Computer-aided detection for tuberculosis and silicosis in chest radiographs of gold miners of South Africa

2020 ◽  
Vol 24 (4) ◽  
pp. 444-451
Author(s):  
C. Young ◽  
S. Barker ◽  
R. Ehrlich ◽  
B. Kistnasamy ◽  
A. Yassi
Keyword(s):  
Disease Burden ◽  
Operating Characteristic ◽  
Screening Tool ◽  
Characteristic Curve ◽  
Chest Radiographs ◽  
Computer Aided Detection ◽  
High Incidence ◽  
Computer Aided ◽  
Gold Miners ◽  
Compensation Claims

BACKGROUND: For over one hundred years, the gold mining sector has been a considerable source of tuberculosis (TB) and silicosis disease burden across Southern Africa. Reading chest radiographs (CXRs) is an expert and time-intensive process necessary for the screening and diagnosis of lung disease and the provision of evidence for compensation claims. Our study explores the use of computer-aided detection (CAD) of TB and silicosis in CXRs of a population with a high incidence of both diseases.METHODS: A set of 330 CXRs with human expert-determined classifications of silicosis, TB, silcotuberculosis and normal were provided to four health technology companies. The ability of each of their respective CAD systems to predict disease was assessed using receiver operating characteristic curve analysis of the under the curve metric.RESULTS: Three of the four systems differentiated accurately between TB and normal images, while two differentiated accurately between silicosis and normal images. Inclusion of silicotuberculosis images reduced each system's ability to detect either disease. In differentiating between any abnormal from normal CXR, the most accurate system achieved both a sensitivity and specificity of 98.2%.CONCLUSION: The current ability of CAD to differentiate between TB and silicosis is limited, but its use as a mass screening tool for both diseases shows considerable promise.

scholarly journals An AI-Based Algorithm for the Automatic Classification of Thoracic Radiographs in Cats

2021 ◽  
Vol 8 ◽  
Author(s):  
Tommaso Banzato ◽  
Marek Wodzinski ◽  
Federico Tauceri ◽  
Chiara Donà ◽  
Filippo Scavazza ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Pleural Effusion ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Computer Aided Detection ◽  
Radiographic Findings ◽  
Computer Aided ◽  
Operating Characteristic Curve

An artificial intelligence (AI)-based computer-aided detection (CAD) algorithm to detect some of the most common radiographic findings in the feline thorax was developed and tested. The database used for training comprised radiographs acquired at two different institutions. Only correctly exposed and positioned radiographs were included in the database used for training. The presence of several radiographic findings was recorded. Consequenly, the radiographic findings included for training were: no findings, bronchial pattern, pleural effusion, mass, alveolar pattern, pneumothorax, cardiomegaly. Multi-label convolutional neural networks (CNNs) were used to develop the CAD algorithm, and the performance of two different CNN architectures, ResNet 50 and Inception V3, was compared. Both architectures had an area under the receiver operating characteristic curve (AUC) above 0.9 for alveolar pattern, bronchial pattern and pleural effusion, an AUC above 0.8 for no findings and pneumothorax, and an AUC above 0.7 for cardiomegaly. The AUC for mass was low (above 0.5) for both architectures. No significant differences were evident in the diagnostic accuracy of either architecture.

Computer-Aided Detection for Tuberculosis and Silicosis in Chest Radiographs of Southern African Gold Miners

2019 ◽  
Author(s):  
Cheryl Young ◽  
Stephen Barker ◽  
Rodney Ehrlich ◽  
Barry Kistnasamy ◽  
Annalee Yassi
Keyword(s):  
Chest Radiographs ◽  
Computer Aided Detection ◽  
Computer Aided ◽  
Gold Miners

Optimal matrix size of chest radiographs for computer-aided detection on lung nodule or mass with deep learning

2020 ◽  
Vol 30 (9) ◽  
pp. 4943-4951
Author(s):  
Young-Gon Kim ◽  
Sang Min Lee ◽  
Kyung Hee Lee ◽  
Ryoungwoo Jang ◽  
Joon Beom Seo ◽  
...  
Keyword(s):  
Deep Learning ◽  
Lung Nodule ◽  
Chest Radiographs ◽  
Computer Aided Detection ◽  
Matrix Size ◽  
Computer Aided

scholarly journals Sensitivity of Computer-Aided Detection (CAD) Device for Lung Nodule Detection on Chest Radiography: A Real-Life Application

2020 ◽  
pp. 1-5
Author(s):  
Ammar Chaudhry ◽  
Ammar Chaudhry ◽  
William H. Moore
Keyword(s):  
Sensitivity And Specificity ◽  
Chest Radiography ◽  
Predictive Value ◽  
Lung Nodule ◽  
Chest Radiographs ◽  
Lung Nodules ◽  
Computer Aided Detection ◽  
Cad System ◽  
Computer Aided ◽  
The Mean

Purpose: The radiographic diagnosis of lung nodules is associated with low sensitivity and specificity. Computer-aided detection (CAD) system has been shown to have higher accuracy in the detection of lung nodules. The purpose of this study is to assess the effect on sensitivity and specificity when a CAD system is used to review chest radiographs in real-time setting. Methods: Sixty-three patients, including 24 controls, who had chest radiographs and CT within three months were included in this study. Three radiologists were presented chest radiographs without CAD and were asked to mark all lung nodules. Then the radiologists were allowed to see the CAD region-of-interest (ROI) marks and were asked to agree or disagree with the marks. All marks were correlated with CT studies. Results: The mean sensitivity of the three radiologists without CAD was 16.1%, which showed a statistically significant improvement to 22.5% with CAD. The mean specificity of the three radiologists was 52.5% without CAD and decreased to 48.1% with CAD. There was no significant change in the positive predictive value or negative predictive value. Conclusion: The addition of a CAD system to chest radiography interpretation statistically improves the detection of lung nodules without affecting its specificity. Thus suggesting CAD would improve overall detection of lung nodules.

