Secondary Pulmonary Tuberculosis Research Articles

Retracted: Spiral CT Image Characteristics and Differential Diagnosis Secondary Pulmonary Tuberculosis and Lung Cancer Based on Visual Sensors.

[This retracts the article DOI: 10.1155/2022/7514898.].

Epidemiological characteristics of pulmonary tuberculosis among students in Guizhou, China: a retrospective study from 2010 to 2020

ObjectiveWe described epidemiological characteristics of pulmonary tuberculosis (PTB) among students and evaluated susceptible populations and areas in Guizhou province and also to provide scientific suggestions for prevention and control.SettingGuizhou, China.DesignThis...

Preface

The 2022 3rd International Conference on Internet of Things, Artificial Intelligence and Mechanical Automation (IoTAIMA 2022) was held virtually on July 22-24, 2022 in Shanghai, China. The conference provided a communication forum for the international experts and researchers in the fields of Internet of Things, Artificial Intelligence and Mechanical Automation to share research achievements, explore solutions to research challenges, encourage international collaborations, and boost development of science and technology.In the conference, we were greatly honored to have Prof. Ke Zhang from Shanghai Institute of Technology, China to serve as our Conference Chair. 120 individuals around the world took part in the conference. Divided into three parts, the conference agenda included keynote speeches, oral presentations and online Q&A discussion. Primarily, the keynote speakers were each allocated 30-45 minutes to address their speeches. Then in the next part, oral presentations, the excellent papers we had selected were presented by their authors one by one.Four distinguished professors were invited to hold keynote speeches during the conference. Among them, Prof. Xiaodong Liu from Dalian University of Technology performed a thought-provoking speech on Knowledge Discovery and Semantic Learning in the Framework of AFS Theory. Under the background that AFS theory gains increasing interest from various research fields, this survey aimed to report the current developments of theoretical research and practical advances on AFS theory. Firstly some notions and foundations of AFS theory with an illustrative example were reviewed and then various extensions of AFS theory for knowledge discovery were analyzed. And then Prof. Yudong Zhang from University of Leicester addressed a speech: Artificial Intelligence Theories and Methods for COVID-19 Recognition. In this research, CT scan, a medical imaging technique used in radiology to get detailed images of the body noninvasively for diagnostic purposes, was applied to discuss the recent AI theories and methods in chest CT-based COVID-19 diagnosis. Two other chest-related diseases: secondary pulmonary tuberculosis and community-acquired pneumonia, were covered in the study. Their insightful speeches had triggered heated discussion. And every participant praised this conference for disseminating useful and insightful knowledge.We are glad to share with you that we received lots of submissions from the conference and we selected a bunch of high-quality papers and compiled them into the proceedings after rigorously reviewing them. These papers feature but are not limited to the following topics: Radio Frequency Identification, New Sensing Technology, Intelligent Perception Systems, Unmanned System Control Technology, Automation etc. All the papers have been checked through rigorous review and processes to meet the requirements of publication.We would like to acknowledge all of those who supported IoTAIMA 2022 and made it a great success. Particularly, we would like to thank the Journal of Physics: Conference Series, for all the efforts of its colleagues in publishing this paper volume. We sincerely hope that the IoTAIMA 2022 turned out to be a forum for excellent discussions that enable new ideas to come about, promoting collaborative research.Committee of IoTAIMA 2022List of Committee member is available in this pdf.

AVNC: Attention-Based VGG-Style Network for COVID-19 Diagnosis by CBAM.

(Aim) To detect COVID-19 patients more accurately and more precisely, we proposed a novel artificial intelligence model. (Methods) We used previously proposed chest CT dataset containing four categories: COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis, and healthy subjects. First, we proposed a novel VGG-style base network (VSBN) as backbone network. Second, convolutional block attention module (CBAM) was introduced as attention module into our VSBN. Third, an improved multiple-way data augmentation method was used to resist overfitting of our AI model. In all, our model was dubbed as a 12-layer attention-based VGG-style network for COVID-19 (AVNC) (Results) This proposed AVNC achieved the sensitivity/precision/F1 per class all above 95%. Particularly, AVNC yielded a micro-averaged F1 score of 96.87%, which is higher than 11 state-of-the-art approaches. (Conclusion) This proposed AVNC is effective in recognizing COVID-19 diseases.

