An exploratory deep learning approach to investigate tuberculosis pathogenesis in nonhuman primate model: Combining automated radiological analysis with clinical and biomarkers data.

BACKGROUND: Tuberculosis (TB) kills approximately 1.6 million people yearly despite the fact anti-TB drugs are generally curative. Therefore, TB-case detection and monitoring of therapy, need a comprehensive approach. Automated radiological analysis, combined with clinical, microbiological, and immunological data, by machine learning (ML), can help achieve it. METHODS: Six rhesus macaques were experimentally inoculated with pathogenic Mycobacterium tuberculosis in the lung. Data, including Computed Tomography (CT), were collected at 0, 2, 4, 8, 12, 16, and 20 weeks. RESULTS: Our ML-based CT analysis (TB-Net) efficiently and accurately analyzed disease progression, performing better than standard deep learning model (LLM OpenAI's CLIP Vi4). TB-Net based results were more consistent than, and confirmed independently by, blinded manual disease scoring by two radiologists and exhibited strong correlations with blood biomarkers, TB-lesion volumes, and disease-signs during disease pathogenesis. CONCLUSION: The proposed approach is valuable in early disease detection, monitoring efficacy of therapy, and clinical decision making.

A new nomogram based on ultrasound and clinical features for distinguishing epididymal tuberculosis and nontuberculous epididymitis.

Using ultrasound findings and clinical characteristics, we constructed and validated a new nomogram for distinguishing epididymal tuberculosis from nontuberculous epididymitis, both of which share similar symptoms. We retrospectively examined data of patients with epididymal tuberculosis and nontuberculous epididymitis hospitalized between January 1, 2013, and March 31, 2023. Eligible patients were randomly assigned to derivation and validation cohorts (ratio, 7:3). We drew a nomogram to construct a diagnostic model through multivariate logistic regression and visualize the model. We used concordance index, calibration plots, and decision curve analysis to assess the discrimination, calibration, and clinical usefulness of the nomogram, respectively. In this study, 136 participants had epididymal tuberculosis and 79 had nontuberculous epididymitis. Five variables-C-reactive protein level, elevated scrotal skin temperature, nodular lesion, chronic infection, and scrotal skin ulceration-were significant and used to construct the nomogram. Concordance indices of the derivation and validation cohorts were 0.95 and 0.96, respectively (95% confidence intervals, 0.91-0.98 and 0.92-1.00, respectively). Decision curve analysis of this nomogram revealed that it helped differentiate epididymal tuberculosis from nontuberculous epididymitis. This nomogram may help clinicians distinguish between epididymal tuberculosis and nontuberculous epididymitis, thereby increasing diagnosis accuracy.

Distributable, metabolic PET reporting of tuberculosis.

Tuberculosis remains a large global disease burden for which treatment regimens are protracted and monitoring of disease activity difficult. Existing detection methods rely almost exclusively on bacterial culture from sputum which limits sampling to organisms on the pulmonary surface. Advances in monitoring tuberculous lesions have utilized the common glucoside [18F]FDG, yet lack specificity to the causative pathogen Mycobacterium tuberculosis (Mtb) and so do not directly correlate with pathogen viability. Here we show that a close mimic that is also positron-emitting of the non-mammalian Mtb disaccharide trehalose - 2-[18F]fluoro-2-deoxytrehalose ([18F]FDT) - is a mechanism-based reporter of Mycobacteria-selective enzyme activity in vivo. Use of [18F]FDT in the imaging of Mtb in diverse models of disease, including non-human primates, successfully co-opts Mtb-mediated processing of trehalose to allow the specific imaging of TB-associated lesions and to monitor the effects of treatment. A pyrogen-free, direct enzyme-catalyzed process for its radiochemical synthesis allows the ready production of [18F]FDT from the most globally-abundant organic 18F-containing molecule, [18F]FDG. The full, pre-clinical validation of both production method and [18F]FDT now creates a new, bacterium-selective candidate for clinical evaluation. We anticipate that this distributable technology to generate clinical-grade [18F]FDT directly from the widely-available clinical reagent [18F]FDG, without need for either custom-made radioisotope generation or specialist chemical methods and/or facilities, could now usher in global, democratized access to a TB-specific PET tracer.

