Back

Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks

Ali NarinCeren KayaZiynet Pamuk

article2020Pattern Analysis and Applications1,868 citations

Establishes a highly accurate automated COVID-19 screening approach by evaluating five pre-trained convolutional neural network architectures on chest X-rays, identifying ResNet50 as the top performer with up to 99.7% accuracy in differentiating coronavirus from other forms of pneumonia.

Listen

During the COVID-19 pandemic, rapid surge demand for diagnostics combined with severe shortages of test kits and specialist physicians created major operational bottlenecks in healthcare systems. While chest X-rays provide an accessible, fast, and low-radiation imaging method for evaluating pneumonia, accurate manual interpretation requires specialized radiologist expertise that is globally scarce. This shortage increases radiologist fatigue, raising the risk of diagnostic errors and delayed isolation of contagious patients.

The article evaluates whether pre-trained deep learning models can automatically, accurately, and rapidly identify COVID-19 from chest X-ray images, differentiating it from healthy lungs as well as bacterial and other viral pneumonia cases.

The researchers assessed five pre-trained deep convolutional neural network architectures: ResNet50, ResNet101, ResNet152, InceptionV3, and Inception-ResNetV2. Using transfer learning to compensate for limited medical data, the models were trained end-to-end on public image datasets without manual feature extraction. The analysis evaluated 341 COVID-19 cases against 2,800 healthy scans, 1,493 viral pneumonia scans, and 2,772 bacterial pneumonia scans across three binary classification tasks using a five-fold cross-validation approach.

The ResNet50 architecture consistently demonstrated the strongest and most reliable performance among all tested models across every diagnostic scenario. Specifically, ResNet50 achieved 96.1% overall accuracy and 91.8% recall when distinguishing COVID-19 from normal healthy scans. For differentiating COVID-19 from viral pneumonia, ResNet50 attained 99.5% accuracy, 99.4% recall, and 98.0% precision. When distinguishing COVID-19 from bacterial pneumonia, it achieved 99.7% accuracy, 98.8% recall, and 98.3% precision. While InceptionV3 captured 100% of COVID-19 cases in bacterial pneumonia comparisons, it generated more false positives, yielding a lower precision of 82.4% compared to ResNet50's 98.3%.

These findings show that automated deep learning systems can provide high-accuracy clinical decision support to radiologists. Implementing such tools can reduce specialist workload, mitigate fatigue-driven diagnostic errors, accelerate patient triaging, and improve isolation and quarantine response times during public health emergencies. Furthermore, the ability to clearly distinguish COVID-19 from other types of pneumonia provides critical diagnostic precision for clinical intervention.

Decision-makers considering artificial intelligence support tools should prioritize architectures like ResNet50 for pilot evaluations due to their superior stability, high precision, and low false-alarm rates. To move toward robust clinical deployment, future initiatives should test these models across multi-center hospital datasets, combine X-ray and computed tomography data, and incorporate patient demographic factors into diagnostic workflows.

The primary limitation of this study is the relatively small sample size of 341 COVID-19 images drawn from open-source repositories, along with testing restricted to binary rather than simultaneous multi-class scenarios. While confidence in the comparative ranking and high baseline capability of the models is strong, stakeholders should exercise caution and validate performance against larger, diverse multi-site real-world populations before clinical adoption.

Zonguldak Bülent Ecevit Universitybinary classificationconvolutional neural networkscorrelation analysisdeep convolutional neural networksautomatic detectioncoronavirus disease
arXiv: 2003.10849
Cover for Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks

Abstract

The 2019 novel coronavirus disease (COVID-19), with a starting point in China, has spread rapidly among people living in other countries, and is approaching approximately 34,986,502 cases worldwide according to the statistics of European Centre for Disease Prevention and Control. There are a limited number of COVID-19 test kits available in hospitals due to the increasing cases daily. Therefore, it is necessary to implement an automatic detection system as a quick alternative diagnosis option to prevent COVID-19 spreading among people. In this study, five pre-trained convolutional neural network based models (ResNet50, ResNet101, ResNet152, InceptionV3 and Inception-ResNetV2) have been proposed for the detection of coronavirus pneumonia infected patient using chest X-ray radiographs. We have implemented three different binary classifications with four classes (COVID-19, normal (healthy), viral pneumonia and bacterial pneumonia) by using 5-fold cross validation. Considering the performance results obtained, it has seen that the pre-trained ResNet50 model provides the highest classification performance (96.1% accuracy for Dataset-1, 99.5% accuracy for Dataset-2 and 99.7% accuracy for Dataset-3) among other four used models.

