local guidelines in arms B and C. The TREATS study was conducted in the same 21 communities as the HPTN 071 (PopART) trial between 2017 and 2022, and TB prevalence was a co-primary endpoint of the TREATS study. The primary comparison was between the PopART intervention (arms A and B combined) and the standard-of-care (arm C). During 2019 to 2021, a TB prevalence survey was conducted among randomly selected individuals aged ≥15 years (approximately 1,750 per community in arms A and B, approximately 3,500 in arm C). Participants were screened on TB symptoms and chest X-ray, with diagnostic testing using Xpert-Ultra followed by culture for individuals who screened positive. Sputum eligibility was determined by the presence of a cough for ≥2 weeks, or ≥2 of 5 "TB suggestive" symptoms (cough, weight loss for ≥4 weeks, night sweats, chest pain, and fever for ≥2 weeks), or chest X-ray CAD4TBv5 score ≥50, or no available X-ray results. TB prevalence was compared between trial arms using standard methods for cluster-randomised trials, with adjustment for age, sex, and HIV status, and multiple imputation was used for missing data on prevalent TB. Among 83,092 individuals who were eligible for the survey, 49,556 (59.6%) participated, 8,083 (16.3%) screened positive, 90.8% (7,336/8,083) provided 2 sputum samples for Xpert-Ultra testing, and 308 (4.2%) required culture confirmation. Overall, estimated TB prevalence was 0.92% (457/49,556). The geometric means of 7 community-level prevalence estimates were 0.91%, 0.70%, and 0.69% in arms A, B, and C, respectively, with no evidence of a difference comparing arms A and B combined with arm C (adjusted prevalence ratio 1.14, 95% confidence interval, CI [0.67, 1.95], p = 0.60). TB prevalence was higher among people living with HIV than HIV-negative individuals, with an age-sex-community adjusted odds ratio of 2.29 [95% CI 1.54, 3.41] in Zambian communities and 1.61 [95% CI 1.13, 2.30] in South African communities. The primary limitations are that the study was powered to detect only large reductions in TB prevalence in the intervention arm compared with standard-of-care, and the between-community variation in TB prevalence was larger than anticipated.

CONCLUSIONS

There was no evidence that the PopART intervention reduced TB prevalence. Systematic screening for TB that is based on symptom screening alone may not be sufficient to achieve a large reduction in TB prevalence over a period of several years. Including chest X-ray screening alongside TB symptom screening could substantially increase the sensitivity of systematic screening for TB.

TRIAL REGISTRATION

The TREATS study was registered with ClinicalTrials.gov Identifier: NCT03739736 on November 14, 2018. The HPTN 071 (PopART) trial was registered at ClinicalTrials.gov under number NCT01900977 on July 17, 2013.

Incidental radiological findings during clinical tuberculosis screening in Lesotho and South Africa: a case series

BACKGROUND

Chest X-ray offers high sensitivity and acceptable specificity as a tuberculosis screening tool, but in areas with a high burden of tuberculosis, there is often a lack of radiological expertise to interpret chest X-ray. Computer-aided detection systems based on artificial intelligence are therefore increasingly used to screen for tuberculosis-related abnormalities on digital chest radiographies. The CAD4TB software has previously been shown to demonstrate high sensitivity for chest X-ray tuberculosis-related abnormalities, but it is not yet calibrated for the detection of non-tuberculosis abnormalities. When screening for tuberculosis, users of computer-aided detection need to be aware that other chest pathologies are likely to be as prevalent as, or more prevalent than, active tuberculosis. However, non--tuberculosis chest X-ray abnormalities detected during chest X-ray screening for tuberculosis remain poorly characterized in the sub-Saharan African setting, with only minimal literature.

CASE PRESENTATION

In this case series, we report on four cases with non-tuberculosis abnormalities detected on CXR in TB TRIAGE + ACCURACY (ClinicalTrials.gov Identifier: NCT04666311), a study in adult presumptive tuberculosis cases at health facilities in Lesotho and South Africa to determine the diagnostic accuracy of two potential tuberculosis triage tests: computer-aided detection (CAD4TB v7, Delft, the Netherlands) and C-reactive protein (Alere Afinion, USA). The four Black African participants presented with the following chest X-ray abnormalities: a 59-year-old woman with pulmonary arteriovenous malformation, a 28-year-old man with pneumothorax, a 20-year-old man with massive bronchiectasis, and a 47-year-old woman with aspergilloma.

CONCLUSIONS

Solely using chest X-ray computer-aided detection systems based on artificial intelligence as a tuberculosis screening strategy in sub-Saharan Africa comes with benefits, but also risks. Due to the limitation of CAD4TB for non-tuberculosis-abnormality identification, the computer-aided detection software may miss significant chest X-ray abnormalities that require treatment, as exemplified in our four cases. Increased data collection, characterization of non-tuberculosis anomalies and research on the implications of these diseases for individuals and health systems in sub-Saharan Africa is needed to help improve existing artificial intelligence software programs and their use in countries with high tuberculosis burden.

Generative Adversarial Network (Generative Artificial Intelligence) in Pediatric Radiology: A Systematic Review

Generative artificial intelligence, especially with regard to the generative adversarial network (GAN), is an important research area in radiology as evidenced by a number of literature reviews on the role of GAN in radiology published in the last few years. However, no review article about GAN in pediatric radiology has been published yet. The purpose of this paper is to systematically review applications of GAN in pediatric radiology, their performances, and methods for their performance evaluation. Electronic databases were used for a literature search on 6 April 2023. Thirty-seven papers met the selection criteria and were included. This review reveals that the GAN can be applied to magnetic resonance imaging, X-ray, computed tomography, ultrasound and positron emission tomography for image translation, segmentation, reconstruction, quality assessment, synthesis and data augmentation, and disease diagnosis. About 80% of the included studies compared their GAN model performances with those of other approaches and indicated that their GAN models outperformed the others by 0.1-158.6%. However, these study findings should be used with caution because of a number of methodological weaknesses. For future GAN studies, more robust methods will be essential for addressing these issues. Otherwise, this would affect the clinical adoption of the GAN-based applications in pediatric radiology and the potential advantages of GAN could not be realized widely.

