Abstract
Featured Application: The method presented in this paper can be applied in medical computer systems for supporting medical diagnosis.Abstract: Thoracic radiography (chest X-ray) is an inexpensive but effective and widely used medical imaging procedure. However, a lack of qualified radiologists severely limits the applicability of the technique. Even current Deep Learning-based approaches often require strong supervision, e.g., annotated bounding boxes, to train such systems, which is impossible to harvest on a large scale. In this work, we proposed the classification and prediction of lung pathologies of frontal thoracic X-rays using a modified model MobileNet V2. We considered using transfer learning with metadata leverage. We used the NIH Chest-Xray-14 database, and we did a comparison of performance of our approach to other state-of-the-art methods for pathology classification. The main comparison was by Area under the Receiver Operating Characteristic Curve (AUC) statistics and analyzed the differences between classifiers. Overall, we notice a considerable spread in the achieved result with an average AUC of 0.811 and an accuracy above 90%. We conclude that resampling the dataset gives a huge improvement to the model performance. In this work, we intended to create a model that is capable of being trained, and modified devices with low computing power because they can be implemented into smaller IoT devices.
Highlights
Different types of lung disease have affected many people around the world
Some lung diseases, such as emphysema, asthma, pleural effusion, tuberculosis, and other diseases including aspiration fibrosis, pneumonia, and lung malignancies, lead to loss of versatility in the lungs, which causes a decrease in the total volume of air [1]
To detect and diagnose lung diseases, radiologists mainly deal with chest X-rays
Summary
Different types of lung disease have affected many people around the world. Lung diseases make the lungs more prone to certain physical problems and air pollution. To improve workflow priority and clinical decision support in large-scale projections and global population health programs, computer systems must be used to interpret chest radiographs as effectively as radiologists This could play an important role in many clinical environments. Dey et al [18] developed a new method to detect pneumonia by computing the handcrafted features from the chest X-ray with the use of a modified VGGNet (Visual Geometry Group Network) [19]. This method achieved a 97.94% classification accuracy (Check Table 1).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
