Advancement of deep learning in pneumonia/Covid‐19 classification and localization: A systematic review with qualitative and quantitative analysis

Abstract

Around 450 million people are affected by pneumonia every year, which results in 2.5 million deaths. Coronavirus disease 2019 (Covid‐19) has also affected 181 million people, which led to 3.92 million casualties. The chances of death in both of these diseases can be significantly reduced if they are diagnosed early. However, the current methods of diagnosing pneumonia (complaints + chest X‐ray) and Covid‐19 (real‐time polymerase chain reaction) require the presence of expert radiologists and time, respectively. With the help of deep learning models, pneumonia and Covid‐19 can be detected instantly from chest X‐rays or computerized tomography (CT) scans. The process of diagnosing pneumonia/Covid‐19 can become faster and more widespread. In this paper, we aimed to elicit, explain, and evaluate qualitatively and quantitatively all advancements in deep learning methods aimed at detecting community‐acquired pneumonia, viral pneumonia, and Covid‐19 from images of chest X‐rays and CT scans. Being a systematic review, the focus of this paper lies in explaining various deep learning model architectures, which have either been modified or created from scratch for the task at hand. For each model, this paper answers the question of why the model is designed the way it is, the challenges that a particular model overcomes, and the tradeoffs that come with modifying a model to the required specifications. A grouped quantitative analysis of all models described in the paper is also provided to quantify the effectiveness of different models with a similar goal. Some tradeoffs cannot be quantified and, hence, they are mentioned explicitly in the qualitative analysis, which is done throughout the paper. By compiling and analyzing a large quantum of research details in one place with all the data sets, model architectures, and results, we aimed to provide a one‐stop solution to beginners and current researchers interested in this field.

Artificial intelligence and feature based transfer learning framework for diagnosis of chest diseases using radiology images

“…With a 93.9% success rate, the suggested model has a noteworthy degree of accuracy. Rajpurkar et al [22] made use of a dataset made up of x-ray images from 30 805 individuals. The images were normalized and scaled to 224x224 dimensions with different metrics.…”

Detection of Pneumonia from Chest X-ray Images Utilizing MobileNet Model

“…The classes pneumonia and non-pneumonia (14 classes including other lung disorders) were quite unbalanced because the NIH dataset has 15 classes. When tested with 420 photos, the model finished with an F1-score of 0.435 and an AUROC of 0.76 [12]. Pak KinWonga et al recognized that COVID-19 pneumonia, non-COVID-19 viral pneumonia, bacterial pneumonia, mycoplasma pneumonia, and typical lung on chest CT images play a pivotal part in opportune isolation and restorative treatment.…”

An Ensemble Novel Deep Learning Technique for Chest Radiograph-Based Pneumonia Prediction

“…Advanced convolutional along with attention processes were added to YOLOv3 by Yao et al [16], improving its capacity to discriminate lung abnormalities. A model depending VGG19 structure was introduced by Dey et al [17]. GeminiNet, which combines fully convolutional networks with susceptible region structures to obtain good performance in the diagnosis of pneumonia, was also introduced by Yao et al [16].…”

“…By including a further outcome for compact targets, produced outstanding results in pneumonia identification. Collectively, these studies highlight the difficulties in using CXR to diagnose pneumonia [17], with newer research frequently highlighting the creation of model ensembles and network topologies. This study draws its main focuses on two main areas: the feature extraction network and a novel technique for suppressing overlapping detection bounding boxes.…”