Detection of Esophageal Tuberculosis, a Rare Cause of Abdominal Pain, on 18F-FDG PET/CT.

The esophagus is rarely affected by Mycobacterium A 75-y-old man presented with upper abdominal pain and significant weight loss for 2 mo. Contrast-enhanced CT, upper gastrointestinal endoscopy, and abdominal vessel angiography gave normal results. To clarify the facts, 18F-FDG PET/CT was performed, revealing an 18F-FDG-avid lesion in the posterior wall of the lower thoracic esophagus. On endoscopic ultrasound-guided fine-needle aspiration of this lesion, puslike material was released. On microscopic examination, acid-fast bacilli were noted. The patient then began receiving standard antitubercular therapy.

Integrating molecular and radiological screening tools during community-based active case-finding for tuberculosis and COVID-19 in southern Africa.

OBJECTIVES: To evaluate diagnostic yield and feasibility of integrating testing for TB and COVID-19 using molecular and radiological screening tools during community-based active case-finding (ACF). METHODS: Community-based participants with presumed TB and/or COVID-19 were recruited using a mobile clinic. Participants underwent simultaneous point-of-care (POC) testing for TB (sputum; Xpert Ultra) and COVID-19 (nasopharyngeal swabs; Xpert SARS-CoV-2). Sputum culture and SARS-CoV-2 RT-PCR served as reference standards. Participants underwent ultra-portable POC chest radiography with computer-aided detection (CAD). TB infectiousness was evaluated using smear microscopy, cough aerosol sampling studies (CASS), and chest radiographic cavity detection. Feasibility of POC testing was evaluated via user-appraisals. RESULTS: Six hundred and one participants were enrolled, with 144/601 (24.0%) reporting symptoms suggestive of TB and/or COVID-19. 16/144 (11.1%) participants tested positive for TB, while 10/144 (6.9%) tested positive for COVID-19 (2/144 [1.4%] had concurrent TB/COVID-19). Seven (7/16 [43.8%]) individuals with TB were probably infectious. Test-specific sensitivity and specificity (95% CI) were: Xpert Ultra 75.0% (42.8-94.5) and 96.9% (92.4-99.2); Xpert SARS-CoV-2 66.7% (22.3-95.7) and 97.1% (92.7-99.2). Area under the curve (AUC) for CAD4TB was 0.90 (0.82-0.97). User appraisals indicated POC Xpert to have 'good' user-friendliness. CONCLUSIONS: Integrating TB/COVID-19 screening during community-based ACF using POC molecular and radiological tools is feasible, has a high diagnostic yield, and can identity probably infectious persons.

Chest Radiograph Screening for Detecting Subclinical Tuberculosis in Asymptomatic Household Contacts, Peru.

The World Health Organization's end TB strategy promotes the use of symptom and chest radiograph screening for tuberculosis (TB) disease. However, asymptomatic early states of TB beyond latent TB infection and active disease can go unrecognized using current screening criteria. We conducted a longitudinal cohort study enrolling household contacts initially free of TB disease and followed them for the occurrence of incident TB over 1 year. Among 1,747 screened contacts, 27 (52%) of the 52 persons in whom TB subsequently developed during follow-up had a baseline abnormal radiograph. Of contacts without TB symptoms, persons with an abnormal radiograph were at higher risk for subsequent TB than persons with an unremarkable radiograph (adjusted hazard ratio 15.62 [95% CI 7.74-31.54]). In young adults, we found a strong linear relationship between radiograph severity and time to TB diagnosis. Our findings suggest chest radiograph screening can extend to detecting early TB states, thereby enabling timely intervention.

Point-of-care ultrasound for diagnosing extrapulmonary TB.