Computed Tomography Comparative Analysis of Nontuberculous Mycobacterial Lung Disease in the Elderly and Secondary Pulmonary Tuberculosis.

The study aimed to explore the key points of computed tomography (CT) differential diagnosis of nontuberculous mycobacteria (NTM) and secondary pulmonary tuberculosis in elderly patients. We retrospectively analyzed 45 patients with NTM pulmonary disease and 65 patients with secondary pulmonary tuberculosis. All patients were older than 60 years. The diseases were confirmed by laboratory examination. The general data and CT images of the 2 groups were compared and analyzed using χ 2 tests, single-factor analysis, and multivariate logistic regression analysis. Single-factor analysis showed significant differences between the 2 groups in 9 factors: bronchiectasis of the left upper lobe lingual segment, bronchiectasis of the right middle lobe, small nodules, large nodules, thin-walled cavities, thick-walled cavities, nonsubpleural hollows, strip opacity, and mediastinal lymph node enlargement ( P < 0.05). Multivariate logistic regression analysis showed that thin-walled cavities, bronchiectasis of the right middle lobe, small nodules, and large nodules were important factors in the differential diagnosis of the two groups. Nontuberculous mycobacteria show certain characteristics on CT, which are helpful for differential diagnosis when coupled with clinical and sputum smear examinations.

Spiral CT Image Characteristics and Differential Diagnosis Secondary Pulmonary Tuberculosis and Lung Cancer Based on Visual Sensors.

Helical CT plain scan has high spatial and area resolution, which is beneficial to the extraction of CT features of pulmonary nodules, and is of great significance for the diagnosis and differential diagnosis of pulmonary diseases. In order to deeply study the role of visual sensor image algorithm in CT image, this paper adopts clinical simulation method, data fusion method, and image acquisition method to collect images, analyze CT image features, and simplify the algorithm and create a CT model that can better diagnose secondary tuberculosis and lung cancer. We selected 45 patients with lung disease in this group, with an average age of 38 years. At the same time, the consistency analysis results of the diameter and plain CT value data of the five groups of cases measured by two observers are between 0.82 and 0.88, which has a good consistency. We could find that the nodule diameters of the five groups of cases were different (F =16.99, P < 0.01), and the difference was statistically significant (P < 0.06), indicating that our data are not only accurate but also very reliable. ROC was used to analyze the precise value of CT values in the pulmonary tuberculosis group and lung cancer group, intrapulmonary lymph node group, and pulmonary hamartoma group to determine the cutoff value. The results showed that the AUC values of the pulmonary tuberculosis group and the lung cancer group were 0.788, and the middle was the largest, indicating that the values were guaranteed. The basic realization starts with visual sensor technology and designs a clinical model that can more accurately identify CT images and differential diagnosis.

Giant bronchopleural fistula and empyema in a tuberculosis patient with diabetes mellitus: Vista from a high tuberculosis burden country in Southeast Asia.

