Application with deep learning models for COVID-19 diagnosis

Turk, F. J.; KÖKVER, Yunus

doi:10.35377/saucis...1085625

Cited by 5 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of images in each class included in the dataset is shown in Table 1 . The created dataset has been made publicly available for the knowledge of researchers [ 29 ]. More detailed descriptions of the dataset and a link to the dataset can be found at: https://github.com/turkfuat/covid19-pneumonia-dataset .…”

Section: Methodsmentioning

confidence: 99%

Detection of Lung Opacity and Treatment Planning with Three-Channel Fusion CNN Model

Turk

Kökver

2023

Arab J Sci Eng

View full text Add to dashboard Cite

Lung opacities are extremely important for physicians to monitor and can have irreversible consequences for patients if misdiagnosed or confused with other findings. Therefore, long-term monitoring of the regions of lung opacity is recommended by physicians. Tracking the regional dimensions of images and classifying differences from other lung cases can provide significant ease to physicians. Deep learning methods can be easily used for the detection, classification, and segmentation of lung opacity. In this study, a three-channel fusion CNN model is applied to effectively detect lung opacity on a balanced dataset compiled from public datasets. The MobileNetV2 architecture is used in the first channel, the InceptionV3 model in the second channel, and the VGG19 architecture in the third channel. The ResNet architecture is used for feature transfer from the previous layer to the current layer. In addition to being easy to implement, the proposed approach can also provide significant cost and time advantages to physicians. Our accuracy values for two, three, four, and five classes on the newly compiled dataset for lung opacity classifications are found to be 92.52%, 92.44%, 87.12%, and 91.71%, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Detection of Lung Opacity and Treatment Planning with Three-Channel Fusion CNN Model

Turk

Kökver

2023

Arab J Sci Eng

View full text Add to dashboard Cite

show abstract

“…Accuracy, recall, precision, F1-score, the Dice coefficient, and the Jaccard Index are used to evaluate the efficiency of the newly proposed RNGU-NET model ( Turk & Kökver, 2022 ). The rest of this section presents the formulae and working principles of these calculations.…”

Section: Rngu-netmentioning

confidence: 99%

RNGU-NET: a novel efficient approach in Segmenting Tuberculosis using chest X-Ray images

Turk

2024

PeerJ Computer Science

View full text Add to dashboard Cite

Tuberculosis affects various tissues, including the lungs, kidneys, and brain. According to the medical report published by the World Health Organization (WHO) in 2020, approximately ten million people have been infected with tuberculosis. U-NET, a preferred method for detecting tuberculosis-like cases, is a convolutional neural network developed for segmentation in biomedical image processing. The proposed RNGU-NET architecture is a new segmentation technique combining the ResNet, Non-Local Block, and Gate Attention Block architectures. In the RNGU-NET design, the encoder phase is strengthened with ResNet, and the decoder phase incorporates the Gate Attention Block. The key innovation lies in the proposed Local Non-Local Block architecture, overcoming the bottleneck issue in U-Net models. In this study, the effectiveness of the proposed model in tuberculosis segmentation is compared to the U-NET, U-NET+ResNet, and RNGU-NET algorithms using the Shenzhen dataset. According to the results, the RNGU-NET architecture achieves the highest accuracy rate of 98.56%, Dice coefficient of 97.21%, and Jaccard index of 96.87% in tuberculosis segmentation. Conversely, the U-NET model exhibits the lowest accuracy and Jaccard index scores, while U-NET+ResNet has the poorest Dice coefficient. These findings underscore the success of the proposed RNGU-NET method in tuberculosis segmentation.

show abstract

“…The F1 Score value shows the harmonic mean of the Precision and Recall values. True Positive and True Negative are areas that the model predicts correctly, while False Positive and False Negative are areas that the model predicts incorrectly [13,28].…”

Section: Performance Evaluation Criteriamentioning

confidence: 99%

“…Classification processes are carried out successfully in agriculture with artificial intelligence models. Classical CNN models from artificial intelligence models, architectures such as DenseNet, NasNet Mobile, VGG16, VGG19 are widely used in classification problems [13,14]. In the literature, applications such as the recognition of plant diseases [15], classification and grading of fruits [16,17], classification of flowers [18], classification of hazelnut varieties [19], classification of green coffee beans [20], classification of cherry varieties [21], classification of lemons [22], weed detection in wheat fields [23], image-based quality analysis of strawberries [24], detection of impurities in wheat [25] and image-based wheat grain classification using CNN [26] have been carried out successfully.…”

mentioning

confidence: 99%

U2-Net Segmentation and Multi-Label CNN Classification of Wheat Varieties

Argun,

Türk,

Civelek

2024

KONJES

Self Cite

View full text Add to dashboard Cite

There are many varieties of wheat grown around the world. In addition, they have different physiological states such as vitreous and yellow berry. These reasons make it difficult to classify wheat by experts. In this study, a workflow was carried out for both segmentation of wheat according to its vitreous/yellow berry grain status and classification according to variety. Unlike previous studies, automatic segmentation of wheat images was carried out with the U2-NET architecture. Thus, roughness and shadows on the image are minimized. This increased the level of success in classification. The newly proposed CNN architecture is run in two stages. In the first stage, wheat was sorted as vitreous-yellow berry. In the second stage, these separated wheats were grouped by multi-label classification. Experimental results showed that the accuracy for binary classification was 98.71% and the multi-label classification average accuracy was 89.5%. The results showed that the proposed study has the potential to contribute to making the wheat classification process more reliable, effective, and objective by helping the experts.

show abstract

Application with deep learning models for COVID-19 diagnosis

Cited by 5 publications

References 21 publications

Detection of Lung Opacity and Treatment Planning with Three-Channel Fusion CNN Model

Detection of Lung Opacity and Treatment Planning with Three-Channel Fusion CNN Model

RNGU-NET: a novel efficient approach in Segmenting Tuberculosis using chest X-Ray images

U2-Net Segmentation and Multi-Label CNN Classification of Wheat Varieties

Contact Info

Product

Resources

About