Despite the high morbidity and mortality globally, standard microbiologic diagnosis for TB requires laboratory infrastructure inaccessible in many resource-limited areas and may be insufficient for identifying extrapulmonary disease. Point-of-care (POC) ultrasound facilitates visualization of extrapulmonary manifestations, permitting laboratory-independent diagnosis, but its diagnostic utility remains unclear.We conducted a systematic review of five online databases for studies reporting ultrasound findings among cases with and without extrapulmonary TB (EPTB). A minimum of two authors independently screened and reviewed each article, and extracted data elements of interest. We conducted a series of univariate meta-analyses using a random-effects model to calculate the pooled effect estimate and 95% confidence interval (CI) for each outcome: sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).Of 279 articles identified, 6 were included. There were 699 cases of EPTB among 1,633 participants. The pooled sensitivity estimate was 0.72 (95% CI 0.57-0.88). The pooled specificity estimate was 0.77 (95% CI 0.63-0.90). The pooled PPV and NPV estimates were respectively 0.67 (95% CI 0.47-0.87) and 0.85 (95% CI 0.77-0.93).POC ultrasound showed modest test characteristics for diagnosing EPTB, which may constitute an improvement over some currently available diagnostics..

Adapted generative latent diffusion models for accurate pathological analysis in chest X-ray images.

Respiratory diseases have a significant global impact, and assessing these conditions is crucial for improving patient outcomes. Chest X-ray is widely used for diagnosis, but expert evaluation can be challenging. Automatic computer-aided diagnosis methods can provide support for clinicians in these tasks. Deep learning has emerged as a set of algorithms with exceptional potential in such tasks. However, these algorithms require a vast amount of data, often scarce in medical imaging domains. In this work, a new data augmentation methodology based on adapted generative latent diffusion models is proposed to improve the performance of an automatic pathological screening in two high-impact scenarios: tuberculosis and lung nodules. The methodology is evaluated using three publicly available datasets, representative of real-world settings. An ablation study obtained the highest-performing image generation model configuration regarding the number of training steps. The results demonstrate that the novel set of generated images can improve the performance of the screening of these two highly relevant pathologies, obtaining an accuracy of 97.09%, 92.14% in each dataset of tuberculosis screening, respectively, and 82.19% in lung nodules. The proposal notably improves on previous image generation methods for data augmentation, highlighting the importance of the contribution in these critical public health challenges.

Explainable deep-neural-network supported scheme for tuberculosis detection from chest radiographs.

Chest radiographs are examined in typical clinical settings by competent physicians for tuberculosis diagnosis. However, this procedure is time consuming and subjective. Due to the growing usage of machine learning techniques in applied sciences, researchers have begun applying comparable concepts to medical diagnostics, such as tuberculosis screening. In the period of extremely deep neural nets which comprised of hundreds of convolution layers for feature extraction, we create a shallow-CNN for screening of TB condition from Chest X-rays so that the model is able to offer appropriate interpretation for right diagnosis. The suggested model consists of four convolution-maxpooling layers with various hyperparameters that were optimized for optimal performance using a Bayesian optimization technique. The model was reported with a peak classification accuracy, F1-score, sensitivity and specificity of 0.95. In addition, the receiver operating characteristic (ROC) curve for the proposed shallow-CNN showed a peak area under the curve value of 0.976. Moreover, we have employed class activation maps (CAM) and Local Interpretable Model-agnostic Explanations (LIME), explainer systems for assessing the transparency and explainability of the model in comparison to a state-of-the-art pre-trained neural net such as the DenseNet.

Imaging of supra-thoracic tuberculosis.

Tuberculosis (TB) typically affects the lungs, but may involve many extra-pulmonary sites; with the latter especially prone in patients with human immunodeficiency virus infection. The clinical features of extra-pulmonary TB are often non-specific, mimicking many different disease entities. Application of the most appropriate imaging modality and knowing the imaging findings with clinical context awareness help initiation of further investigations, diagnosis and early treatment. This pictorial essay highlights the imaging spectrum of extra-pulmonary TB affecting the supra-thoracic region, i.e. brain, neck, and ear, nose and throat.