Artificial Intelligence in Paediatric Tuberculosis

Tuberculosis (TB) continues to be a leading cause of death in children despite global efforts focused on early diagnosis and interventions to limit the spread of the disease. This challenge has been made more complex in the context of the coronavirus pandemic, which has disrupted the "End TB Strategy" and framework set out by the World Health Organization (WHO). Since the inception of artificial intelligence (AI) more than 60 years ago, the interest in AI has risen and more recently we have seen the emergence of multiple real-world applications, many of which relate to medical imaging. Nonetheless, real-world AI applications and clinical studies are limited in the niche area of paediatric imaging. This review article will focus on how AI, or more specifically deep learning, can be applied to TB diagnosis and management in children. We describe how deep learning can be utilised in chest imaging to provide computer-assisted diagnosis to augment workflow and screening efforts. We also review examples of recent AI applications for TB screening in resource constrained environments and we explore some of the challenges and the future directions of AI in paediatric TB.

Artificial Intelligence-Based Software with CE Mark for Chest X-ray Interpretation: Opportunities and Challenges

Chest X-ray (CXR) is the most important technique for performing chest imaging, despite its well-known limitations in terms of scope and sensitivity. These intrinsic limitations of CXR have prompted the development of several artificial intelligence (AI)-based software packages dedicated to CXR interpretation. The online database "AI for radiology" was queried to identify CE-marked AI-based software available for CXR interpretation. The returned studies were divided according to the targeted disease. AI-powered computer-aided detection software is already widely adopted in screening and triage for pulmonary tuberculosis, especially in countries with few resources and suffering from high a burden of this disease. AI-based software has also been demonstrated to be valuable for the detection of lung nodules detection, automated flagging of positive cases, and post-processing through the development of digital bone suppression software able to produce digital bone suppressed images. Finally, the majority of available CE-marked software packages for CXR are designed to recognize several findings, with potential differences in sensitivity and specificity for each of the recognized findings.

Review on chest pathogies detection systems using deep learning techniques

Chest radiography is the standard and most affordable way to diagnose, analyze, and examine different thoracic and chest diseases. Typically, the radiograph is examined by an expert radiologist or physician to decide about a particular anomaly, if exists. Moreover, computer-aided methods are used to assist radiologists and make the analysis process accurate, fast, and more automated. A tremendous improvement in automatic chest pathologies detection and analysis can be observed with the emergence of deep learning. The survey aims to review, technically evaluate, and synthesize the different computer-aided chest pathologies detection systems. The state-of-the-art of single and multi-pathologies detection systems, which are published in the last five years, are thoroughly discussed. The taxonomy of image acquisition, dataset preprocessing, feature extraction, and deep learning models are presented. The mathematical concepts related to feature extraction model architectures are discussed. Moreover, the different articles are compared based on their contributions, datasets, methods used, and the results achieved. The article ends with the main findings, current trends, challenges, and future recommendations.

AI for Anglophone Africa: Unlocking its adoption for responsible solutions in academia-private sector

In recent years, AI technologies have become indispensable in social and industrial development, yielding revolutionary results in improving labor efficiency, lowering labor costs, optimizing human resource structure, and creating new job demands. To reap the full benefits of responsible AI solutions in Africa, it is critical to investigate existing challenges and propose strategies, policies, and frameworks for overcoming and eliminating them. As a result, this study investigated the challenges of adopting responsible AI solutions in the Academia-Private sectors for Anglophone Africa through literature reviews, expert interviews, and then proposes solutions and framework for the sustainable and successful adoption of responsible AI.

Evaluation of chest X-ray with automated interpretation algorithms for mass tuberculosis screening in prisons: a cross-sectional study

Background

The World Health Organization (WHO) recommends systematic tuberculosis (TB) screening in prisons. Evidence is lacking for accurate and scalable screening approaches in this setting. We aimed to assess the accuracy of artificial intelligence-based chest x-ray interpretation algorithms for TB screening in prisons.

Methods

We performed prospective TB screening in three male prisons in Brazil from October 2017 to December 2019. We administered a standardized questionnaire, performed a chest x-ray in a mobile unit, and collected sputum for confirmatory testing using Xpert MTB/RIF and culture. We evaluated x-ray images using three algorithms (CAD4TB version 6, Lunit version 3.1.0.0 and qXR version 3) and compared their accuracy. We utilized multivariable logistic regression to assess the effect of demographic and clinical characteristics on algorithm accuracy. Finally, we investigated the relationship between abnormality scores and Xpert semi-quantitative results.

Findings

Among 2075 incarcerated individuals, 259 (12.5%) had confirmed TB. All three algorithms performed similarly overall with area under the receiver operating characteristic curve (AUC) of 0.88-0.91. At 90% sensitivity, only LunitTB and qXR met the WHO Target Product Profile requirements for a triage test, with specificity of 84% and 74%, respectively. All algorithms had variable performance by age, prior TB, smoking, and presence of TB symptoms. LunitTB was the most robust to this heterogeneity but nonetheless failed to meet the TPP for individuals with previous TB. Abnormality scores of all three algorithms were significantly correlated with sputum bacillary load.

Interpretation

Automated x-ray interpretation algorithms can be an effective triage tool for TB screening in prisons. However, their specificity is insufficient in individuals with previous TB.

Funding

This study was supported by the US National Institutes of Health (grant numbers R01 AI130058 and R01 AI149620) and the State Secretary of Health of Mato Grosso do Sul.

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.