Bronchopleural fistula is a pathological tract between the bronchial tree and the pleural space, which can be life-threatening due to tension pneumothorax. It is a rare complication in tuberculosis cases with highly variable in clinical manifestations and persistent air leaks which might lead to complications such as empyema. Herein, we present a tuberculosis and diabetic patient complicated with giant bronchopleural fistula and empyema. A 48-year-old man presented with shortness of breath for two weeks and cough with phlegm for two months. The patient was a smoker with severe Brinkman Index and diabetes. Physical examination revealed hyper resonant percussion and vesicular diminished on the left hemithorax. Laboratory results indicated the patient had anemia, leukocytosis, and hypoalbuminemia. GeneXpert sputum confirmed the presence of Mycobacterium tuberculosis and chest X-ray indicated a collapsed left lung. The patient was diagnosed with left secondary spontaneous pneumothorax, pulmonary tuberculosis, and diabetes. The patient was treated with chest tube drainage and anti- tuberculosis drugs. There was no improvement based on serial chest X-ray, and empyema appeared from the chest tube. CT-scan showed tuberculosis lesion, the collapsed of the left lung and fistula in segments 7-8 inferior lobe. Exploratory thoracostomy was performed, in which a giant bronchopleural fistula was detected and then repaired with BioGlue surgical adhesive. Unfortunately, the thoracostomy led to extensive subcutaneous emphysema and was treated by cervical mediastinotomy. The drainage was unable to be removed, and the patient was discharged with Heimlich-type drainage valves on day 28 of treatment. The empyema fluid was cultured and revealed Staphylococcus haemolyticus. This case highlights that tuberculosis could cause a bronchopleural fistula and empyema may occur secondary to late diagnosis that needs immediate surgery.

Histamine-containing lung cell structures in certain forms of secondary tuberculosis

The aim of research was to study the distribution of histamine in macrophages and mast cells of the lung structures in autopsy material in certain forms of secondary tuberculosis.Material and methods. The authors examined 165 cases of secondary pulmonary tuberculosis. The study included 500 histological specimens of male patients, aged 30 to 55 years, divided into 5 groups depending on the forms of secondary tuberculosis., The luminescent-histochemical method of Cross was used to determine the content of histamine in the lung structures; the specimens were further exposed to re-staining with hematoxylin and eosin.Results. Histamine-containing specific alveolar and interstitial macrophages and mast cells were detected when studying autopsy material from the lungs of "nominally healthy" people. The highest content of histamine in the lung structures of this group was recorded in interstitial macrophages. In acute focal tuberculosis, there was an increased content of histamine in intra-alveolar and interstitial macrophages, with a simultaneous decrease of this bioamine in mast cells. In fibro-focal tuberculosis, the content of histamine exceeded the control parameters in all the studied cellular lung structures, with the highest content in mast cells. In infiltrative tuberculosis, there was detected an infiltrative luminescent track from lymphocytes together with the maximum luminescence of histamine. In acute cavernous and fibrous-cavernous tuberculosis, total degranulation of mast cells was observed. The content of the studied bioamine significantly decreased in interstitial macrophages compared to the control group.Conclusion. The study of small forms of secondary tuberculosis detected an increased concentration of histamine in intra-alveolar and interstitial macrophages. Its maximum accumulation in all cellular structures was registered in the infiltrative form of tuberculosis. In destructive forms of tuberculosis, histamine was detected only in macrophages, which appeared to be the regulatory link of specific inflammation. The literature data and the results obtained allow us to report on the influence of Mycobacterium tuberculosis as a corpuscular antigen that causes destruction of structures that produce and metabolize neuroamines in the lungs.

Ensemble Learning With Attention-Based Multiple Instance Pooling for Classification of SPT

Tuberculosis is one of the most common infections in the human population, while reactivation of the MTB bacteria can lead to secondary pulmonary tuberculosis (SPT). SPT is a significant health risk for both immunocompromised individuals and the population of regional hotspots. This paper proposes a novel model for ensemble learning for the efficient identification of SPT in CT imaging. We reformulate the ensemble process as multiple instance learning and utilizes an attention-based pooling layer to ensemble features extracted from a range of base networks. The best performing model consists of 4 base models and an ensemble network with Hopfield-pooling. We abbreviate this model as Hopfield-pooling ensemble (HFPE). For the classification of CT slices between healthy controls and SPT patients, HFPE achieved an accuracy of 96.00±2.55%, specificity of 97.00±2.45%, precision of 96.99±2.46%, sensitivity of 95.00±4.47, and F1-score of 95.92±2.63%, achieving comparable or higher performances to a number of state-of-art approaches.

