Chest x-ray analysis with deep learning-based software as a triage test for pulmonary tuberculosis: a prospective study of diagnostic accuracy for culture-confirmed disease

To assess the value of routine preoperative chest x-ray films in pediatric patients, a prospective study of 1,500 patients, ages newborn to 19 years, was undertaken. Of all the patients, 7.5% demonstrated at least one roentgenographic abnormality, with 4.7% of the patients demonstrating a totally unsuspected significant roentgenographic anomaly. In 3.8% of the patients, surgery was either postponed or cancelled or the anesthetic technique was altered as a result of the roentgenographic finding. It is believed that the routine preoperative chest film is justified if the film is evaluated before surgery and the results clinically followed up.

Download Full-text

Can We Screen Febrile Children for Pneumonia and/or Bacteremia Without Chest X-ray Films and Blood Cultures?

PEDIATRICS ◽

10.1542/peds.61.2.332a ◽

1978 ◽

Vol 61 (2) ◽

pp. 332-333

Author(s):

Henry M. Feder

Keyword(s):

Young Children ◽

Prospective Study ◽

False Negative ◽

Blood Cultures ◽

Chest Roentgenogram ◽

Negative Group ◽

X Ray ◽

Chest X Ray ◽

Wbc Count ◽

A Prospective Study

McCarthy et al. in their article "Temperature Greater Than or Equal to 40 C in Children Less Than 24 Months of Age: A Prospective Study" (Pediatrics 59:663, May 1977) recommend using both WBC count (≥ 15,000/cu mm) and ESR (≥ 30 mm/hr) for screening febrile young children for pneumonia or bacteremia. If either is elevated they suggest doing blood cultures and taking a chest roentgenogram. However, in 25% of their patients with bacteremia and 42% of their patients with pneumonia neither WBC count nor ESR was elevated, leaving a sizable false-negative group.

Download Full-text

Which method is best for an early accurate diagnosis of acute heart failure? Comparison between lung ultrasound, chest X-ray and NT pro-BNP performance: a prospective study

Internal and Emergency Medicine ◽

10.1007/s11739-016-1498-3 ◽

2016 ◽

Vol 12 (6) ◽

pp. 861-869 ◽

Cited By ~ 13

Author(s):

Stefano Sartini ◽

Jacopo Frizzi ◽

Matteo Borselli ◽

Elisabetta Sarcoli ◽

Carolina Granai ◽

...

Keyword(s):

Heart Failure ◽

Prospective Study ◽

Acute Heart Failure ◽

Lung Ultrasound ◽

Accurate Diagnosis ◽

X Ray ◽

Chest X Ray ◽

A Prospective Study

Download Full-text

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

Pakistan Journal of Medical Sciences ◽

10.12669/pjms.38.1.4531 ◽

2021 ◽

Vol 38 (1) ◽

Author(s):

Tahira Nishtar ◽

Shamsullah Burki ◽

Fatima Sultan Ahmad ◽

Tabish Ahmad

Keyword(s):

Pulmonary Tuberculosis ◽

Diagnostic Accuracy ◽

World Health ◽

Computer Aided Detection ◽

Pulmonary Tb ◽

High Burden ◽

X Ray ◽

Computer Aided ◽

Chest X Ray ◽

Computer Aided Reading

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. Abbreviations: TB = Tuberculosis, WHO = World Health Organization, CAD4TB = Computer aided detection for tuberculosis, CXR = Chest X-Ray, CAR = Computer aided reading. doi: https://doi.org/10.12669/pjms.38.1.4531 How to cite this:Nishtar T, Burki S, Ahmad FS, Ahmad T. Diagnostic accuracy of computer aided reading of chest x-ray in screening for pulmonary tuberculosis in comparison with Gene-Xpert. Pak J Med Sci. 2022;38(1):---------. doi: https://doi.org/10.12669/pjms.38.1.4531 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Download Full-text

The application of Hybrid deep learning Approach to evaluate chest ray images for the diagnosis of pneumonia in children

10.1101/2020.12.03.20243550 ◽

2020 ◽

Author(s):

Mohammad Ali Abbasa ◽

Syed Usama Khalid Bukhari ◽

Syed Khuzaima Arssalan Bokhari ◽

manal niazi

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Diagnostic Accuracy ◽

Morbidity And Mortality ◽

Hybrid Architecture ◽

X Ray ◽

Light Gradient ◽

Study Results ◽

Chest X Ray ◽

Hybrid Machine

AbstractBackgroundPneumonia is a leading cause of morbidity and mortality worldwide, particularly among the developing nations. Pneumonia is the most common cause of death in children due to infectious etiology. Early and accurate Pneumonia diagnosis could play a vital role in reducing morbidity and mortality associated with this ailment. In this regard, the application of a new hybrid machine learning vision-based model may be a useful adjunct tool that can predict Pneumonia from chest X-ray (CXR) images.Aim & Objectivewe aimed to assess the diagnostic accuracy of hybrid machine learning vision-based model for the diagnosis of Pneumonia by evaluating chest X-ray (CXR) imagesMaterials & MethodsA total of five thousand eight hundred and fifty-six digital X-ray images of children from ages one to five were obtained from the Chest X-Ray Pneumonia dataset using the Kaggle site. The dataset contains fifteen hundred and eighty-three digital X-ray images categorized as normal, where four thousand two hundred and seventy-three digital X-ray images are categorized as Pneumonia by an expert clinician. In this research project, a new hybrid machine learning vision-based model has been evaluated that can predict Pneumonia from chest X-ray (CXR) images. The proposed model is a hybrid of convolutional neural network and tree base algorithms (random forest and light gradient boosting machine). In this study, a hybrid architecture with four variations and two variations of ResNet architecture are employed, and a comparison is made between them.ResultsIn the present study, the analysis of digital X-ray images by four variations of hybrid architecture RN-18 RF, RN-18 LGBM, RN-34 RF, and RN-34 LGBM, along with two variations of ResNet architecture, ResNet-18 and ResNet-30 have revealed the diagnostic accuracy of 97.78%, 96.42%, 97.1%,96.59%, 95.05%, and 95.05%, respectively.DiscussionThe analysis of the present study results revealed more than 95% diagnostic accuracy for the diagnosis of Pneumonia by evaluating chest x-ray images of children with the help of four variations of hybrid architectures and two variations of ResNet architectures. Our findings are in accordance with the other published study in which the author used the deep learning algorithm Chex-Net with 121 layers.ConclusionThe hybrid machine learning vision-based model is a useful tool for the assessment of chest x rays of children for the diagnosis of Pneumonia.

Download Full-text