COVIDScreen: Explainable deep learning framework for differential diagnosis of COVID-19 using chest X-Rays

Singh, Rajeev Kumar; Pandey, Rohan; Babu, Rishie Nandhan

doi:10.21203/rs.3.rs-61891/v1

Cited by 16 publications

(22 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, all images used in this study required contrast correction through the histogram equalization technique and resizing to a uniform size before the experiment. In this study, preprocessing was performed using the contrast limited adaptive histogram equalization (CLAHE) technique [ 25 ], which has been adopted in previous studies related to lung segmentation and pneumonia classification [ 26 , 27 , 28 ]. Figure 2 shows sample images with CXR contrast corrected using the CLAHE technique.…”

Section: Methodsmentioning

confidence: 99%

Evaluation of Scalability and Degree of Fine-Tuning of Deep Convolutional Neural Networks for COVID-19 Screening on Chest X-ray Images Using Explainable Deep-Learning Algorithm

Lee

Kim

Jeon

et al. 2020

JPM

View full text Add to dashboard Cite

According to recent studies, patients with COVID-19 have different feature characteristics on chest X-ray (CXR) than those with other lung diseases. This study aimed at evaluating the layer depths and degree of fine-tuning on transfer learning with a deep convolutional neural network (CNN)-based COVID-19 screening in CXR to identify efficient transfer learning strategies. The CXR images used in this study were collected from publicly available repositories, and the collected images were classified into three classes: COVID-19, pneumonia, and normal. To evaluate the effect of layer depths of the same CNN architecture, CNNs called VGG-16 and VGG-19 were used as backbone networks. Then, each backbone network was trained with different degrees of fine-tuning and comparatively evaluated. The experimental results showed the highest AUC value to be 0.950 concerning COVID-19 classification in the experimental group of a fine-tuned with only 2/5 blocks of the VGG16 backbone network. In conclusion, in the classification of medical images with a limited number of data, a deeper layer depth may not guarantee better results. In addition, even if the same pre-trained CNN architecture is used, an appropriate degree of fine-tuning can help to build an efficient deep learning model.

show abstract

Section: Methodsmentioning

confidence: 99%

Evaluation of Scalability and Degree of Fine-Tuning of Deep Convolutional Neural Networks for COVID-19 Screening on Chest X-ray Images Using Explainable Deep-Learning Algorithm

Lee

Kim

Jeon

et al. 2020

JPM

View full text Add to dashboard Cite

show abstract

“…Finally, Singh, Pandey [ 75 ] suggested a DL-based approach that uses chest X-rays to assist COVID-19 patient triaging. They tested several GAN architectures and their ability to produce practical synthetic COVID-19 chest X-rays to deal with small numbers of training samples.…”

Section: Covid-19 Detection Mechanismsmentioning

confidence: 99%

“… No COVID-19 X-Ray datasets from three separate sources. No GNN Detection in chest X-ray Singh, Pandey [ 75 ] Proposing a GAN-based approach to assist in the quicker triage of COVID-19 patients, thus reducing the risk of human error. −98.67% accuracy, 0.98 Kappa score, and F-1 scores of 100, 98, and 98, respectively.…”

Section: Covid-19 Detection Mechanismsmentioning

confidence: 99%

The COVID-19 epidemic analysis and diagnosis using deep learning: A systematic literature review and future directions