Secondary Pulmonary Tuberculosis Recognition by 4-Direction Varying-Distance GLCM and Fuzzy SVM

Tuberculosis (TB) is an infectious disease caused by Mycobacterium tuberculosis. Our study investigates the recognition of secondary pulmonary (SPTB). A novel F3 model is proposed. The first F means using a four-direction varying-distance gray-level co-occurrence matrix (FDVDGLCM) to analyze the chest CT images; the second F means a five-property feature set (FPFS) from the FDVDGLCM results; the third F means fuzzy support vector machine (FSVM). Besides, a slight adaption of multiple-way data augmentation is used to boost the training set. The 10 runs of 10-fold cross-validation demonstrate that this F3 model achieves a sensitivity of 93.68% ± 1.75%, a specificity of 94.17% ± 1.68%, a precision of 94.17% ± 1.55%, an accuracy of 93.92% ± 1.05%, an F1 score of 93.91% ± 1.07%, an MCC of 87.88% ± 2.09%, and an FMI of 93.92% ± 1.06%. The AUC is 0.9624. The FSVM can give better performance than ordinary SVM. The proposed F3 model is superior to six state-of-the-art SPTB recognition models.

Hand Tuberculous Chancre with Secondary Pulmonary Tuberculosis.

Hand Tuberculous Chancre with Secondary Pulmonary Tuberculosis.

Secondary Pulmonary Tuberculosis Identification Via pseudo-Zernike Moment and Deep Stacked Sparse Autoencoder.

Secondary pulmonary tuberculosis (SPT) is one of the top ten causes of death from a single infectious agent. To recognize SPT more accurately, this paper proposes a novel artificial intelligence model, which uses Pseudo Zernike moment (PZM) as the feature extractor and deep stacked sparse autoencoder (DSSAE) as the classifier. In addition, 18-way data augmentation is employed to avoid overfitting. This model is abbreviated as PZM-DSSAE. The ten runs of 10-fold cross-validation show this model achieves a sensitivity of 93.33% ± 1.47%, a specificity of 93.13% ± 0.95%, a precision of 93.15% ± 0.89%, an accuracy of 93.23% ± 0.81%, and an F1 score of 93.23% ± 0.83%. The area-under-curve reaches 0.9739. This PZM-DSSAE is superior to 5 state-of-the-art approaches.

Neurotransmitter level in neuroamin-containing lung structures in different forms of tuberculosis

The aim of the study was to identify features of varying localization of monoamines (catecholamines, serotonin) in the cell structures in tuberculosis-affected lung autopsy samples. Material and methods. 165 cases of secondary pulmonary tuberculosis were studied by examining 2,500 histological preparations from patients aged 30 to 55 years, divided into 5 groups, corresponding to the forms of tuberculosis. The Falck–Hillarp luminescence-histochemical method was used to determine the content of neurotransmitters in lung structures. Results. While using the Falck–Hillarp luminescence-histochemical method, mycobacteria tuberculosis containing catecholamines and serotonin were detected in autopsy material of lungs affected by a specific inflammatory process, as well as neuroamine-containing granular luminescent cells and mast cells. Affected and intact areas of the lungs contain different amounts of monoamines. The number of cells and level of the bioamines studied depends on the form of secondary tuberculosis. It was found that in small forms of secondary tuberculosis (acute focal, fibrous-focal, infiltrative), the number of cells and quantitative parameters of neurotransmitters (catecholamines, serotonin) examined in granular luminescent and mast cells change to rise. In case of lung destructive processes, the level of catecholamines in the structures studied of affected area was higher than in control. The concentration of serotonin in the studied cells lung tissue affected by the tuberculosis process was reduced. Elastic nerve fibers at the sites of mycobacteria were altered as well. They displayed no clear luminescence, looked “swollen”, sometimes lacking varicose veins. Conclusion. Comparing the results of the study with the literature data, it was found that pulmonary tuberculosis occurs as a delayed reaction, and Mycobacterium tuberculosis manifests itself as a corpuscular antigen.