Diagnostic Accuracy of the Artificial Intelligence Methods in Medical Imaging for Pulmonary Tuberculosis: A Systematic Review and Meta-Analysis

Tuberculosis (TB) remains one of the leading causes of death among infectious diseases worldwide. Early screening and diagnosis of pulmonary tuberculosis (PTB) is crucial in TB control, and tend to benefit from artificial intelligence. Here, we aimed to evaluate the diagnostic efficacy of a variety of artificial intelligence methods in medical imaging for PTB. We searched MEDLINE and Embase with the OVID platform to identify trials published update to November 2022 that evaluated the effectiveness of artificial-intelligence-based software in medical imaging of patients with PTB. After data extraction, the quality of studies was assessed using quality assessment of diagnostic accuracy studies 2 (QUADAS-2). Pooled sensitivity and specificity were estimated using a bivariate random-effects model. In total, 3987 references were initially identified and 61 studies were finally included, covering a wide range of 124,959 individuals. The pooled sensitivity and the specificity were 91% (95% confidence interval (CI), 89-93%) and 65% (54-75%), respectively, in clinical trials, and 94% (89-96%) and 95% (91-97%), respectively, in model-development studies. These findings have demonstrated that artificial-intelligence-based software could serve as an accurate tool to diagnose PTB in medical imaging. However, standardized reporting guidance regarding AI-specific trials and multicenter clinical trials is urgently needed to truly transform this cutting-edge technology into clinical practice.

Economic analysis of different throughput scenarios and implementation strategies of computer-aided detection software as a screening and triage test for pulmonary TB

BACKGROUND

Artificial Intelligence (AI) systems have demonstrated potential in detecting tuberculosis (TB) associated abnormalities from chest X-ray (CXR) images. Thus, they might provide a solution to radiologist shortages in high TB burden countries. However, the cost of implementing computer-aided detection (CAD) software has thus far been understudied. In this study, we performed a costing analysis of CAD software when used as a screening or triage test for pulmonary TB, estimated the incremental cost compared to a radiologist reading of different throughput scenarios, and predicted the cost for the national scale-up plan in Pakistan.

METHODS

For the study, we focused on CAD software reviewed by the World Health Organization (CAD4TB, Lunit INSIGHT CXR, qXR) or listed in the Global Drug Facility diagnostics catalogue (CAD4TB, InferRead). Costing information was obtained from the CAD software developers. CAD4TB and InferRead use a perpetual license pricing model, while Lunit and qXR are priced per license for restricted number of scans. A major implementer in Pakistan provided costing information for human resource and software training. The per-screen cost was estimated for each CAD software and for radiologist for 1) active case finding, and 2) facility based CXR testing scenarios with throughputs ranging from 50,000-100,000 scans. Moreover, we estimated the scale-up cost for CAD or radiologist CXR reading in Pakistan based on the National Strategic Plan, considering that to reach 80% diagnostic coverage, 50% of TB patients would need to be found through facility-based triage and 30% through active case finding (ACF).

RESULTS

The per-screen cost for CAD4TB (0.25 USD- 2.33 USD) and InferRead (0.19 USD- 2.78 USD) was lower than that of a radiologist (0.70 USD- 0.93 USD) for high throughput scenarios studied. In comparison, the per-screen cost for Lunit (0.94 USD- 1.69 USD) and qXR (0.95 USD-1.9 USD) were only comparable with that of the radiologists in the highest throughput scenario in ACF. To achieve 80 percent diagnostic coverage at scale in Pakistan, the projected additional cost of deploying CAD software to complement the current infrastructure over a four-year period were estimated at 2.65-19.23 million USD, whereas Human readers, would cost an additional 23.97 million USD.

CONCLUSIONS

Our findings suggest that using CAD software could enable large-scale screening programs in high TB-burden countries and be less costly than radiologist. To achieve minimum cost, the target number of screens in a specific screening strategy should be carefully considered when selecting CAD software, along with the offered pricing structure and other aspects such as performance and operational features. Integrating CAD software in implementation strategies for case finding could be an economical way to attain the intended programmatic goals.

eHealth in TB clinical management

BACKGROUND: The constant expansion of internet and mobile technologies has created new opportunities in the field of eHealth, or the digital delivery of healthcare services. This TB meta-analysis aims to examine eHealth and its impact on TB clinical management in order to formulate recommendations for further development.METHODS: A systematic search was performed using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework in PubMed and Embase of articles published up to April 2021. Screening, extraction and quality assessment were performed by two independent researchers. Studies evaluating an internet and/or mobile-based eHealth intervention with an impact on TB clinical management were included. Outcomes were organised following the five domains described in the WHO "Recommendations on Digital Interventions for Health System Strengthening" guideline.RESULTS: Search strategy yielded 3,873 studies, and 89 full texts were finally included. eHealth tended to enhance screening, diagnosis and treatment indicators, while being cost-effective and acceptable to users. The main challenges concern hardware malfunction and software misuse.CONCLUSION: This study offers a broad overview of the innovative field of eHealth applications in TB. Different studies implementing eHealth solutions consistently reported on benefits, but also on specific challenges. eHealth is a promising field of research and could enhance clinical management of TB.

Ensemble Technique Coupled with Deep Transfer Learning Framework for Automatic Detection of Tuberculosis from Chest X-ray Radiographs

Tuberculosis (TB) is an infectious disease affecting humans' lungs and is currently ranked the 13th leading cause of death globally. Due to advancements in technology and the availability of medical datasets, automatic analysis and classification of chest X-rays (CXRs) into TB and non-TB can be a reliable alternative for early TB screening. We propose an automatic TB detection system using advanced deep learning (DL) models. A substantial part of a CXR image is dark, with no relevant information for diagnosis and potentially confusing DL models. In this work, the U-Net model extracts the region of interest from CXRs and the segmented images are fed to the DL models for feature extraction. Eight different convolutional neural networks (CNN) models are employed in our experiments, and their classification performance is compared based on three publicly available CXR datasets. The U-Net model achieves segmentation accuracy of 98.58%, intersection over union (IoU) of 93.10, and a Dice coefficient score of 96.50. Our proposed stacked ensemble algorithm performed better by achieving accuracy, sensitivity, and specificity values of 98.38%, 98.89%, and 98.70%, respectively. Experimental results confirm that segmented lung CXR images with ensemble learning produce a better result than un-segmented lung CXR images.

Portable digital X-ray for TB pre-diagnosis screening in rural communities in Nigeria

SETTING

This pilot project was conducted in hard-to-reach communities of two Niger Delta States in the South-South Region of Nigeria.

