Screening for pulmonary tuberculosis in a Tanzanian prison and computer-aided interpretation of chest X-rays

Iterative evaluation of mobile computer-assisted digital chest x-ray screening for TB improves efficiency, yield, and outcomes in Nigeria

Wellness on Wheels (WoW) is a model of mobile systematic tuberculosis (TB) screening of high-risk populations combining digital chest radiography with computer-aided automated detection (CAD) and chronic cough screening to identify presumptive TB clients in communities, health facilities, and prisons in Nigeria. The model evolves to address technical, political, and sustainability challenges. Screening methods were iteratively refined to balance TB yield and feasibility across heterogeneous populations. Performance metrics were compared over time. Screening volumes, risk mix, number needed to screen (NNS), number needed to test (NNT), sample loss, TB treatment initiation and outcomes. Efforts to mitigate losses along the diagnostic cascade were tracked. Persons with high CAD4TB score (≥80), who tested negative on a single spot GeneXpert were followed-up to assess TB status at six months. An experimental calibration method achieved a viable CAD threshold for testing. High risk groups and key stakeholders were engaged. Operations evolved in real time to fix problems. Incremental improvements in mean client volumes (128 to 140/day), target group inclusion (92% to 93%), on-site testing (84% to 86%), TB treatment initiation (87% to 91%), and TB treatment success (71% to 85%) were recorded. Attention to those as highest risk boosted efficiency (the NNT declined from 8.2 ± SD8.2 to 7.6 ± SD7.7). Clinical diagnosis was added after follow-up among those with ≥ 80 CAD scores and initially spot -sputum negative found 11 additional TB cases (6.3%) after 121 person-years of follow-up. Iterative adaptation in response to performance metrics foster feasible, acceptable, and efficient TB case-finding in Nigeria. High CAD scores can identify subclinical TB and those at risk of progression to bacteriologically-confirmed TB disease in the near term.

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.

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.

A systematic and meta-analysis study on the prevalence of tuberculosis and relative risk factors for prisoners in Iran

INTRODUCTION

This study aimed to evaluate the incidence of Tuberculosis (TB) among prisoners in Iran, by performing a systematic and meta-analysis study on the related articles.

METHODOLOGY

Scopus, Iran doc, Cochrane, Pubmed, Medline, Embase and Iran Medex, Magiran, SID, Google Scholar, and EBSCO were searched. After quality assessment of the articles, a fixed or random model, as appropriate, was used to pool the results in a meta-analysis. Heterogeneity between the studies was assessed using I-square and Q-test.

RESULTS

The overall sample size of included studies was 19562 that 64 of them were with TB. The highest prevalence of tuberculosis was related to the study of Rasht, 517 in 100,000 but the lowest rate was related to the study of Sought Khorasan, 25 in 100,000. The ES of the random effect model is 0.003 (95% CI, 0.001-0.005) and p-value <0.0001. The Higgins' I2 of all studies is 86.55%, and the p-value of the Cochrane Q statistics is <0.001, indicating that there is heterogeneity. Based on the Egger regression plot (t=2.18, p = 0.08, CI 95%: -0.001, 0.005) no publication bias existed.

CONCLUSION

The frequency of TB among the prisoners in Iran was low. Due to important limitations in this study, it is not possible to indicate the exact prevalence of TB among prisoners in Iran and compare this with the general population. More studies are needed to assess the related risk factor for designing health interventions plan to decrease the incidence rate of TB among prisoners.

Development and Validation of a Deep Learning-based Automatic Detection Algorithm for Active Pulmonary Tuberculosis on Chest Radiographs

Background

Detection of active pulmonary tuberculosis on chest radiographs (CRs) is critical for the diagnosis and screening of tuberculosis. An automated system may help streamline the tuberculosis screening process and improve diagnostic performance.