Topics

binary classificationconvolutional neural networkscorrelation analysiscross validationvalidationdetection algorithmdeep learningclassification modelshigh resolution imagenetwork architecture

Keywords

deep convolutional neural networksautomatic detectioncoronavirus diseasetransfer learningpre-trained ResNet50ImageNet dataset

Table of Contents

  • 1 Introduction
  • 2 Related works
  • 3 Materials and methods
  • 3.1 Dataset
  • 3.2 Architecture of deep transfer learning
  • 3.2.1 Convolutional layer
  • 3.2.2 Pooling layer
  • 3.2.3 Fully connected layer
  • 3.2.4 Pre-trained models
  • 3.3 Experimental setup
  • 3.4 Performance metrics
  • 4 Experimental results
  • 5 Discussion
  • 6 Conclusion
  • Declaration
  • References

Knowls

  1. Knowl 1 — Deep Transfer Learning Architecture for Chest X-Ray Binary Diagnosis

    model/method

    The diagnostic method employs pre-trained convolutional neural network (CNN) architectures—specifically ResNet50, ResNet101, ResNet152, InceptionV3, and Inception-ResNetV2—initialized with ImageNet weights to classify chest X-ray radiographs into binary classes.

    The feature extraction base is connected to a Global Average Pooling 2D layer that collapses spatial feature maps into a single dimension. This is followed by a fully connected dense layer with 1024 hidden units activated by the Rectified Linear Unit (ReLU) function:

    ReLU(x)={0if x<0xif x≥0\text{ReLU}(x) = \begin{cases} 0 & \text{if } x < 0 \\ x & \text{if } x \ge 0 \end{cases}

    The network terminates with a 2-unit fully connected layer using the Softmax activation function to generate class probability distributions:

    Softmax(xi)=exi∑y=1mexy\text{Softmax}(x_i) = \frac{e^{x_i}}{\sum_{y=1}^{m} e^{x_y}}

    where m=2m = 2 represents the number of output target classes. The entire framework operates end-to-end directly on raw image matrices without manual feature extraction or selection.

  2. Knowl 2 — Chest X-Ray Binary Classification Datasets and Preprocessing

    experimental setup

    Three distinct binary classification datasets were constructed from open-source chest X-ray repositories to evaluate automated COVID-19 detection:

    1. Dataset-1 (COVID-19 vs. Normal): 341 COVID-19 X-ray images (obtained from the Dr. Joseph Cohen open-source repository) and 2800 normal (healthy) X-ray images (selected from the ChestX-ray8 database).
    2. Dataset-2 (COVID-19 vs. Viral Pneumonia): 341 COVID-19 X-ray images and 1493 viral pneumonia X-ray images (selected from the Kaggle Chest X-Ray Images Pneumonia repository).
    3. Dataset-3 (COVID-19 vs. Bacterial Pneumonia): 341 COVID-19 X-ray images and 2772 bacterial pneumonia X-ray images (selected from the Kaggle Chest X-Ray Images Pneumonia repository).

    All chest X-ray radiographs were resized to 224×224224 \times 224 pixels and normalized with a scaling factor of 1/2551/255. Data augmentation applied during training included random horizontal flipping, a shear range of 0.10.1, and a zoom range of 0.10.1.

  3. Knowl 3 — Training Configuration and Hyperparameter Setup

    experimental setup

    Deep transfer learning models were trained on Google Colaboratory Linux servers (Ubuntu 16.04) using GPU/TPU/CPU hardware.

    Evaluation was conducted using 5-fold cross-validation, where each dataset was randomly split into 80% training data and 20% testing data across 5 distinct iterations so that every sample was evaluated once as test data.

