Radiological difference between new sputum-positive and sputum-negative pulmonary tuberculosis

Deependra, K; Kirti, Ravi; Kumar, Subhash; Karmakar, Saurabh; Thakur, Seema

doi:10.4103/jfmpc.jfmpc_652_19

Cited by 8 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also analysed the radiological pro ile among the 36 cases detected on Gene Xpert and found that 44%had non homogenous opacity, 25 % had homogenous opacity with air bronchogram, 17% had cavitation, 8% had nodules and 6 % had hilar enlargement. In a study done by Deependra k rai et al patchy in iltrates and cavitation was observed in sputum positive compared to sputum negative cases, but in our study we could not make that comparison as we have studied only sputum negative PTB suspects (Rai et al, 2019).…”

Section: Resultsmentioning

confidence: 71%

Diagnostic accuracy of BAL Gene Xpert compared to BAL AFB staining in Sputum negative Pulmonary Tuberculosis Suspects

G¹,

Aradhyula²,

Gangadharan³

et al. 2020

ijrps

View full text Add to dashboard Cite

Tuberculosis has stood the test of time over the millennia and still wreaks havoc on human life all over the world. We have studied the role of bronchoscopy in smear negative PTB suspects and have compared the results of BAL Gene Xpert with BAL AFB staining among the study population. We have also determined the microbiological profile in cases who are MTB negative. We retrospectively reviewed the respiratory samples (sputum and BAL) of 82 sputum negative PTB suspects from july 2018 – july 2019 for ZN stain and Gene Xpert. 25 cases were detected by Gene Xpert additionally to the 11 cases detected by BAL afb staining alone. Out of the 36 cases detected on gene Xpert 3(8%) were RIF resistant. These 5 samples which were positive on BAL AFB and negative on Gene Xpert,are suspected to be NON TB mycobacteria. Out of the remaining 41 samples, non TB culture results showed 8 Acinetobacter, 10 pseudomonas, 12 klebsiella, 2 e.coli,2 candida, 7 no growth on culture. According to our study, the bronchoscopic samples when subjected to Gene Xpert detect a higher number of cases which would go undetected otherwise compared to BAL AFB staining. Hence, bronchoscopy must be performed on such smear negative suspects and Gene Xpert could replace smear microscopy as initial diagnostic testing. It also helps in detecting first line drug resistance in addition.

show abstract

Section: Resultsmentioning

confidence: 71%

Diagnostic accuracy of BAL Gene Xpert compared to BAL AFB staining in Sputum negative Pulmonary Tuberculosis Suspects

G¹,

Aradhyula²,

Gangadharan³

et al. 2020

ijrps

View full text Add to dashboard Cite

show abstract

“…12 In another Indian study frequency of patchy consolidation (78.9% vs 49.5%) and cavitation (36.8% vs 15.6%) was significantly higher in smear positive patients. 2 CXR features of smear negative pulmonary TB cases differs from smear positive pulmonary TB cases probably due to lower bacillary load. Parenchymal lobe involved showed upper and middle lobes to be more commonly involved.…”

Section: Discussionmentioning

confidence: 87%

“…1 Prompt diagnosis of TB facilitates timely therapeutic interventions and minimizes community transmission. 2 For the diagnosis of pulmonary TB, smear microscopy and culture of the respiratory specimen are considered as the gold standard. Culture has the disadvantage of long turn-around time, which limits its usefulness as an initial diagnostic test.…”

Section: Introductionmentioning

confidence: 99%

Pulmonary tuberculosis: An observational study to compare radiographic abnormalities with reference to smear microscopy status

Agarwal¹,

Narayan

Agarwal³

et al. 2022

PJMS

View full text Add to dashboard Cite

Interpretation of Chest X Ray (CXR) in relation to sputum smear microscopy can be useful in early diagnosis of pulmonary TB. The study aimed to compare the CXR findings in pulmonary TB cases with positive sputum microscopy and negative sputum microscopy. Patients with presumptive pulmonary TB were grouped into smear positive pulmonary TB and smear negative pulmonary TB groups based on CXR and sputum smear microscopy. CXR findings in the two groups were compared using chi square and students- t test. A total of 225 patients with presumptive pulmonary TB were evaluated. Of these, 174 subjects were included in the study: 129 (74.2%) in smear positive pulmonary TB group and 45(25.8%) in smear negative pulmonary TB group. Parenchymal involvement was the most common finding in both smear positive and smear negative groups seen in 118 (91.5%) and 42 (93.3%) subjects, respectively. The area of parenchymal involvement was significantly more in smear positive group as compared to smear negative group (p<0.001). Cavitation was more commonly associated with smear positive group (p=0.005) Nodal enlargement was significantly more common among smear negative subjects (p<.001). CXR could detect 25.8% smear negative pulmonary TB cases. Extensive parenchymal infiltration and cavitation were more commonly associated with smear positive patients whereas nodal involvement was significantly more common in smear negative patients.

show abstract

“…Research in the application of deep learning to radiology (10,11) is a rapidly growing field as a result of its promising performance in disease detection, such as pleural effusion and cardiomegaly detection on chest radiographs (12,13), and mediastinal lymph node and lung nodule detection on computed tomography (CT) (14,15). Researchers have realized that AI-based chest X-ray (CXR) is a very promising tool for diagnosing TB, especially in resource-limited rural areas (10).…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based pulmonary tuberculosis automated detection on chest radiography: large-scale independent testing

Zhou¹,

Cheng²,

Zhang³

et al. 2022

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: It is critical to have a deep learning-based system validated on an external dataset before it is used to assist clinical prognoses. The aim of this study was to assess the performance of an artificial intelligence (AI) system to detect tuberculosis (TB) in a large-scale external dataset.Methods: An artificial, deep convolutional neural network (DCNN) was developed to differentiate TB from other common abnormalities of the lung on large-scale chest X-ray radiographs. An internal dataset with 7,025 images was used to develop the AI system, including images were from five sources in the U.S. and China, after which a 6-year dynamic cohort accumulation dataset with 358,169 images was used to conduct an independent external validation of the trained AI system.Results: The developed AI system provided a delineation of the boundaries of the lung region with a Dice coefficient of 0.958. It achieved an AUC of 0.99 and an accuracy of 0.948 on the internal data set, and an AUC of 0.95 and an accuracy of 0.931 on the external data set when it was used to detect TB from normal images. The AI system achieved an AUC of more than 0.9 on the internal data set, and an AUC of over 0.8 on the external data set when it was applied to detect TB, non-TB abnormal and normal images. Conclusions:We conducted a real-world independent validation, which showed that the trained system can be used as a TB screening tool to flag possible cases for rapid radiologic review and guide further examinations for radiologists.

show abstract

Radiological difference between new sputum-positive and sputum-negative pulmonary tuberculosis

Cited by 8 publications

References 9 publications

Diagnostic accuracy of BAL Gene Xpert compared to BAL AFB staining in Sputum negative Pulmonary Tuberculosis Suspects

Diagnostic accuracy of BAL Gene Xpert compared to BAL AFB staining in Sputum negative Pulmonary Tuberculosis Suspects

Pulmonary tuberculosis: An observational study to compare radiographic abnormalities with reference to smear microscopy status

Deep learning-based pulmonary tuberculosis automated detection on chest radiography: large-scale independent testing

Contact Info

Product

Resources

About