OBJECTIVE

To assess the usefulness of portable digital X-ray, the Delft-Light Backpack (DLB) for TB active case-finding (ACF) in hard-to-reach Niger Delta communities using the WHO 3B TB screening/diagnosis algorithm.

DESIGN

DLB X-ray was used to screen all consenting eligible participants during community TB screening out-reaches in all hard-to-reach communities of Akwa Ibom and Cross River States in the Niger Delta, Nigeria. Participants with a CAD4TB (computer-aided detection for TB score) ⩾60 had Xpert (sputum) and/or clinical (radiograph) assessment for TB diagnosis. Data from the project were analysed for this study.

RESULTS

A total of 8,230 participants (males: 47.2%, females: 52.8%) underwent TB screening and 1,140 (13.9%) presumptive TB cases were identified. The TB prevalence among all participants and among those with presumptive TB were respectively 1.2% and 8.6%. The number needed to screen was 84. Among people with presumptive TB, the proportion of males and females with confirmed TB was respectively 12.0% and 5.6% (P < 0.001).

CONCLUSION

TB screening using DLB X-ray during community-based ACF in hard-to-reach Niger Delta communities of Nigeria showed a high TB prevalence among participants. Nationwide deployment of the instrument in hard-to-reach areas is recommended.

Comparing different versions of computer-aided detection products when reading chest X-rays for tuberculosis

Computer-aided detection (CAD) was recently recommended by the WHO for TB screening and triage based on several evaluations, but unlike traditional diagnostic tests, software versions are updated frequently and require constant evaluation. Since then, newer versions of two of the evaluated products have already been released. We used a case control sample of 12,890 chest X-rays to compare performance and model the programmatic effect of upgrading to newer versions of CAD4TB and qXR. We compared the area under the receiver operating characteristic curve (AUC), overall, and with data stratified by age, TB history, gender, and patient source. All versions were compared against radiologist readings and WHO's Target Product Profile (TPP) for a TB triage test. Both newer versions significantly outperformed their predecessors in terms of AUC: CAD4TB version 6 (0.823 [0.816-0.830]), version 7 (0.903 [0.897-0.908]) and qXR version 2 (0.872 [0.866-0.878]), version 3 (0.906 [0.901-0.911]). Newer versions met WHO TPP values, older versions did not. All products equalled or surpassed the human radiologist performance with improvements in triage ability in newer versions. Humans and CAD performed worse in older age groups and among those with TB history. New versions of CAD outperform their predecessors. Prior to implementation CAD should be evaluated using local data because underlying neural networks can differ significantly. An independent rapid evaluation centre is necessitated to provide implementers with performance data on new versions of CAD products as they are developed.

New developments in tuberculosis diagnosis and treatment

Tuberculosis (TB) is a major cause of morbidity and mortality worldwide. It is estimated that 25% of the world's population are infected with Mycobacterium tuberculosis, with a 5–10% lifetime risk of progression into TB disease. Early recognition of TB disease and prompt detection of drug resistance are essential to halting its global burden. Culture, direct microscopy, biomolecular tests and whole genome sequencing are approved methods of diagnosis; however, their widespread use is often curtailed owing to costs, local resources, time constraints and operator efficiency. Methods of optimising these diagnostics, in addition to developing novel techniques, are under review. The selection of an appropriate drug regimen is dependent on the susceptibility pattern of the isolate detected. At present, there are 16 new drugs under evaluation for TB treatment in phase I or II clinical trials, with an additional 22 drugs in preclinical stages. Alongside the development of these new drugs, most of which are oral medications, new shorter regimes are under evaluation. The aim of these shorter regimens is to encourage patient adherence, and prevent relapse or the evolution of further drug resistance. Screening for TB infection, especially in vulnerable populations, provides an opportunity for intervention prior to progression towards infectious TB disease. New regimens are currently under evaluation to assess the efficacy of shorter durations of treatment in this population. In addition, there is extensive research into the use of post-exposure vaccinations in this cohort. Worldwide collaboration and sharing of expertise are essential to our ultimate aim of global eradication of TB disease.

Early detection of drug resistance is essential to our goal of global eradication of TB. Tolerable drugs and shorter regimens promote patient adherence. Treating TB infection in vulnerable groups will prevent further global spread of TB disease.https://bit.ly/3oUW0SN

Chest Imaging for Pulmonary TB—An Update

The diagnosis of pulmonary tuberculosis (PTB) in children is challenging. Difficulties in acquiring suitable specimens, pauci-bacillary load, and limitations of current diagnostic methods often make microbiological confirmation difficult. Chest imaging provides an additional diagnostic modality that is frequently used in clinical practice. Chest imaging can also provide insight into treatment response and identify development of disease complications. Despite widespread use, chest radiographs are usually non-specific and have high inter- and intra-observer variability. Other diagnostic imaging modalities such as ultrasound, computed tomography (CT), and magnetic resonance imaging (MRI) can provide additional information to substantiate diagnosis. In this review, we discuss the radiological features of PTB in each modality, highlighting the advantages and limitations of each. We also address newer imaging technologies and potential use.

Spatially targeted digital chest radiography to reduce tuberculosis in high-burden settings: a study of adaptive decision making

Background:

Spatially-targeted approaches to screen for tuberculosis (TB) could accelerate TB control in high-burden populations. We aimed to estimate gains in case-finding yield under an adaptive decision-making approach for spatially-targeted, mobile digital chest radiography (dCXR)-based screening in communities with varying levels of TB prevalence.

Methods:

We used a Monte-Carlo simulation model to simulate a spatially-targeted screening intervention in 24 communities with TB prevalence estimates derived from a large community-randomized trial. We implemented a Thompson sampling algorithm to allocate screening units based on Bayesian probabilities of local TB prevalence that are continuously updated during weekly screening rounds. Four mobile units for dCXR-based screening and subsequent Xpert Ultra-based testing were allocated among the communities during a 52-week period. We estimated the yield of bacteriologically-confirmed TB per 1000 screenings comparing scenarios of spatially-targeted and untargeted resource allocation.