    The training hyperparameters applied across all model architectures and datasets were:

    • Optimizer: Adaptive Moment Estimation (ADAM) with parameters β1=0.9\beta_1 = 0.9 and β2=0.999\beta_2 = 0.999.
    • Loss Function: Categorical cross-entropy.
    • Batch Size: 3.
    • Learning Rate: 1×10−51 \times 10^{-5}.
    • Epochs: 30 epochs per fold.

  4. Knowl 4 — Classification Performance on COVID-19 vs. Normal Radiographs

    data/table

    In 5-fold cross-validation on Dataset-1 (341 COVID-19 vs. 2800 Normal images), ResNet50 and ResNet101 both yielded the highest overall accuracy of 96.1%. ResNet50 demonstrated superior COVID-19 sensitivity, achieving a recall of 91.8% and an F1-score of 83.5%, compared to 78.3% recall and 81.2% F1-score for ResNet101.

    The aggregate 5-fold confusion matrix totals and performance metrics across the tested architectures are:

    Model TP TN FP FN Accuracy (%) Recall (%) Specificity (%) Precision (%) F1-score (%)
    InceptionV3 309 2688 112 32 95.4 90.6 96.0 73.4 81.1
    ResNet50 313 2704 96 28 96.1 91.8 96.6 76.5 83.5
    ResNet101 267 2750 50 74 96.1 78.3 98.2 84.2 81.2
    ResNet152 223 2725 75 118 93.9 65.4 97.3 74.8 69.8
    Inception-ResNetV2 268 2672 128 53 94.2 83.5 95.4 67.7 74.8

    TP denotes COVID-19 cases correctly identified as COVID-19; TN denotes normal cases correctly identified as normal; FP denotes normal cases misclassified as COVID-19; FN denotes COVID-19 cases misclassified as normal.

  5. Knowl 5 — Classification Performance on COVID-19 vs. Viral Pneumonia Radiographs

    data/table

    For differentiating COVID-19 from viral pneumonia on Dataset-2 (341 COVID-19 vs. 1493 Viral Pneumonia images) under 5-fold cross-validation, ResNet50 achieved the best overall performance with 99.5% accuracy, 99.4% recall, 99.5% specificity, 98.0% precision, and a 98.7% F1-score.

    The aggregated 5-fold confusion matrix totals and performance metrics are:

    Model TP TN FP FN Accuracy (%) Recall (%) Specificity (%) Precision (%) F1-score (%)
    InceptionV3 340 1468 25 1 98.6 99.7 98.3 93.2 96.3
    ResNet50 339 1486 7 2 99.5 99.4 99.5 98.0 98.7
    ResNet101 301 1479 14 40 97.1 88.3 99.1 95.6 91.8
    ResNet152 310 1479 14 31 97.5 90.9 99.1 95.7 93.2
    Inception-ResNetV2 314 1417 76 27 94.4 92.1 94.9 80.5 85.9

    TP indicates COVID-19 correctly classified as COVID-19; TN indicates viral pneumonia correctly classified as viral pneumonia; FP indicates viral pneumonia misclassified as COVID-19; FN indicates COVID-19 misclassified as viral pneumonia.

  6. Knowl 6 — Classification Performance on COVID-19 vs. Bacterial Pneumonia Radiographs

    data/table

    In the pairwise classification of COVID-19 versus bacterial pneumonia on Dataset-3 (341 COVID-19 vs. 2772 Bacterial Pneumonia images) across 5 folds, ResNet50 attained the highest accuracy of 99.7%, with 98.8% recall, 99.8% specificity, 98.3% precision, and an F1-score of 98.5%. InceptionV3 achieved 100.0% recall (identifying all 341 COVID-19 cases without false negatives) with an accuracy of 97.7%.