Methods

We developed a deep learning–based automatic detection (DLAD) algorithm using 54c221 normal CRs and 6768 CRs with active pulmonary tuberculosis that were labeled and annotated by 13 board-certified radiologists. The performance of DLAD was validated using 6 external multicenter, multinational datasets. To compare the performances of DLAD with physicians, an observer performance test was conducted by 15 physicians including nonradiology physicians, board-certified radiologists, and thoracic radiologists. Image-wise classification and lesion-wise localization performances were measured using area under the receiver operating characteristic (ROC) curves and area under the alternative free-response ROC curves, respectively. Sensitivities and specificities of DLAD were calculated using 2 cutoffs (high sensitivity [98%] and high specificity [98%]) obtained through in-house validation.

Results

DLAD demonstrated classification performance of 0.977–1.000 and localization performance of 0.973–1.000. Sensitivities and specificities for classification were 94.3%–100% and 91.1%–100% using the high-sensitivity cutoff and 84.1%–99.0% and 99.1%–100% using the high-specificity cutoff. DLAD showed significantly higher performance in both classification (0.993 vs 0.746–0.971) and localization (0.993 vs 0.664–0.925) compared to all groups of physicians.

Conclusions

Our DLAD demonstrated excellent and consistent performance in the detection of active pulmonary tuberculosis on CR, outperforming physicians, including thoracic radiologists.

Deep learning for automated classification of tuberculosis-related chest X-Ray: dataset distribution shift limits diagnostic performance generalizability

Background

Machine learning has been an emerging tool for various aspects of infectious diseases including tuberculosis surveillance and detection. However, the World Health Organization (WHO) provided no recommendations on using computer-aided tuberculosis detection software because of a small number of studies, methodological limitations, and limited generalizability of the findings.

Methods

To quantify the generalizability of the machine-learning model, we developed a Deep Convolutional Neural Network (DCNN) model using a Tuberculosis (TB)-specific chest x-ray (CXR) dataset of one population (National Library of Medicine Shenzhen No.3 Hospital) and tested it with non-TB-specific CXR dataset of another population (National Institute of Health Clinical Centers).

Results

In the training and intramural test sets using the Shenzhen hospital database, the DCCN model exhibited an AUC of 0.9845 and 0.8502 for detecting TB, respectively. However, the AUC of the supervised DCNN model in the ChestX-ray8 dataset was dramatically dropped to 0.7054. Using the cut points at 0.90, which suggested 72% sensitivity and 82% specificity in the Shenzhen dataset, the final DCNN model estimated that 36.51% of abnormal radiographs in the ChestX-ray8 dataset were related to TB.

Conclusion

A supervised deep learning model developed by using the training dataset from one population may not have the same diagnostic performance in another population. Conclusion: Technical specification of CXR images, disease severity distribution, dataset distribution shift, and overdiagnosis should be examined before implementation in other settings.

Using artificial intelligence to read chest radiographs for tuberculosis detection: A multi-site evaluation of the diagnostic accuracy of three deep learning systems

Deep learning (DL) neural networks have only recently been employed to interpret chest radiography (CXR) to screen and triage people for pulmonary tuberculosis (TB). No published studies have compared multiple DL systems and populations. We conducted a retrospective evaluation of three DL systems (CAD4TB, Lunit INSIGHT, and qXR) for detecting TB-associated abnormalities in chest radiographs from outpatients in Nepal and Cameroon. All 1196 individuals received a Xpert MTB/RIF assay and a CXR read by two groups of radiologists and the DL systems. Xpert was used as the reference standard. The area under the curve of the three systems was similar: Lunit (0.94, 95% CI: 0.93-0.96), qXR (0.94, 95% CI: 0.92-0.97) and CAD4TB (0.92, 95% CI: 0.90-0.95). When matching the sensitivity of the radiologists, the specificities of the DL systems were significantly higher except for one. Using DL systems to read CXRs could reduce the number of Xpert MTB/RIF tests needed by 66% while maintaining sensitivity at 95% or better. Using a universal cutoff score resulted different performance in each site, highlighting the need to select scores based on the population screened. These DL systems should be considered by TB programs where human resources are constrained, and automated technology is available.