From Bench to Clinic: A Nitroreductase Rv3368c-Responsive Cyanine-Based Probe for the Specific Detection of Live Mycobacterium tuberculosis.

Tuberculosis (TB), characterized by high mortality and low diagnosis, is caused by a single pathogen, Mycobacterium tuberculosis (Mtb). Imaging tools that can be used to track Mtb without pre-labeling and to diagnose live Mtb in clinical samples can shorten the gap between bench and clinic, fuel the development of novel anti-TB drugs, strengthen TB prevention, and improve patient treatment. In this study, we report an unprecedented novel nitroreductase-responsive cyanine-based fluorescent probe (Cy3-NO2-tre) that rapidly and specifically labels Mtb and detects it in clinical samples. Cy3-NO2-tre generated fluorescence after activation by a specific nitroreductase, Rv3368c, which is conserved in the Mycobacteriaceae. Cy3-NO2-tre effectively imaged mycobacteria within infected host cells, tracked the infection process, and visualized Mycobacterium smegmatis being endocytosed by macrophages. Cy3-NO2-tre also detected Mtb in the sputum of patients with TB and exhibited excellent photostability. Furthermore, the Cy3-NO2-tre/auramine O percentage change within 7 ± 2 days post drug treatment in the sputum of inpatients was closely correlated with the reexamination results of the chest computed tomography, strongly demonstrating the clinical application of Cy3-NO2-tre as a prognostic indicator in monitoring the therapeutic efficacy of anti-TB drugs in the early patient care stage.

PET-CT-guided characterisation of progressive, preclinical tuberculosis infection and its association with low-level circulating Mycobacterium tuberculosis DNA in household contacts in Leicester, UK: a prospective cohort study.

BACKGROUND: Incipient tuberculosis, a progressive state of Mycobacterium tuberculosis infection with an increased risk of developing into tuberculosis disease, remains poorly characterised. Animal models suggest an association of progressive infection with bacteraemia. Circulating M tuberculosis DNA has previously been detected in pulmonary tuberculosis by use of Actiphage, a bacteriophage-based real-time PCR assay. We aimed to investigate whether serial [18F]fluorodeoxyglucose ([18F]FDG)-PET-CT could be used to characterise the state and progressive trajectory of incipient tuberculosis, and examine whether these PET-CT findings are associated with Actiphage-based detection of circulating M tuberculosis DNA. METHODS: We did a prospective 12-month cohort study in healthy, asymptomatic adults (aged ≥16 years) who were household contacts of patients with pulmonary tuberculosis, and who had a clinical phenotype of latent tuberculosis infection, in Leicester, UK. Actiphage testing of participants' blood samples was done at baseline, and [18F]FDG PET-CT at baseline and after 3 months. Baseline PET-CT features were classified as positive, indeterminate, or negative, on the basis of the quantitation (maximum standardised uptake value [SUVmax]) and distribution of [18F]FDG uptake. Microbiological sampling was done at amenable sites of [18F]FDG uptake. Changes in [18F]FDG uptake after 3 months were quantitatively categorised as progressive, stable, or resolving. Participants received treatment if features of incipient tuberculosis, defined as microbiological detection of M tuberculosis or progressive PET-CT change, were identified. FINDINGS: 20 contacts were recruited between Aug 5 and Nov 5, 2020; 16 of these participants had a positive result on IFNγ release assay (QuantiFERON-TB Gold Plus [QFT]) indicating tuberculosis infection. Baseline PET-CT scans were positive in ten contacts (all QFT positive), indeterminate in six contacts (three QFT positive), and negative in four contacts (three QFT positive). Four of eight PET-CT-positive contacts sampled had M tuberculosis identified (three through culture, one through Xpert MTB/RIF Ultra test) from intrathoracic lymph nodes or bronchial wash and received full antituberculosis treatment. Two further unsampled PET-CT-positive contacts were also treated: one with [18F]FDG uptake in the lung (SUVmax 9·4) received empirical antituberculosis treatment and one who showed progressive [18F]FDG uptake received preventive treatment. The ten untreated contacts with [18F]FDG uptake at baseline (seven QFT positive) had stable or resolving changes at follow-up and remained free of tuberculosis disease after 12 months. A positive baseline Actiphage test was associated with the presence of features of incipient tuberculosis requiring treatment (p=0·018). INTERPRETATION: Microbiological and inflammatory features of incipient tuberculosis can be visualised on PET-CT and are associated with M tuberculosis detection in the blood, supporting the development of pathogen-directed blood biomarkers of tuberculosis risk. FUNDING: MRC Confidence in Concept.