    The aggregate 5-fold results are:

    Model TP TN FP FN Accuracy (%) Recall (%) Specificity (%) Precision (%) F1-score (%)
    InceptionV3 341 2699 73 0 97.7 100.0 97.4 82.4 90.3
    ResNet50 337 2766 6 4 99.7 98.8 99.8 98.3 98.5
    ResNet101 179 2770 2 162 94.7 52.5 99.9 98.9 68.6
    ResNet152 174 2716 56 167 92.8 51.0 98.0 75.7 60.9
    Inception-ResNetV2 241 2726 46 100 95.3 70.7 98.3 84.0 76.8

    TP denotes COVID-19 correctly identified as COVID-19; TN denotes bacterial pneumonia correctly identified as bacterial pneumonia; FP denotes bacterial pneumonia misclassified as COVID-19; FN denotes COVID-19 misclassified as bacterial pneumonia.

  7. Knowl 7 — Computational Training Time Across Pre-trained CNN Models

    empirical result

    The cumulative training time across all 5 folds (30 epochs per fold with batch size 3) varied substantially across network architectures on the three datasets:

    • Dataset-1 (COVID-19 vs. Normal):

      • ResNet50: 14,638 s
      • InceptionV3: 16,027 s
      • ResNet101: 17,841 s
      • ResNet152: 18,802 s
      • Inception-ResNetV2: 23,078 s

    • Dataset-2 (COVID-19 vs. Viral Pneumonia):

      • ResNet50: 9,948 s
      • InceptionV3: 12,241 s
      • ResNet101: 13,089 s
      • ResNet152: 14,923 s
      • Inception-ResNetV2: 19,336 s

    • Dataset-3 (COVID-19 vs. Bacterial Pneumonia):

      • ResNet50: 14,386 s
      • InceptionV3: 15,801 s
      • ResNet101: 17,658 s
      • ResNet152: 18,581 s
      • Inception-ResNetV2: 22,865 s

    Across all experiments, ResNet50 consistently achieved the shortest training duration, while Inception-ResNetV2 required the longest training duration.

  8. Knowl 8 — Limitations of Cohort Size and Binary Classification Design

    limitation

    The study highlights three primary limitations:

    1. Limited COVID-19 Cohort Size: The positive dataset is constrained to 341 COVID-19 chest X-ray radiographs, which restricts pathological diversity relative to the larger normal and pneumonia control sets.
    2. Decomposed Binary Setup: The system evaluates three independent pairwise binary classifications rather than an integrated single multi-class model distinguishing all four conditions simultaneously.
    3. Single-Source Sampling: Positive cases were compiled from a public online repository without multi-center clinical validation, requiring broader multi-center validation to ensure clinical robustness and avoid center-specific distribution shifts.

Coverage note — Standard textbook background equations for basic 2D convolution and standard descriptions of off-the-shelf ImageNet architectures were omitted as non-contributed background material.