scholarly journals Computer-aided Detection of Lung Cancer on Chest Radiographs: Effect on Observer Performance

Radiology ◽  
2010 ◽  
Vol 257 (2) ◽  
pp. 532-540 ◽  
Author(s):  
Bartjan de Hoop ◽  
Diederik W. De Boo ◽  
Hester A. Gietema ◽  
Frans van Hoorn ◽  
Banafsche Mearadji ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Chest Radiographs ◽  
Observer Performance ◽  
Computer Aided Detection ◽  
Computer Aided

The Utility of Pleural Fluid Lactate Dehydrogenase to Adenosine Deaminase Ratio in Pleural Tuberculosis

Respiration ◽  
2020 ◽  
pp. 1-5
Author(s):  
Amanda Beukes ◽  
Jane Alexandra Shaw ◽  
Andreas H. Diacon ◽  
Elvis M. Irusen ◽  
Coenraad F.N. Koegelenberg
Keyword(s):  
Lactate Dehydrogenase ◽  
Adenosine Deaminase ◽  
Pleural Fluid ◽  
Operating Characteristic ◽  
Retrospective Studies ◽  
Characteristic Curve ◽  
Diagnostic Efficiency ◽  
Pleural Tuberculosis ◽  
High Incidence ◽  
The Mean

In high-burden settings, the diagnosis of pleural tuberculosis (TB) is frequently inferred in patients who present with lymphocyte predominant exudative effusions and high adenosine deaminase (ADA) levels. Two recent small retrospective studies suggested that the lactate dehydrogenase (LDH)/ADA ratio is significantly lower in TB than in non-TB pleural effusions and that the LDH/ADA ratio may be useful in differentiating pleural TB from other pleural exudates. We compared the pleural LDH/ADA ratios, ADA levels, and lymphocyte predominance of a prospectively collected cohort of patients with proven pleural TB (<i>n</i> = 160) to those with a definitive alternative diagnosis (<i>n</i> = 68). The mean pleural fluid LDH/ADA ratio was lower in patients with pleural TB than alternative diagnoses (6.2 vs. 34.3, <i>p</i> &#x3c; 0.001). The area under the receiver operating characteristic curve was 0.92 (<i>p</i> &#x3c; 0.001) for LDH/ADA ratio and 0.88 (<i>p</i> &#x3c; 0.001) for an ADA ≥40 U/L alone. A ratio of ≤12.5 had the best overall diagnostic efficiency, while a ratio of ≤10 had a specificity of 90% and a positive predictive value of 95%, with a sensitivity of 78%, making it a clinically useful “rule in” value for pleural TB in high incidence settings. When comparing the LDH/ADA ratio to an ADA level ≥40 U/L in the presence of a lymphocyte predominant effusion, the latter performed better. When lymphocyte values are unavailable, our data suggest that the LDH/ADA ratio is valuable in distinguishing TB effusions from other pleural exudates.

scholarly journals A Computer-Aided Detection System for Digital Chest Radiographs

2016 ◽  
Vol 2016 ◽  
pp. 1-9 ◽  
Author(s):  
Juan Manuel Carrillo-de-Gea ◽  
Ginés García-Mateos ◽  
José Luis Fernández-Alemán ◽  
José Luis Hernández-Hernández
Keyword(s):  
Template Matching ◽  
Detection System ◽  
Local Binary Patterns ◽  
Chest Radiographs ◽  
Computer Aided Detection ◽  
Success Rates ◽  
Novel Approach ◽  
Computer Aided ◽  
Digital Chest ◽  
Areas Of Interest

Computer-aided detection systems aim at the automatic detection of diseases using different medical imaging modalities. In this paper, a novel approach to detecting normality/pathology in digital chest radiographs is proposed. The problem tackled is complicated since it is not focused on particular diseases but anything that differs from what is considered as normality. First, the areas of interest of the chest are found using template matching on the images. Then, a texture descriptor called local binary patterns (LBP) is computed for those areas. After that, LBP histograms are applied in a classifier algorithm, which produces the final normality/pathology decision. Our experimental results show the feasibility of the proposal, with success rates above 87% in the best cases. Moreover, our technique is able to locate the possible areas of pathology in nonnormal radiographs. Strengths and limitations of the proposed approach are described in the Conclusions.

Lung Cancers Missed on Chest Radiographs: Results Obtained with a Commercial Computer-aided Detection Program

Radiology ◽  
2008 ◽  
Vol 246 (1) ◽  
pp. 273-280 ◽  
Author(s):  
Feng Li ◽  
Roger Engelmann ◽  
Charles E. Metz ◽  
Kunio Doi ◽  
Heber MacMahon
Keyword(s):  
Chest Radiographs ◽  
Computer Aided Detection ◽  
Lung Cancers ◽  
Detection Program ◽  
Computer Aided

scholarly journals A Comparison of Computer-Aided Detection (CAD) Effectiveness in Pulmonary Nodule Identification Using Different Methods of Bone Suppression in Chest Radiographs

2013 ◽  
Vol 26 (4) ◽  
pp. 651-656 ◽  
Author(s):  
Ronald D. Novak ◽  
Nicholas J. Novak ◽  
Robert Gilkeson ◽  
Bahar Mansoori ◽  
Gunhild E. Aandal
Keyword(s):  
Pulmonary Nodule ◽  
Chest Radiographs ◽  
Computer Aided Detection ◽  
Computer Aided
Sign in / Sign up

Export Citation Format

Share Document