18 F-FDG PET/CT in Renal Allograft Tuberculosis Mimicking as Posttransplant Malignancy.

ABSTRACT: The most common complications after the renal transplant are infections and malignancies, including posttransplant lymphoproliferative disorders. Tubercular infection in renal allograft recipients is a relatively rare entity. However, nonspecific constitutional symptoms often delay diagnosis, leading to significant morbidity and mortality. We present the 18 F-FDG PET/CT findings in a patient with renal allograft tuberculosis who had clinical and imaging suspicion of posttransplant lymphoproliferative disorder or renal cell carcinoma. Histopathology from the renal lesion revealed tuberculosis.

Revisiting Computer-Aided Tuberculosis Diagnosis.

Tuberculosis (TB) is a major global health threat, causing millions of deaths annually. Although early diagnosis and treatment can greatly improve the chances of survival, it remains a major challenge, especially in developing countries. Recently, computer-aided tuberculosis diagnosis (CTD) using deep learning has shown promise, but progress is hindered by limited training data. To address this, we establish a large-scale dataset, namely the Tuberculosis X-ray (TBX11 K) dataset, which contains 11 200 chest X-ray (CXR) images with corresponding bounding box annotations for TB areas. This dataset enables the training of sophisticated detectors for high-quality CTD. Furthermore, we propose a strong baseline, SymFormer, for simultaneous CXR image classification and TB infection area detection. SymFormer incorporates Symmetric Search Attention (SymAttention) to tackle the bilateral symmetry property of CXR images for learning discriminative features. Since CXR images may not strictly adhere to the bilateral symmetry property, we also propose Symmetric Positional Encoding (SPE) to facilitate SymAttention through feature recalibration. To promote future research on CTD, we build a benchmark by introducing evaluation metrics, evaluating baseline models reformed from existing detectors, and running an online challenge. Experiments show that SymFormer achieves state-of-the-art performance on the TBX11 K dataset.

Does PET-CT Have a Role in the Evaluation of Tuberculosis Treatment in Phase 2 Clinical Trials?

Positron emission tomography-computed tomography (PET-CT) has the potential to revolutionize research in infectious diseases, as it has done with cancer. There is growing interest in it as a biomarker in the setting of early-phase tuberculosis clinical trials, particularly given the limitations of current biomarkers as adequate predictors of sterilizing cure for tuberculosis. PET-CT is a real-time tool that provides a 3-dimensional view of the spatial distribution of tuberculosis within the lung parenchyma and the nature of lesions with uptake (ie, whether nodular, consolidative, or cavitary). Its ability to provide functional data on changes in metabolism, drug penetration, and immune control of tuberculous lesions has the potential to facilitate drug development and regimen selection for advancement to phase 3 trials in tuberculosis. In this narrative review, we discuss the role that PET-CT may have in evaluating responses to drug therapy in active tuberculosis treatment and the challenges in taking PET-CT forward as predictive biomarker of relapse-free cure in the setting of phase 2 clinical trials.

Point-of-care ultrasound for tuberculosis and HIV-revisiting the focused assessment with sonography for HIV-associated tuberculosis (FASH) protocol and its differential diagnoses.

