Learning Invariant Feature Representation to Improve Generalization Across Chest X-Ray Datasets

The world is experiencing an unprecedented crisis due to the coronavirus disease (COVID-19) outbreak that has affected nearly 216 countries and territories across the globe. Since the pandemic outbreak, there is a growing interest in computational model-based diagnostic technologies to support the screening and diagnosis of COVID-19 cases using medical imaging such as chest X-ray (CXR) scans. It is discovered in initial studies that patients infected with COVID-19 show abnormalities in their CXR images that represent specific radiological patterns. Still, detection of these patterns is challenging and time-consuming even for skilled radiologists. In this study, we propose a novel convolutional neural network- (CNN-) based deep learning fusion framework using the transfer learning concept where parameters (weights) from different models are combined into a single model to extract features from images which are then fed to a custom classifier for prediction. We use gradient-weighted class activation mapping to visualize the infected areas of CXR images. Furthermore, we provide feature representation through visualization to gain a deeper understanding of the class separability of the studied models with respect to COVID-19 detection. Cross-validation studies are used to assess the performance of the proposed models using open-access datasets containing healthy and both COVID-19 and other pneumonia infected CXR images. Evaluation results show that the best performing fusion model can attain a classification accuracy of 95.49% with a high level of sensitivity and specificity.

Download Full-text

Model Helps Reduce Chest X-Ray Usage

Pediatric News ◽

10.1016/s0031-398x(05)70569-5 ◽

2005 ◽

Vol 39 (9) ◽

pp. 26

Keyword(s):

X Ray ◽

Chest X Ray

Download Full-text

Comment on Adar et al, page 106 - 114 Calcifications in the aortic arch on chest x-ray - Incidental finding or valuable surrogate marker for cardiovascular risk?

VASA ◽

10.1024/0301-1526/a000412 ◽

2015 ◽

Vol 44 (2) ◽

pp. 83-84

Author(s):

Sasan Partovi ◽

Daniel Staub

Keyword(s):

Cardiovascular Risk ◽

Aortic Arch ◽

Incidental Finding ◽

Surrogate Marker ◽

X Ray ◽

Chest X Ray

Download Full-text

Tuberculosis: Diagnostic Challenges in Rural Africa

Praxis ◽

10.1024/1661-8157/a003355 ◽

2019 ◽

Vol 108 (15) ◽

pp. 991-996

Author(s):

Ngisi Masawa ◽

Farida Bani ◽

Robert Ndege

Keyword(s):

Extrapulmonary Tuberculosis ◽

X Ray ◽

Molecular Tests ◽

Rural Settings ◽

Chest X Ray ◽

Screening Questions ◽

Rural Africa ◽

Tb Diagnostics ◽

Strip Test ◽

Urine Strip

Abstract. Tuberculosis (TB) remains among the top 10 infectious diseases with highest mortality globally since the 1990s despite effective chemotherapy. Among 10 million patients that fell ill with tuberculosis in the year 2017, 36 % were undiagnosed or detected and not reported; the number goes as high as 55 % in Tanzania, showing that the diagnosis of TB is a big challenge in the developing countries. There have been great advancements in TB diagnostics with introduction of the molecular tests such as Xpert MTB/RIF, loop-mediated isothermal amplification, lipoarabinomannan urine strip test, and molecular line-probe assays. However, most of the hospitals in Tanzania still rely on the TB score chart in children, the WHO screening questions in adults, acid-fast bacilli and chest x-ray for the diagnosis of TB. Xpert MTB/RIF has been rolled-out but remains a challenge in settings where the samples for testing must be transported over many kilometers. Imaging by sonography – nowadays widely available even in rural settings of Tanzania – has been shown to be a useful tool in the diagnosis of extrapulmonary tuberculosis. Despite all the efforts and new diagnostics, 30–50 % of patients in high-burden TB countries are still empirically treated for tuberculosis. More efforts need to be placed if we are to reduce the death toll by 90 % until 2030.

Download Full-text

Lingual Dystonia Treated with Botulinum Toxin - A Case Report

Journal of Bangladesh College of Physicians and Surgeons ◽

10.3329/jbcps.v24i2.152 ◽

1970 ◽

Vol 24 (2) ◽

pp. 75-78

Author(s):

MA Hayee ◽

QD Mohammad ◽

H Rahman ◽

M Hakim ◽

SM Kibria

Keyword(s):

Botulinum Toxin ◽

Botulinum Toxin A ◽

Botulinum Toxin Type A ◽

Botulinum Toxin Type ◽

X Ray ◽

Medical College ◽

Lingual Dystonia ◽

History Of ◽

Chest X Ray

A 42-year-old female presented in Neurology Department of Sir Salimullah Medical College with gradually worsening difficulty in talking and eating for the last four months. Examination revealed dystonic tongue, macerated lips due to continuous drooling of saliva and aspirated lungs. She had no history of taking antiparkinsonian, neuroleptics or any other drugs causing dystonia. Chest X-ray revealed aspiration pneumonia corrected later by antibiotics. She was treated with botulinum toxin type-A. Twenty units of toxin was injected in six sites of the tongue. The dystonic tongue became normal by 24 hours. Subsequent 16 weeks follow up showed very good result and the patient now can talk and eat normally. (J Bangladesh Coll Phys Surg 2006; 24: 75-78)

Download Full-text

Hubungan antara Luas Lesi pada Foto Toraks Penderita TB Paru Dewasa yang Memiliki Riwayat Diabetes Melitus dengan Indeks Massa Tubuh di Rumah Sakit Hasan Sadikin Bandung

Jurnal Radiologi Indonesia ◽

10.33748/jradidn.v1i3.18 ◽

2016 ◽

Vol 1 (3) ◽

pp. 138-144

Author(s):

Ina Edwina ◽

Rista D Soetikno ◽

Irma H Hikmat

Keyword(s):

Chest Radiograph ◽

Chi Square ◽

Pulmonary Tb ◽

X Ray ◽

Consecutive Sampling ◽

Close Relationship ◽

Chi Square Test ◽

Chest X Ray ◽

The Relationship ◽

Diabetes Melitus

Background: Tuberculosis (TB) and diabetes mellitus (DM) prevalence rates are increasing rapidly, especially in developing countries like Indonesia. There is a relationship between TB and DM that are very prominent, which is the prevalence of pulmonary TB with DM increased by 20 times compared with pulmonary TB without diabetes. Chest X-ray picture of TB patients with DM is atypical lesion. However, there are contradictories of pulmonary TB lesion on chest radiograph of DM patients. Nutritional status has a close relationship with the morbidity of DM, as well as TB.Objectives: The purpose of this study was to determine the relationship between the lesions of TB on the chest radiograph of patients who su?er from DM with their Body Mass Index (BMI) in Hasan Sadikin Hospital Bandung.Material and Methods: The study was conducted in Department of Radiology RSHS Bandung between October 2014 - February 2015. We did a consecutive sampling of chest radiograph and IMT of DM patients with clinical diagnosis of TB, then the data was analysed by Chi Square test to determine the relationship between degree of lesions on chest radiograph of pulmonary TB on patients who have DM with their BMI.Results: The results showed that adult patients with active pulmonary TB with DM mostly in the range of age 51-70 years old, equal to 62.22%, with the highest gender in men, equal to 60%. Chest radiograph of TB in patients with DM are mostly seen in people who are obese, which is 40% and the vast majority of lesions are minimal lesions that is equal to 40%.Conclusions: There is a signifcant association between pulmonary TB lesion degree with BMI, with p = 0.03

Download Full-text