Targeted active screening for tuberculosis in Zimbabwe: are field digital chest X-ray ratings reliable?

SETTING

Fifteen purposively selected districts in Zimbabwe in which targeted active screening for tuberculosis (Tas4TB) was conducted among TB high-risk groups (HRGs). There were 230 patients started on TB treatment on the basis of chest X-ray (CXR) results without corresponding bacteriological confirmation.

OBJECTIVES

To determine 1) the percentage of agreements in digital CXR ratings by medical officers against final ratings by radiologist(s), 2) inter-rater agreement in CXR ratings between medical officers and radiologists, and 3) number (and proportion) of patients belonging to HRGs who were over-treated during Tas4TB.

DESIGN

This was a cross-sectional study using programme data.

RESULTS

A total of 168 patients had their CXRs rated by two independent radiologists. Discordances among the radiologists were resolved by a third index radiologist, who provided the final rating. κ scores were 0.01 (field ratings vs. Radiologist A); 0.02 (field ratings vs. Radiologist B); 0.74 (Radiologists A vs. B). The percentage agreement for field and final radiologist rating was 70% (95%CI 64-78). Around 29% (95%CI 23-36) of the patients were potentially over-treated during Tas4TB.

CONCLUSION

Over a quarter of patients with presumptive TB are potentially over-treated during Tas4TB. Over-treatment is highest among those with previous contact with TB patients. Trainings of radiographers and medical officers may improve CXR ratings.

A systematic review of the diagnostic accuracy of artificial intelligence-based computer programs to analyze chest x-rays for pulmonary tuberculosis

We undertook a systematic review of the diagnostic accuracy of artificial intelligence-based software for identification of radiologic abnormalities (computer-aided detection, or CAD) compatible with pulmonary tuberculosis on chest x-rays (CXRs). We searched four databases for articles published between January 2005-February 2019. We summarized data on CAD type, study design, and diagnostic accuracy. We assessed risk of bias with QUADAS-2. We included 53 of the 4712 articles reviewed: 40 focused on CAD design methods (“Development” studies) and 13 focused on evaluation of CAD (“Clinical” studies). Meta-analyses were not performed due to methodological differences. Development studies were more likely to use CXR databases with greater potential for bias as compared to Clinical studies. Areas under the receiver operating characteristic curve (median AUC [IQR]) were significantly higher: in Development studies AUC: 0.88 [0.82–0.90]) versus Clinical studies (0.75 [0.66–0.87]; p-value 0.004); and with deep-learning (0.91 [0.88–0.99]) versus machine-learning (0.82 [0.75–0.89]; p = 0.001). We conclude that CAD programs are promising, but the majority of work thus far has been on development rather than clinical evaluation. We provide concrete suggestions on what study design elements should be improved.

Evaluation of the diagnostic accuracy of Computer-Aided Detection of tuberculosis on Chest radiography among private sector patients in Pakistan

The introduction of digital CXR with automated computer-aided interpretation, has given impetus to the role of CXR in TB screening, particularly in low resource, high-burden settings. The aim of this study was to evaluate the diagnostic accuracy of CAD4TB as a screening tool, implemented in the private sector in Karachi, Pakistan. This study analyzed retrospective data from CAD4TB and Xpert MTB/RIF testing carried out at two private TB treatment and diagnostic centers in Karachi. Sensitivity, specificity, potential Xperts saved, were computed and the receiver operator characteristic curves were constructed for four different models of CAD4TB. A total of 6,845 individuals with presumptive TB were enrolled in the study, 15.2% of which had MTB + ve result on Xpert. A high sensitivity (range 65.8-97.3%) and NPV (range 93.1-98.4%) were recorded for CAD4TB. The Area under the ROC curve (AUC) for CAD4TB was 0.79. CAD4TB with patient demographics (age and gender) gave an AUC of 0.83. CAD4TB offered high diagnostic accuracy. In low resource settings, CAD4TB, as a triage tool could minimize use of Xpert. Using CAD4TB in combination with age and gender data enhanced the performance of the software. Variations in demographic information generate different individual risk probabilities for the same CAD4TB scores.