Results:

We estimated that under the untargeted scenario, an expected 666 (95% uncertainty interval 522–825) TB cases would be detected over one year, equivalent to 8.9 (7.5–10.3) per 1000 individuals screened. Allocating the screening units to the communities with the highest (prior-year) cases notification rates resulted in an expected 760 (617–926) TB cases detected, 10.1 (8.6–11.8) per 1000 screened. Adaptive, spatially-targeted screening resulted in an expected 1241 (995–1502) TB cases detected, 16.5 (14.5–18.7) per 1000 screened. Numbers of dCXR-based screenings needed to detect one additional TB case declined during the first 12–14 weeks as a result of Bayesian learning.

Conclusion:

We introduce a spatially-targeted screening strategy that could reduce the number of screenings necessary to detect additional TB in high-burden settings and thus improve the efficiency of screening interventions. Empirical trials are needed to determine whether this approach could be successfully implemented.

Current and emerging artificial intelligence applications in chest imaging: a pediatric perspective

Artificial intelligence (AI) applications for chest radiography and chest CT are among the most developed applications in radiology. More than 40 certified AI products are available for chest radiography or chest CT. These AI products cover a wide range of abnormalities, including pneumonia, pneumothorax and lung cancer. Most applications are aimed at detecting disease, complemented by products that characterize or quantify tissue. At present, none of the thoracic AI products is specifically designed for the pediatric population. However, some products developed to detect tuberculosis in adults are also applicable to children. Software is under development to detect early changes of cystic fibrosis on chest CT, which could be an interesting application for pediatric radiology. In this review, we give an overview of current AI products in thoracic radiology and cover recent literature about AI in chest radiography, with a focus on pediatric radiology. We also discuss possible pediatric applications.

How does artificial intelligence in radiology improve efficiency and health outcomes?

Since the introduction of artificial intelligence (AI) in radiology, the promise has been that it will improve health care and reduce costs. Has AI been able to fulfill that promise? We describe six clinical objectives that can be supported by AI: a more efficient workflow, shortened reading time, a reduction of dose and contrast agents, earlier detection of disease, improved diagnostic accuracy and more personalized diagnostics. We provide examples of use cases including the available scientific evidence for its impact based on a hierarchical model of efficacy. We conclude that the market is still maturing and little is known about the contribution of AI to clinical practice. More real-world monitoring of AI in clinical practice is expected to aid in determining the value of AI and making informed decisions on development, procurement and reimbursement.

Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey

Community-based screening for tuberculosis (TB) could improve detection but is resource intensive. We set out to evaluate the accuracy of computer-aided TB screening using digital chest X-ray (CXR) to determine if this approach met target product profiles (TPP) for community-based screening. CXR images from participants in the 2016 Kenya National TB Prevalence Survey were evaluated using CAD4TBv6 (Delft Imaging), giving a probabilistic score for pulmonary TB ranging from 0 (low probability) to 99 (high probability). We constructed a Bayesian latent class model to estimate the accuracy of CAD4TBv6 screening compared to bacteriologically-confirmed TB across CAD4TBv6 threshold cut-offs, incorporating data on Clinical Officer CXR interpretation, participant demographics (age, sex, TB symptoms, previous TB history), and sputum results. We compared model-estimated sensitivity and specificity of CAD4TBv6 to optimum and minimum TPPs. Of 63,050 prevalence survey participants, 61,848 (98%) had analysable CXR images, and 8,966 (14.5%) underwent sputum bacteriological testing; 298 had bacteriologically-confirmed pulmonary TB. Median CAD4TBv6 scores for participants with bacteriologically-confirmed TB were significantly higher (72, IQR: 58-82.75) compared to participants with bacteriologically-negative sputum results (49, IQR: 44-57, p<0.0001). CAD4TBv6 met the optimum TPP; with the threshold set to achieve a mean sensitivity of 95% (optimum TPP), specificity was 83.3%, (95% credible interval [CrI]: 83.0%-83.7%, CAD4TBv6 threshold: 55). There was considerable variation in accuracy by participant characteristics, with older individuals and those with previous TB having lowest specificity. CAD4TBv6 met the optimal TPP for TB community screening. To optimise screening accuracy and efficiency of confirmatory sputum testing, we recommend that an adaptive approach to threshold setting is adopted based on participant characteristics.

Diagnostic accuracy of computer aided reading of chest x-ray in screening for pulmonary tuberculosis in comparison with Gene-Xpert

Background & Objectives:

Pakistan ranked fifth amongst 22 high-burden Tuberculosis countries, and it is an epidemic in Pakistan, hence screening is performed nationally, as part of the ambitious ZERO TB drive. Our objective was to assess the diagnostic accuracy of Computer Aided Detection (CAD4TB) software on chest Xray in screening for pulmonary tuberculosis in comparison with gene-Xpert.

Methods:

The study was conducted by Radiology Department Lady Reading Hospital Peshawar in affiliation with Indus Hospital network over a period of one year. Screening was done by using mobile Xray unit equipped with CAD4TB software with scoring system. All of those having score of more than 70 and few selected cases with strong clinical suspicion but score of less than 70 were referred to dedicated TB clinic for Gene-Xpert analysis.

Results:

Among 26,997 individuals screened, 2617 (9.7%) individuals were found presumptive for pulmonary TB. Sputum samples for Gene-Xpert were obtained in 2100 (80.24%) individuals, out of which 1825 (86.9%) were presumptive for pulmonary TB on CAD4TB only. Gene-Xpert was positive in 159 (8.7%) patients and negative in 1,666(91.3%). Sensitivity and specificity of CAD4TB and symptomatology with threshold score of ≥70 was 83.2% and 12.7% respectively keeping Gene-Xpert as gold standard.

Conclusion:

Combination of chest X-ray analysis by CAD4TB and symptomatology is of immense value to screen a large population at risk in a developing high burden country. It is significantly a more effective tool for screening and early diagnosis of TB in individuals, who would otherwise go undiagnosed.

