Intelligent Pneumonia Identification From Chest X-Rays: A Systematic Literature Review

Abstract

Chest radiography is a significant diagnostic tool used to detect diseases afflicting the chest. The automatic detection techniques associated with computer vision are being adopted in medical imaging research. Over the last decade, several remarkable advancements have been made in the field of medical diagnostics with the application of deep learning techniques. Various automated systems have been proposed for the rapid detection of pneumonia from chest X-rays. Although several algorithms are currently available for pneumonia detection, a detailed review summarizing the literature and offering guidelines for medical practitioners is lacking. This study will help practitioners to select the most effective and efficient methods from a real-time perspective, review the available datasets, and understand the results obtained in this domain. It will also present an overview of the literature on intelligent pneumonia identification from chest X-rays. The usability, goodness factors, and computational complexities of the algorithms employed for intelligent pneumonia identification are analyzed. Additionally, this study discusses the quality, usability, and size of the available chest X-ray datasets and techniques for coping with unbalanced datasets. A detailed comparison of the available studies reveals that the majority of the applied datasets are highly unbalanced and limited, providing unreliable results and rendering methods that are unsuitable for large-scale use. Large-scale balanced datasets can be obtained via smart techniques, such as generative adversarial networks. Current literature has indicated that deep learning-based algorithms achieve the best results for pneumonia classification with an accuracy of 98.7%, a sensitivity of 0.99, and a specificity of 0.98. The higher accuracy offered by deep-learning algorithms in addition to their appropriate class balancing techniques serves as a good reference for further research.

Deep Learning for Predicting Cognitive Gap as a Reliable Biomarker of Dementia

“…We developed a DL model to predict the cognitive gap. Over the past decade, DL techniques have shown an enormous breakthrough in the field of medical diagnostics by achieving excellent performance in automatic medical imaging classification, detection, and segmentation [25].…”

Automatic Diagnosis of Pneumothorax From Chest Radiographs: A Systematic Literature Review

“…Mostly the chest radiographs are acquired in DICOM format, which not only contains the X-ray image of the chest but also contains meta-data like patient's name, age, gender etc. [10]. This DICOM format is not only incomprehensible (except for radiologists), but also many machine learning algorithms are programmed to take the input image in other formats like JPEG or PNG.…”

“…In the medical field, CAD systems have been used for several purposes including arrhythmia detection [7], classification of skin cancer [8] and diabetic retinopathy identification [9]. Any CAD system comprises of four main steps [10]. (1) Preprocessing of the data (2) extraction of region of interest.…”

“…A systematic literature review is important as it summarizes and analyzes the existing literature on relevant topic along with highlighting the limitations and shortcomings of existing research. Such literature reviews are available for pneumonia, TB and multiple thoracic diseases [4], [10], [13], however, regardless of the fact that lot of research has been done for automatic diagnosis of pneumothorax, a brief overview of the existing work for pneumothorax is not available so far. Thus, there is a need to explore and summarize the available literature.…”

Prediction Model for Coronavirus Pandemic Using Deep Learning

“…Similarly, a DL-based image analytics solution can be used to fight different forms of pneumonia. Further, the Vaccination process can also be accelerated using DL and AI techniques [13,14].…”