Automated Chest X-Ray Screening: Can Lung Region Symmetry Help Detect Pulmonary Abnormalities?

Our primary motivator is the need for screening HIV+ populations in resource-constrained regions for exposure to Tuberculosis, using posteroanterior chest radiographs (CXRs). The proposed method is motivated by the observation that radiological examinations routinely conduct bilateral comparisons of the lung field. In addition, the abnormal CXRs tend to exhibit changes in the lung shape, size, and content (textures), and in overall, reflection symmetry between them. We analyze the lung region symmetry using multi-scale shape features, and edge plus texture features. Shape features exploit local and global representation of the lung regions, while edge and texture features take internal content, including spatial arrangements of the structures. For classification, we have performed voting-based combination of three different classifiers: Bayesian network, multilayer perception neural networks, and random forest. We have used three CXR benchmark collections made available by the U.S. National Library of Medicine and the National Institute of Tuberculosis and Respiratory Diseases, India, and have achieved a maximum abnormality detection accuracy (ACC) of 91.00% and area under the ROC curve (AUC) of 0.96. The proposed method outperforms the previously reported methods by more than 5% in ACC and 3% in AUC.

An evaluation of automated chest radiography reading software for tuberculosis screening among public- and private-sector patients

Computer-aided reading (CAR) of medical images is becoming increasingly common, but few studies exist for CAR in tuberculosis (TB). We designed a prospective study evaluating CAR for chest radiography (CXR) as a triage tool before Xpert MTB/RIF (Xpert).Consecutively enrolled adults in Dhaka, Bangladesh, with TB symptoms received CXR and Xpert. Each image was scored by CAR and graded by a radiologist. We compared CAR with the radiologist for sensitivity and specificity, area under the receiver operating characteristic curve (AUC), and calculated the potential Xpert tests saved.A total of 18 036 individuals were enrolled. TB prevalence by Xpert was 15%. The radiologist graded 49% of CXRs as abnormal, resulting in 91% sensitivity and 58% specificity. At a similar sensitivity, CAR had a lower specificity (41%), saving fewer (36%) Xpert tests. The AUC for CAR was 0.74 (95% CI 0.73-0.75). CAR performance declined with increasing age. The radiologist grading was superior across all sub-analyses.Using CAR can save Xpert tests, but the radiologist's specificity was superior. Differentiated CAR thresholds may be required for different populations. Access to, and costs of, human readers must be considered when deciding to use CAR software. More studies are needed to evaluate CAR using different screening approaches.

Parameter set for computer-assisted texture analysis of fetal brain

BACKGROUND

Magnetic resonance data were collected from a diverse population of gravid women to objectively compare the quality of 1.5-tesla (1.5 T) versus 3-T magnetic resonance imaging of the developing human brain. MaZda and B11 computational-visual cognition tools were used to process 2D images. We proposed a wavelet-based parameter and two novel histogram-based parameters for Fisher texture analysis in three-dimensional space.

RESULTS

Wavenhl, focus index, and dispersion index revealed better quality for 3 T. Though both 1.5 and 3 T images were 16-bit DICOM encoded, nearly 16 and 12 usable bits were measured in 3 and 1.5 T images, respectively. The four-bit padding observed in 1.5 T K-space encoding mimics noise by adding illusionistic details, which are not really part of the image. In contrast, zero-bit padding in 3 T provides space for storing more details and increases the likelihood of noise but as well as edges, which in turn are very crucial for differentiation of closely related anatomical structures.

CONCLUSIONS

Both encoding modes are possible with both units, but higher 3 T resolution is the main difference. It contributes to higher perceived and available dynamic range. Apart from surprisingly larger Fisher coefficient, no significant difference was observed when testing was conducted with down-converted 8-bit BMP images.