Early TB case detection by community-based mobile X-ray screening and Xpert testing in Balochistan

SETTING

This survey was conducted at 35 sites of 20 cities in 15 districts with low programmatic TB case notifications in the past years in Balochistan.

OBJECTIVE

To assess the effectiveness of the systemic community-based screening and diagnosis for early detection of TB; and 2) to describe the characteristics and understand the strengths and weaknesses of the intervention in Balochistan, and sociodemographic factors associated with it.

DESIGN

This cross-sectional descriptive study was conducted using a mobile van equipped with a digital X-ray machine with computer-aided detection for TB (CAD4TB) software for screening, followed by confirmatory high sensitivity Xpert® MTB/RIF assay testing.

RESULTS

A total of 236 (3.4%) TB cases was detected out of 6,899 screened. About 1,168 (17%) presumptive TB cases were identified and 1,065 (91%) sputum samples were tested on Xpert. Among those diagnosed, 166 (70%) were Mycobacterium tuberculosis-positive and 70 (30%) were with clinical suspicion. Of the sputum samples tested, 87% (923/1065) had a probability score of >70 on CAD4TB.

CONCLUSION

Community-based screening with innovative activities, comprising sensitive screening and diagnostic tools, effectively improves TB case detection, which might suffice to reduce the prevalence of TB and break the chain of infection transmission in the at-risk population.

Triage of Persons With Tuberculosis Symptoms Using Artificial Intelligence-Based Chest Radiograph Interpretation: A Cost-Effectiveness Analysis

BACKGROUND

In settings without access to rapid expert radiographic interpretation, artificial intelligence (AI)-based chest radiograph (CXR) analysis can triage persons presenting with possible tuberculosis (TB) symptoms, to identify those who require additional microbiological testing. However, there is limited evidence of the cost-effectiveness of this technology as a triage tool.

METHODS

A decision analysis model was developed to evaluate the cost-effectiveness of triage strategies with AI-based CXR analysis for patients presenting with symptoms suggestive of pulmonary TB in Karachi, Pakistan. These strategies were compared to the current standard of care using microbiological testing with smear microscopy or GeneXpert, without prior triage. Positive triage CXRs were considered to improve referral success for microbiologic testing, from 91% to 100% for eligible persons. Software diagnostic accuracy was based on a prospective field study in Karachi. Other inputs were obtained from the Pakistan TB Program. The analysis was conducted from the healthcare provider perspective, and costs were expressed in 2020 US dollars.

RESULTS

Compared to upfront smear microscopy for all persons with presumptive TB, triage strategies with AI-based CXR analysis were projected to lower costs by 19%, from $23233 per 1000 persons, and avert 3%-4% disability-adjusted life-years (DALYs), from 372 DALYs. Compared to upfront GeneXpert, AI-based triage strategies lowered projected costs by 37%, from $34346 and averted 4% additional DALYs, from 369 DALYs. Reinforced follow-up for persons with positive triage CXRs but negative microbiologic tests was particularly cost-effective.

CONCLUSIONS

In lower-resource settings, the addition of AI-based CXR triage before microbiologic testing for persons with possible TB symptoms can reduce costs, avert additional DALYs, and improve TB detection.

An accurate artificial intelligence system for the detection of pulmonary and extra pulmonary Tuberculosis

Tuberculosis (TB) is the greatest irresistible illness in humans, caused by microbes Mycobacterium TB (MTB) bacteria and is an infectious disease that spreads from one individual to another through the air. It principally influences lung, which is termed Pulmonary TB (PTB). However, it can likewise influence other parts of the body such as the brain, bones and lymph nodes. Hence, it is also referred to as Extra Pulmonary TB (EPTB). TB has normal symptoms, so without proper testing, it is hard to detect if a patient has TB or not. In this paper, an accurate and novel system for diagnosing TB (PTB and EPTB) has been designed using image processing and AI-based classification techniques. The designed system is comprised of two phases. Firstly, the X-Ray image is processed using preprocessing, segmentation and features extraction and then, three different AI-based techniques are applied for classification. For image processing, 'Histogram Filter' and 'Median Filter' are applied with the CLAHE process to retrieve the segmented image. Then, classification based on AI techniques is done. The designed system produces the accuracy of 98%, 83%, and 89% for Decision Tree, SVM, and Naïve Bayes Classifier, respectively and has been validated by the doctors of the Jalandhar, India.

Pattern of abnormalities amongst chest X-rays of adults undergoing computer-assisted digital chest X-ray screening for tuberculosis in Peri-Urban Blantyre, Malawi: A cross-sectional study

BACKGROUND

The prevalence of diseases other than tuberculosis (TB) detected during chest X-ray screening is poorly described in sub-Saharan Africa. Computer-assisted digital chest X-ray technology is available for TB screening and has the potential to be a screening tool for non-communicable diseases as well. Low- and middle-income countries are in a transition period where the burden of non-communicable diseases is increasing, but health systems are mainly focused on addressing infectious diseases.

METHODS

Participants were adults undergoing computer-assisted chest X-ray screening for tuberculosis in a community-wide tuberculosis prevalence survey in Blantyre, Malawi. Adults with abnormal radiographs by field radiographer interpretation were evaluated by a physician in a community-based clinic. X-ray classifications were compared to classifications of a random sample of normal chest X-rays by radiographer interpretation. Radiographic features were classified using WHO Integrated Management for Adult Illnesses (IMAI) guidelines. All radiographs taken at the screening tent were analysed by the Qure.ai qXR v2.0 software.

RESULTS

5% (648/13,490) of adults who underwent chest radiography were identified to have an abnormal chest X-ray by the radiographer. 387 (59.7%) of the participants attended the X-ray clinic, and another 387 randomly sampled normal X-rays were available for comparison. Participants who were referred to the community clinic had a significantly higher HIV prevalence than those who had been identified to have a normal CXR by the field radiographer (90 [23.3%] vs. 43 [11.1%] p-value < 0.001). The commonest radiographic finding was cardiomegaly (20.7%, 95% CI 18.0-23.7). One in five (81/387) chest X-rays were misclassified by the radiographer. The overall mean Qure.ai qXR v2.0 score for all reviewed X-rays was 0.23 (SD 0.20). There was a high concordance of cardiomegaly classification between the physician and the computer-assisted software (109/118, 92.4%).