DSSAE: Deep Stacked Sparse Autoencoder Analytical Model for COVID-19 Diagnosis by Fractional Fourier Entropy

( Aim ) COVID-19 has caused more than 2.28 million deaths till 4/Feb/2021 while it is still spreading across the world. This study proposed a novel artificial intelligence model to diagnose COVID-19 based on chest CT images. ( Methods ) First, the two-dimensional fractional Fourier entropy was used to extract features. Second, a custom deep stacked sparse autoencoder (DSSAE) model was created to serve as the classifier. Third, an improved multiple-way data augmentation was proposed to resist overfitting. ( Results ) Our DSSAE model obtains a micro-averaged F1 score of 92.32% in handling a four-class problem (COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis, and healthy control). ( Conclusion ) Our method outperforms 10 state-of-the-art approaches.

Deep Fractional Max Pooling Neural Network for COVID-19 Recognition.

Aim: Coronavirus disease 2019 (COVID-19) is a form of disease triggered by a new strain of coronavirus. This paper proposes a novel model termed “deep fractional max pooling neural network (DFMPNN)” to diagnose COVID-19 more efficiently.Methods: This 12-layer DFMPNN replaces max pooling (MP) and average pooling (AP) in ordinary neural networks with the help of a novel pooling method called “fractional max-pooling” (FMP). In addition, multiple-way data augmentation (DA) is employed to reduce overfitting. Model averaging (MA) is used to reduce randomness.Results: We ran our algorithm on a four-category dataset that contained COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis (SPT), and healthy control (HC). The 10 runs on the test set show that the micro-averaged F1 (MAF) score of our DFMPNN is 95.88%.Discussions: This proposed DFMPNN is superior to 10 state-of-the-art models. Besides, FMP outperforms traditional MP, AP, and L2-norm pooling (L2P).

Pathogenesis of Secondary Pulmonary Tuberculosis and Role of Cord Factor in Secondary Infection

The primary and secondary tuberculosis features two completely different pathogenesis.At present,the pathogenesis of primary tuberculosis has been clear,whereas that of secondary tuberculosis remains unclear.In order to decipher the mechanism of secondary infection of Mycobacterium tuberculosis and provide insights into vaccine research and drug development,this paper reviews the problems of the widely accepted mechanism of secondary infection,the new findings of the research on the mechanism,as well as the role of cord factors.

Comparison of Chest X-Ray Findings Between Primary and Secondary Multidrug Resistant Pulmonary Tuberculosis

Introduction: Radiological imaging has a key role in multidrug-resistant (MDR) pulmonary tuberculosis (TB) screening and diagnosis. However, new cases of MDR pulmonary TB are often overlooked; therefore, its transmission might continue before its diagnosis. The most widely used and affordable radiological modality is a chest radiograph. This study aims to describe the characteristics of primary and secondary MDR pulmonary TB chest x-ray findings for differential diagnosis.&#x0D; Methods: This study was an analytic observational study with a retrospective design. Researchers evaluated medical record data of primary and secondary MDR pulmonary TB patients who underwent chest x-ray examinations. The patient's chest x-rays were then evaluated. Evaluated variables were lung, pleural, and mediastinal abnormalities and severity category.&#x0D; Results: The most common chest x-ray finding in primary MDR pulmonary TB was consolidation (96.2%), which was mostly unilateral (52.0%), accompanied by cavities (71.2%), most of which were multiple (83.8%) with a moderate category of severity. The most common chest x-ray finding in secondary MDR pulmonary TB was consolidation (100%), which was mostly bilateral (60.4%), accompanied by cavities (80.2%), most of which were multiple (90.1%) with severe category of severity. Pleural thickening (47.5%) was also found.&#x0D; Conclusion: There was a significant difference between primary and secondary MDR pulmonary TB in terms of mild severity category, and pleural thickening. Mild severity category is mostly found in primary MDR-TB and pleural thickening is mostly found in secondary TB.

