COVID-19 infection map generation and detection from chest X-ray images

Degerli, Aysen; Ahishali, Mete; Yamaç, Mehmet; Kıranyaz, Serkan; Chowdhury, Muhammad E. H.; Hameed, Khalid; Hamid, Tahir; Mazhar, Rashid; Gabbouj, Moncef

doi:10.1007/s13755-021-00146-8

Cited by 73 publications

(77 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This consolidation pattern had a variable presentation in terms of density and shape. Smooth homogeneous consolidation was noticed in few patients and most have a peripheral distribution in the form of homogeneous, crescent-shaped or partially nodular opacities [22][23] . The Indeterminate group considered the radiological characteristics of COVID-19, the unique occurrence of tuberculosis, the seasonal occurrence of allergic chest disease, and hypersensitivity pneumonitis in our residents 24 .…”

Section: Discussionmentioning

confidence: 99%

Chest X-Rays Findings in Patients Positive for COVID 19 at Sheikh Zayed Hospital Lahore

Sheikh¹,

Tariq²,

Noor³

et al. 2021

PJMHS

View full text Add to dashboard Cite

Aim: To assess the results of chest x ray radiographs of patients positive for Covid-19, presented at the tertiary care hospital according to the classification by the British Society of Thoracic Imaging (BSTI. Place and Duration: In COVID-19 Ward (Department of Medicine) Sheikh Zayed Hospital, Lahore for three months duration from January 2021 to March 2021. Methods: A total of 96 patients were selected. In this observational study, positive COVID-19 patient determined by the reverse transcriptase polymerase chain reaction (RT-PCR) were enrolled for this study above the age of 14 years. CXR results were classified conferring to BSTI documentation and classification in terms of percentage and frequency. Results: Chest rays of 96 patients who tested positive for Covid-19 by RT-PCR over the age of 14 years were examined. Chest X-rays are classified according to the BSTI Covid-19 X-ray classification. Out of 96 patients, 10 patients (10.41%) had normal chest x-rays, 19 (19.80%) patients had classic bilateral, peripheral and basal consolidation / ground glass opacity (GMO), 60 (62.5%) had unspecified group,7(7.29%) patients have poor quality X-ray film. The unilateral involvement was noticed in 15 and bilateral in 49 patients, 12 of the patients had diffuse involvement on chest radiograph and peripheral involvement in 39 patients. According to regional dominance, 41 of the unspecified (42.70%) had middle and lower lung involvement, 7 (7.29%) had only the middle zone, and 8 (8.33%) had involvement of lower zone. Conclusions: In this study, Covid-19 chest X-rays are usually presented as ground glass opacity, mixed consolidation with GGOs in the middle and lower peripheral areas of the bilateral lung. Chest X-ray BSTI classification is used to classify Covid-19 severity in our patients, thus differentiating in the classic Covid-19 of the middle zone versus low zone involvement. Keywords: Consolidation, Covid, Ground Glass Opacity, Chest Image.

show abstract

Section: Discussionmentioning

confidence: 99%

Chest X-Rays Findings in Patients Positive for COVID 19 at Sheikh Zayed Hospital Lahore

Sheikh¹,

Tariq²,

Noor³

et al. 2021

PJMHS

View full text Add to dashboard Cite

show abstract

“…At the same time, we evaluate the performance of the proposed ULNet model by using different evaluation indicators. In addition, we use an external dataset (QaTa-COV19 Dataset) [ 31 ] to evaluate the model. The model is used for two classifications of normal people and COVID-19 patients, as well as three classifications of normal people, COVID-19 patients and viral pneumonia patients.…”

Section: Methodsmentioning

confidence: 99%

“…The metadata for this dataset can be found at https://www.kaggle.com/tawsifurrahman/covid19-radiography-database/ version/1. Another dataset, the QaTa-COV19 dataset [ 31 ], was compiled by researchers from Qatar University and Tampere University. We randomly selected 300 chest X-ray images (including 100 COVID-19, 100 Normal and 100 Viral Pneumonia) to evaluate our model, and Fig.…”

Section: Methodsmentioning

confidence: 99%

“…We randomly selected 300 chest X-ray images (including 100 COVID-19, 100 Normal and 100 Viral Pneumonia) to evaluate our model, and Fig. 3 shows some images of the QaTa-COV19 Dataset [ 31 ]. It is worth noting that these 300 images from the QaTa-COV19 Dataset [ 31 ] are not included in the COVID-19 Radiography Dataset [ 32 ].…”

Section: Methodsmentioning

confidence: 99%

“…3 shows some images of the QaTa-COV19 Dataset [ 31 ]. It is worth noting that these 300 images from the QaTa-COV19 Dataset [ 31 ] are not included in the COVID-19 Radiography Dataset [ 32 ].

Fig.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

ULNet for the detection of coronavirus (COVID-19) from chest X-ray images

Tang

et al. 2021

Computers in Biology and Medicine

View full text Add to dashboard Cite

Novel coronavirus disease 2019 (COVID-19) is an infectious disease that spreads very rapidly and threatens the health of billions of people worldwide. With the number of cases increasing rapidly, most countries are facing the problem of a shortage of testing kits and resources, and it is necessary to use other diagnostic methods as an alternative to these test kits. In this paper, we propose a convolutional neural network (CNN) model (ULNet) to detect COVID-19 using chest X-ray images. The proposed architecture is constructed by adding a new downsampling side, skip connections and fully connected layers on the basis of U-net. Because the shape of the network is similar to UL, it is named ULNet. This model is trained and tested on a publicly available Kaggle dataset (consisting of a combination of 219 COVID-19, 1314 normal and 1345 viral pneumonia chest X-ray images), including binary classification (COVID-19 vs. Normal) and multiclass classification (COVID-19 vs. Normal vs. Viral Pneumonia). The accuracy of the proposed model in the detection of COVID-19 in the binary-class and multiclass tasks is 99.53% and 95.35%, respectively. Based on these promising results, this method is expected to help doctors diagnose and detect COVID-19. Overall, our ULNet provides a quick method for identifying patients with COVID-19, which is conducive to the control of the COVID-19 pandemic.

show abstract

Hybrid deep neural network for automatic detection of COVID‐19 using chest x‐ray images

Acharya¹,

Ali

Ahmed

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The 2019 coronavirus (COVID‐19), started in China, spreads rapidly around the entire world. In automated medical imagery diagnostic technique, due to presence of noise in medical images and use of single pre‐trained model on low quality images, the existing deep network models cannot provide the optimal results with better accuracy. Hence, hybrid deep learning model of Xception model & Resnet50V2 model is proposed in this paper. This study suggests classifying X‐ray images into three categories namely, normal, bacterial/viral infections and Covid positive. It utilizes CLAHE & BM3D techniques to improve visual clarity and reduce noise. Transfer learning method with variety of pre‐trained models such as ResNet‐50, Inception V3, VGG‐16, VGG‐19, ResNet50V2, and Xception are used for better feature extraction and Chest X‐ray image classification. The overfitting issue were resolved using K‐fold cross validation. The proposed hybrid deep learning model results high accuracy of 97.8% which is better than existing techniques.

show abstract

COVID-19 infection map generation and detection from chest X-ray images

Cited by 73 publications

References 72 publications

Chest X-Rays Findings in Patients Positive for COVID 19 at Sheikh Zayed Hospital Lahore

Chest X-Rays Findings in Patients Positive for COVID 19 at Sheikh Zayed Hospital Lahore

ULNet for the detection of coronavirus (COVID-19) from chest X-ray images

Hybrid deep neural network for automatic detection of COVID‐19 using chest x‐ray images

Contact Info

Product

Resources

About