CONCLUSION

There is a high burden of cardiomegaly on a chest X-ray at a community level, much of which is in patients with diabetes, heart disease and high blood pressure. Cardiomegaly on chest X-ray may be a potential tool for screening for cardiovascular NCDs at the primary care level as well as in the community.

Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms

BACKGROUND

Artificial intelligence (AI) algorithms can be trained to recognise tuberculosis-related abnormalities on chest radiographs. Various AI algorithms are available commercially, yet there is little impartial evidence on how their performance compares with each other and with radiologists. We aimed to evaluate five commercial AI algorithms for triaging tuberculosis using a large dataset that had not previously been used to train any AI algorithms.

METHODS

Individuals aged 15 years or older presenting or referred to three tuberculosis screening centres in Dhaka, Bangladesh, between May 15, 2014, and Oct 4, 2016, were recruited consecutively. Every participant was verbally screened for symptoms and received a digital posterior-anterior chest x-ray and an Xpert MTB/RIF (Xpert) test. All chest x-rays were read independently by a group of three registered radiologists and five commercial AI algorithms: CAD4TB (version 7), InferRead DR (version 2), Lunit INSIGHT CXR (version 4.9.0), JF CXR-1 (version 2), and qXR (version 3). We compared the performance of the AI algorithms with each other, with the radiologists, and with the WHO's Target Product Profile (TPP) of triage tests (≥90% sensitivity and ≥70% specificity). We used a new evaluation framework that simultaneously evaluates sensitivity, proportion of Xpert tests avoided, and number needed to test to inform implementers' choice of software and selection of threshold abnormality scores.

FINDINGS

Chest x-rays from 23 954 individuals were included in the analysis. All five AI algorithms significantly outperformed the radiologists. The areas under the receiver operating characteristic curve were 90·81% (95% CI 90·33-91·29) for qXR, 90·34% (89·81-90·87) for CAD4TB, 88·61% (88·03-89·20) for Lunit INSIGHT CXR, 84·90% (84·27-85·54) for InferRead DR, and 84·89% (84·26-85·53) for JF CXR-1. Only qXR (74·3% specificity [95% CI 73·3-74·9]) and CAD4TB (72·9% specificity [72·3-73·5]) met the TPP at 90% sensitivity. All five AI algorithms reduced the number of Xpert tests required by 50% while maintaining a sensitivity above 90%. All AI algorithms performed worse among older age groups (>60 years) and people with a history of tuberculosis.

INTERPRETATION

AI algorithms can be highly accurate and useful triage tools for tuberculosis detection in high-burden regions, and outperform human readers.

FUNDING

Government of Canada.

Computer-aided interpretation of chest radiography reveals the spectrum of tuberculosis in rural South Africa

Computer-aided digital chest radiograph interpretation (CAD) can facilitate high-throughput screening for tuberculosis (TB), but its use in population-based active case-finding programs has been limited. In an HIV-endemic area in rural South Africa, we used a CAD algorithm (CAD4TBv5) to interpret digital chest x-rays (CXR) as part of a mobile health screening effort. Participants with TB symptoms or CAD4TBv5 score above the triaging threshold were referred for microbiological sputum assessment. During an initial pilot phase, a low CAD4TBv5 triaging threshold of 25 was selected to maximize TB case finding. We report the performance of CAD4TBv5 in screening 9,914 participants, 99 (1.0%) of whom were found to have microbiologically proven TB. CAD4TBv5 was able to identify TB cases at the same sensitivity but lower specificity as a blinded radiologist, whereas the next generation of the algorithm (CAD4TBv6) achieved comparable sensitivity and specificity to the radiologist. The CXRs of people with microbiologically confirmed TB spanned a range of lung field abnormality, including 19 (19.2%) cases deemed normal by the radiologist. HIV serostatus did not impact CAD4TB's performance. Notably, 78.8% of the TB cases identified during this population-based survey were asymptomatic and therefore triaged for sputum collection on the basis of CAD4TBv5 score alone. While CAD4TBv6 has the potential to replace radiologists for triaging CXRs in TB prevalence surveys, population-specific piloting is necessary to set the appropriate triaging thresholds. Further work on image analysis strategies is needed to identify radiologically subtle active TB.

Adversarial attack vulnerability of medical image analysis systems: Unexplored factors

Adversarial attacks are considered a potentially serious security threat for machine learning systems. Medical image analysis (MedIA) systems have recently been argued to be vulnerable to adversarial attacks due to strong financial incentives and the associated technological infrastructure. In this paper, we study previously unexplored factors affecting adversarial attack vulnerability of deep learning MedIA systems in three medical domains: ophthalmology, radiology, and pathology. We focus on adversarial black-box settings, in which the attacker does not have full access to the target model and usually uses another model, commonly referred to as surrogate model, to craft adversarial examples that are then transferred to the target model. We consider this to be the most realistic scenario for MedIA systems. Firstly, we study the effect of weight initialization (pre-training on ImageNet or random initialization) on the transferability of adversarial attacks from the surrogate model to the target model, i.e., how effective attacks crafted using the surrogate model are on the target model. Secondly, we study the influence of differences in development (training and validation) data between target and surrogate models. We further study the interaction of weight initialization and data differences with differences in model architecture. All experiments were done with a perturbation degree tuned to ensure maximal transferability at minimal visual perceptibility of the attacks. Our experiments show that pre-training may dramatically increase the transferability of adversarial examples, even when the target and surrogate's architectures are different: the larger the performance gain using pre-training, the larger the transferability. Differences in the development data between target and surrogate models considerably decrease the performance of the attack; this decrease is further amplified by difference in the model architecture. We believe these factors should be considered when developing security-critical MedIA systems planned to be deployed in clinical practice. We recommend avoiding using only standard components, such as pre-trained architectures and publicly available datasets, as well as disclosure of design specifications, in addition to using adversarial defense methods. When evaluating the vulnerability of MedIA systems to adversarial attacks, various attack scenarios and target-surrogate differences should be simulated to achieve realistic robustness estimates. The code and all trained models used in our experiments are publicly available.³.