Comparison of Chest X-Ray Findings Between Primary and Secondary Multidrug Resistant Pulmonary Tuberculosis

Introduction: Radiological imaging has a key role in multidrug-resistant (MDR) pulmonary tuberculosis (TB) screening and diagnosis. However, new cases of MDR pulmonary TB are often overlooked; therefore, its transmission might continue before its diagnosis. The most widely used and affordable radiological modality is a chest radiograph. This study aims to describe the characteristics of primary and secondary MDR pulmonary TB chest x-ray findings for differential diagnosis.&#x0D; Methods: This study was an analytic observational study with a retrospective design. Researchers evaluated medical record data of primary and secondary MDR pulmonary TB patients who underwent chest x-ray examinations. The patient's chest x-rays were then evaluated. Evaluated variables were lung, pleural, and mediastinal abnormalities and severity category.&#x0D; Results: The most common chest x-ray finding in primary MDR pulmonary TB was consolidation (96.2%), which was mostly unilateral (52.0%), accompanied by cavities (71.2%), most of which were multiple (83.8%) with a moderate category of severity. The most common chest x-ray finding in secondary MDR pulmonary TB was consolidation (100%), which was mostly bilateral (60.4%), accompanied by cavities (80.2%), most of which were multiple (90.1%) with severe category of severity. Pleural thickening (47.5%) was also found.&#x0D; Conclusion: There was a significant difference between primary and secondary MDR pulmonary TB in terms of mild severity category, and pleural thickening. Mild severity category is mostly found in primary MDR-TB and pleural thickening is mostly found in secondary TB.

Bilateral secondary pulmonary tuberculosis complicated with bilateral chylothorax: a case report

A 26-year-old female was admitted to the emergency department of thoracic surgery complaining of chest tightness, shortness of breath, and a history of bilateral tuberculosis. A chest Computed Tomography (CT) scan showed bilateral pleural effusion. After that, the patient was implanted with bilateral intercostal drainage tubes. Further analysis of the pleural effusion was conducted to confirm the diagnosis of bilateral chylothorax. We initiated conservative treatment consisting of fasting and total parenteral nutrition. After the failure of conservative treatment, the patient underwent ligation of the thoracic duct by right-sided thoracotomy combined with talc slurry. On the first day postoperatively, the right pleural effusion had decreased significantly, while the left pleural effusion had not. Subsequently, talc slurry was injected into the left thoracic drainage tube of the patient. Bilateral pleural effusion was significantly reduced. Re-examination chest X-ray showed the disappearance of pleural effusion, and the patient was discharged good healthy. Chest X-rays were reexamined one month postoperatively, and the patient's lung was well dilated, with no recurrence of pleural effusion. In this case, it was shown that conservative treatment is the first choice for chylothorax. However, if this proves to be ineffective, early surgical treatment should be considered. Early diagnosis and timely surgical intervention are the key factors to improve the prognosis of patients.

Explainable diagnosis of secondary pulmonary tuberculosis by graph rank-based average pooling neural network

AimWe propose a novel graph rank-based average pooling neural network (GRAPNN) to detect secondary pulmonary tuberculosis patients via chest CT imaging.MethodsFirst, we propose a novel rank-based pooling neural network (RAPNN) to learn the individual image-level features from chest CT images. Second, we integrate the graph convolutional network (GCN), which learns relation-aware representation among the batch of chest CT images, to RAPNN. Third, we build a novel Graph RAPNN (GRAPNN) model based on the previous integration via k-means clustering and k-nearest neighbors’ algorithm. Besides, an improved data augmentation is utilized to handle overfitting problem. Grad-ACM is used to make this GRAPNN model explainable.ResultsThis proposed GRAPNN method is compared with seven state-of-the-art algorithms. The results showed GRAPNN model yields the best performances with a sensitivity of 94.65%, a specificity of 95.12%, a precision of 95.17%, an accuracy of 94.88%, and an F1 score of 94.87%.ConclusionsOur GRAPNN is superior to other seven state-of-the-art approaches. The explainable mechanism in our method can identify the lesions of important lung parts (tuberculosis cavities and surrounding small lesions) for transparent decision.