Heidari¹,

Navimipour²,

Ünal³

et al. 2022

Computers in Biology and Medicine

View full text Add to dashboard Cite

Since December 2019, the COVID-19 outbreak has resulted in countless deaths and has harmed all facets of human existence. COVID-19 has been designated an epidemic by the World Health Organization (WHO), which has placed a tremendous burden on nearly all countries, especially those with weak health systems. However, Deep Learning (DL) has been applied in several applications and many types of detection applications in the medical field, including thyroid diagnosis, lung nodule recognition, fetal localization, and detection of diabetic retinopathy. Furthermore, various clinical imaging sources, like Magnetic Resonance Imaging (MRI), X-ray, and Computed Tomography (CT), make DL a perfect technique to tackle the epidemic of COVID-19. Inspired by this fact, a considerable amount of research has been done. A Systematic Literature Review (SLR) has been used in this study to discover, assess, and integrate findings from relevant studies. DL techniques used in COVID-19 have also been categorized into seven main distinct categories as Long Short Term Memory Networks (LSTM), Self-Organizing Maps (SOMs), Conventional Neural Networks (CNNs), Generative Adversarial Networks (GANs), Recurrent Neural Networks (RNNs), Autoencoders, and hybrid approaches. Then, the state-of-the-art studies connected to DL techniques and applications for health problems with COVID-19 have been highlighted. Moreover, many issues and problems associated with DL implementation for COVID-19 have been addressed, which are anticipated to stimulate more investigations to control the prevalence and disaster control in the future. According to the findings, most papers are assessed using characteristics such as accuracy, delay, robustness, and scalability. Meanwhile, other features are underutilized, such as security and convergence time. Python is also the most commonly used language in papers, accounting for 75% of the time. According to the investigation, 37.83% of applications have identified chest CT/chest X-ray images for patients.

show abstract

“…Deep learning, a common field of artificial intelligence (AI), allows the creation of models end-to-end in order without requiring manual feature extraction to produce predicted results using input data. Several approaches have been proposed a deep learning methods for the identification of COVID-19 events such as CNN [ 29 – 31 ], COVIDScreen [ 32 ], and COVINet [ 32 ]. These approaches were used an efficient and robust X-ray and CT scan imaging solutions.…”

Section: Related Workmentioning

confidence: 99%

SOM-LWL method for identification of COVID-19 on chest X-rays

et al. 2021

View full text Add to dashboard Cite

The outbreak of coronavirus disease 2019 (COVID-19) has had an immense impact on world health and daily life in many countries. Sturdy observing of the initial site of infection in patients is crucial to gain control in the struggle with COVID-19. The early automated detection of the recent coronavirus disease (COVID-19) will help to limit its dissemination worldwide. Many initial studies have focused on the identification of the genetic material of coronavirus and have a poor detection rate for long-term surgery. The first imaging procedure that played an important role in COVID-19 treatment was the chest X-ray. Radiological imaging is often used as a method that emphasizes the performance of chest X-rays. Recent findings indicate the presence of COVID-19 in patients with irregular findings on chest X-rays. There are many reports on this topic that include machine learning strategies for the identification of COVID-19 using chest X-rays. Other current studies have used non-public datasets and complex artificial intelligence (AI) systems. In our research, we suggested a new COVID-19 identification technique based on the locality-weighted learning and self-organization map (LWL-SOM) strategy for detecting and capturing COVID-19 cases. We first grouped images from chest X-ray datasets based on their similar features in different clusters using the SOM strategy in order to discriminate between the COVID-19 and non-COVID-19 cases. Then, we built our intelligent learning model based on the LWL algorithm to diagnose and detect COVID-19 cases. The proposed SOM-LWL model improved the correlation coefficient performance results between the Covid19, no-finding, and pneumonia cases; pneumonia and no-finding cases; Covid19 and pneumonia cases; and Covid19 and no-finding cases from 0.9613 to 0.9788, 0.6113 to 1 0.8783 to 0.9999, and 0.8894 to 1, respectively. The proposed LWL-SOM had better results for discriminating COVID-19 and non-COVID-19 patients than the current machine learning-based solutions using AI evaluation measures.

show abstract

COVIDScreen: Explainable deep learning framework for differential diagnosis of COVID-19 using chest X-Rays

Cited by 16 publications

References 56 publications

Evaluation of Scalability and Degree of Fine-Tuning of Deep Convolutional Neural Networks for COVID-19 Screening on Chest X-ray Images Using Explainable Deep-Learning Algorithm

Evaluation of Scalability and Degree of Fine-Tuning of Deep Convolutional Neural Networks for COVID-19 Screening on Chest X-ray Images Using Explainable Deep-Learning Algorithm

The COVID-19 epidemic analysis and diagnosis using deep learning: A systematic literature review and future directions

SOM-LWL method for identification of COVID-19 on chest X-rays

Contact Info

Product

Resources

About