Deep learning for chest X-ray analysis: A survey

Recent advances in deep learning have led to a promising performance in many medical image analysis tasks. As the most commonly performed radiological exam, chest radiographs are a particularly important modality for which a variety of applications have been researched. The release of multiple, large, publicly available chest X-ray datasets in recent years has encouraged research interest and boosted the number of publications. In this paper, we review all studies using deep learning on chest radiographs published before March 2021, categorizing works by task: image-level prediction (classification and regression), segmentation, localization, image generation and domain adaptation. Detailed descriptions of all publicly available datasets are included and commercial systems in the field are described. A comprehensive discussion of the current state of the art is provided, including caveats on the use of public datasets, the requirements of clinically useful systems and gaps in the current literature.

'If not TB, what could it be?' Chest X-ray findings from the 2016 Kenya Tuberculosis Prevalence Survey

BACKGROUND

The prevalence of diseases other than TB detected during chest X-ray (CXR) screening is unknown in sub-Saharan Africa. This represents a missed opportunity for identification and treatment of potentially significant disease. Our aim was to describe and quantify non-TB abnormalities identified by TB-focused CXR screening during the 2016 Kenya National TB Prevalence Survey.

METHODS

We reviewed a random sample of 1140 adult (≥15 years) CXRs classified as 'abnormal, suggestive of TB' or 'abnormal other' during field interpretation from the TB prevalence survey. Each image was read (blinded to field classification and study radiologist read) by two expert radiologists, with images classified into one of four major anatomical categories and primary radiological findings. A third reader resolved discrepancies. Prevalence and 95% CIs of abnormalities diagnosis were estimated.

FINDINGS

Cardiomegaly was the most common non-TB abnormality at 259 out of 1123 (23.1%, 95% CI 20.6% to 25.6%), while cardiomegaly with features of cardiac failure occurred in 17 out of 1123 (1.5%, 95% CI 0.9% to 2.4%). We also identified chronic pulmonary pathology including suspected COPD in 3.2% (95% CI 2.3% to 4.4%) and non-specific patterns in 4.6% (95% CI 3.5% to 6.0%). Prevalence of active-TB and severe post-TB lung changes was 3.6% (95% CI 2.6% to 4.8%) and 1.4% (95% CI 0.8% to 2.3%), respectively.

INTERPRETATION

Based on radiological findings, we identified a wide variety of non-TB abnormalities during population-based TB screening. TB prevalence surveys and active case finding activities using mass CXR offer an opportunity to integrate disease screening efforts.

FUNDING

National Institute for Health Research (IMPALA-grant reference 16/136/35).

Extreme Learning Machine based Differentiation of Pulmonary Tuberculosis in Chest Radiographs using Integrated Local Feature Descriptors

BACKGROUND AND OBJECTIVE

Computer aided diagnostics of Pulmonary Tuberculosis in chest radiographs relies on the differentiation of subtle and non-specific alterations in the images. In this study, an attempt has been made to identify and classify Tuberculosis conditions from healthy subjects in chest radiographs using integrated local feature descriptors and variants of extreme learning machine.

METHODS

Lung fields in the chest images are segmented using Reaction Diffusion Level Set method. Local feature descriptors such as Median Robust Extended Local Binary Patterns and Gradient Local Ternary Patterns are extracted. Extreme Learning Machine (ELM) and Online Sequential ELM (OSELM) classifiers are employed to identify Tuberculosis conditions and, their performances are analysed using standard metrics.

RESULTS

Results show that the adopted segmentation method is able to delineate lung fields in both healthy and Tuberculosis images. Extracted features are statistically significant even in images with inter and intra subject variability. Sigmoid activation function yields accuracy and sensitivity values greater than 98% for both the classifiers. Highest sensitivity is observed with OSELM for minimal significant features in detecting Tuberculosis images.

CONCLUSION

As ELM based method is able to differentiate the subtle changes in inter and intra subject variations of chest X-ray images, the proposed methodology seems to be useful for computer-based detection of Pulmonary Tuberculosis.

Application of artificial intelligence in digital chest radiography reading for pulmonary tuberculosis screening

Currently, the diagnosis of tuberculosis (TB) is mainly based on the comprehensive consideration of the patient's symptoms and signs, laboratory examinations and chest radiography (CXR). CXR plays a pivotal role to support the early diagnosis of TB, especially when used for TB screening and differential diagnosis. However, high cost of CXR hardware and shortage of certified radiologists poses a major challenge for CXR application in TB screening in resource limited settings. The latest development of artificial intelligence (AI) combined with the accumulation of a large number of medical images provides new opportunities for the establishment of computer-aided detection (CAD) systems in the medical applications, especially in the era of deep learning (DL) technology. Several CAD solutions are now commercially available and there is growing evidence demonstrate their value in imaging diagnosis. Recently, WHO published a rapid communication which stated that CAD may be used as an alternative to human reader interpretation of plain digital CXRs for screening and triage of TB.

A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises

Since its renaissance, deep learning has been widely used in various medical imaging tasks and has achieved remarkable success in many medical imaging applications, thereby propelling us into the so-called artificial intelligence (AI) era. It is known that the success of AI is mostly attributed to the availability of big data with annotations for a single task and the advances in high performance computing. However, medical imaging presents unique challenges that confront deep learning approaches. In this survey paper, we first present traits of medical imaging, highlight both clinical needs and technical challenges in medical imaging, and describe how emerging trends in deep learning are addressing these issues. We cover the topics of network architecture, sparse and noisy labels, federating learning, interpretability, uncertainty quantification, etc. Then, we present several case studies that are commonly found in clinical practice, including digital pathology and chest, brain, cardiovascular, and abdominal imaging. Rather than presenting an exhaustive literature survey, we instead describe some prominent research highlights related to these case study applications. We conclude with a discussion and presentation of promising future directions.