BACKGROUND: The 'Focused assessment with sonography for HIV-associated tuberculosis' (FASH) protocol has been applied and researched for over a decade in HIV-infected patients with suspected extra-pulmonary tuberculosis. Interpretation of target FASH features may be challenging as they can also indicate alternative opportunistic diseases. OBJECTIVES: The primary aim of the review was summarizing the accumulated evidence on the diagnostic accuracy of the FASH protocol including description of diagnoses of target FASH features. SOURCES: Literature was searched using PubMed, Google Scholar, and publications referencing the original FASH publications; data from identified studies were compiled with data from studies identified by a preceding Cochrane review. A meta-analysis was performed based on a generalized linearized mixed model. Data on differential diagnoses were compiled by literature review and retrospective evaluation of clinical data. CONTENT: We identified ten studies; abdominal target FASH features were most studied. Sensitivity and specificity estimates were 39% (95% CI 25-54) and 89% (95% CI 83-96) for enlarged lymph nodes (ten studies), and 30% (95% CI 16-45%) and 93% (95% CI 89-98%) for hypoechoic spleen lesions (eight studies). In people living with HIV differential diagnoses of target FASH features are multiple and primarily include other opportunistic infections and malignancies such as non-tuberculous mycobacterial infection, bacillary angiomatosis, hepato-splenic brucellosis, meliodiosis, visceral leishmaniasis, invasive fungal infections, and lymphoma as well as Kaposi sarcoma. Ultrasound-guided diagnostic sampling may assist obtention of a definitive diagnosis. IMPLICATIONS: On the basis of current evidence, although limited by methodology, and personal experience, we recommend basic ultrasound training, including the FASH protocol and ultrasound-guided diagnostic interventions, for all healthcare providers working with people living with HIV in resource-limited settings.

Contrast-enhanced ultrasound findings of gallbladder tuberculosis: a case report.

Preoperative diagnosis of gallbladder tuberculosis (TB) is difficult, and the contrast-enhanced ultrasound (CEUS) pattern has never been reported before. We present a case of TB in which CEUS had some special findings that were helpful for early diagnosis. The thickened gallbladder wall presented in the arterial phase of CEUS the "sandwich biscuit" sign with no enhancement in the middle layer and hyperenhancement in the inner and outer layers.

Frequency of abnormal findings on chest radiograph after positive PPD in children and adolescents in an urban setting in the United States.

BACKGROUND: Chest radiographs (CXR) for tuberculosis (TB) screening in children are valuable in high-burden settings. However, less certain in low prevalence contexts. In the United States, positive PPD is sufficient to treat for "latent" TB, or TB infection in asymptomatic patients. OBJECTIVE: We sought to determine frequency of abnormal CXR findings after a positive purified protein derivative (PPD) test at a tertiary pediatric center in the United States. METHOD: A retrospective evaluation was conducted of patients (0-18 years) with a CXR after a positive PPD (e.g., known exposure, employment, migratory requirements or before immunosuppression) between 2011 and 2021. Clinical information, demographics, and reason for PPD were recorded from health record. CXRs were evaluated using initial report and by a pediatric radiologist with special interest in TB and 8 years of experience. RESULT: Of 485 patients, median [interquartile range (IQR)] age 8.5[3.3-14.4], abnormal CXRs were described in 5 (1%). Most common reasons for PPD included: close contact with someone with TB or with high risk for TB. Most patients 373 (76.9%) received treatment for latent TB, and 111 (22.9%) no treatment. One patient (0.2%) received treatment for active disease. Radiographic findings included isolated lymphadenopathy (n = 2), consolidation (n = 1), pleural fluid/thickening (n = 1) and a patient with lymphadenopathy and a calcified nodule (n = 1). CONCLUSION: In our experience, prevalence of chest radiographs findings for patients with positive PPD was very low. Moreover, no cases of severe disease were seen and those with abnormal findings would not merit treatment change under current WHO guidelines.