References

  1. 1.Roosa K, Lee Y, Luo R, Kirpich A, Rothenberg R, Hyman JM et al (2020) Real-time forecasts of the COVID-19 epidemic in China from February 5th to February 24th, 2020. Infect Dis Model 5:256–263
  2. 2.Yan L, Zhang H-T, Xiao Y, Wang M, Sun C, Liang J et al (2020) Prediction of criticality in patients with severe COVID-19 infection using three clinical features: a machine learning-based prognostic model with clinical data in Wuhan. medRxiv 2020.02.27.20028027
  3. 3.Stoecklin SB, Rolland P, Silue Y, Mailles A, Campese C, Simon-don A et al (2020) First cases of coronavirus disease 2019 (COVID-19) in France: surveillance, investigations and control measures, January 2020. Eurosurveillance 25(6):2000094
  4. 4.Coronavirus (2020) World Health Organization. https://www.who.int/health-topics/coronavirus
  5. 5.McKeever A (2020) Here’s what coronavirus does to the body. National geographic. https://www.nationalgeographic.com/science/2020/02/here-is-what-coronavirus-does-to-the-body/
  6. 6.COVID-19 Coronavirus Pandemic (2020) Worldometer. https://www.worldometers.info/coronavirus/
  7. 7.Jaiswal AK, Tiwari P, Kumar S, Gupta D, Khanna A, Rodrigues JJ (2019) Identifying pneumonia in chest X-rays: a deep learning approach. Measurement 145:511–518
  8. 8.Antin B, Kravitz J, Martayan E (2017) Detecting pneumonia in chest X-rays with supervised learning. http://cs229.stanford.edu/proj2017/final-reports/5231221.pdf
  9. 9.Narayan Das N, Kumar N, Kaur M, Kumar V, Singh D (2020) Automated deep transfer learning-based approach for detection of COVID-19 infection in chest X-rays. IRBM. https://doi.org/10.1016/j.irbm.2020.07.001
  10. 10.Ayan E, Ünver HM (2019) Diagnosis of pneumonia from chest X-ray images using deep learning. In: Scientific meeting on electrical-electronics and biomedical engineering and computer science (EBBT), Istanbul, Turkey, pp 1–5. https://doi.org/10.1109/EBBT.2019.8741582
  11. 11.Gaál G, Maga B, Lukács A (2020) Attention U-Net based adversarial architectures for chest X-ray lung segmentation. arXiv:2003.10304
  12. 12.https://tr.euronews.com. Accessed 12 Dec 2020
  13. 13.Liang G, Zheng L (2020) A transfer learning method with deep residual network for pediatric pneumonia diagnosis. Comput Methods Programs Biomed 187:104964
  14. 14.Jaiswal A, Gianchandani N, Singh D, Kumar V, Kaur M (2020) Classification of the COVID-19 infected patients using DenseNet201 based deep transfer learning. J Biomol Struct Dyn. https://doi.org/10.1080/07391102.2020.1788642
  15. 15.Apostolopoulos ID, Mpesiana TA (2020) Covid-19: automatic detection from x-ray images utilizing transfer learning with convolutional neural networks. Phys Eng Sci Med 43:635–640
  16. 16.Zhang J, Xie Y, Li Y, Shen C, Xia Y (2020) COVID-19 screen-ing on chest X-ray images using deep learning based anomaly detection. arXiv:2003.12338v1
  17. 17.Singh D, Kumar V, Kaur M (2020) Classification of COVID-19 patients from chest CT images using multi-objective differential evolution-based convolutional neural networks. Eur J Clin Microbiol Infect Dis 39:1379–1389. https://doi.org/10.1007/s10096-020-03901-z
  18. 18.Chen X, Yao L, Zhang Y (2020) Residual attention U-Net for automated multi-class segmentation of COVID-19 chest CT images. arXiv:2004.05645v1
  19. 19.Adhikari NCD (2020) Infection severity detection of CoVID19 from X-rays and CT scans using artificial intelligence. Int J Comput (IJC) 38(1):73–92
  20. 20.Alqudah AM, Qazan S, Alqudah A (2020) Automated systems for detection of COVID-19 using chest X-ray images and lightweight convolutional neural networks. https://doi.org/10.21203/rs.3.rs-24305/v1
  21. 21.Khan AI, Shah JL, Bhat MM (2020) Coronet: a deep neural network for detection and diagnosis of COVID-19 from chest X-ray images. Comput Methods Programs Biomed 196:105581
  22. 22.Ghoshal B, Tucker A (2020) Estimating uncertainty and interpretability in deep learning for coronavirus (COVID-19) detection. arXiv:2003.10769v1
  23. 23.Hemdan EED, Shouman MA, Karar ME (2020) COVIDX-Net: a framework of deep learning classifiers to diagnose COVID-19 in X-ray images. arXiv:2003.11055
  24. 24.Ucar F, Korkmaz D (2020) COVIDiagnosis-Net: deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images. Med Hypotheses 140:109761
  25. 25.Apostolopoulos ID, Aznaouridis SI, Tzani MA (2020) Extracting possibly representative COVID-19 Biomarkers from X-ray images with deep learning approach and image data related to pulmonary diseases. J Med Biol Eng 40:462–469
  26. 26.Sahinbas K, Catak FO (2020) Transfer learning based convolutional neural network for COVID-19 detection with X-ray images. https://www.ozgurcatak.org/files/papers/covid19-deep-learning.pdf
  27. 27.Jamil M, Hussain I (2020) Automatic detection of COVID-19 infection from chest X-ray using deep learning. medRxiv. https://doi.org/10.1101/2020.05.10.20097063
  28. 28.Barstugan M, Ozkaya U, Ozturk S (2020) Coronavirus (COVID-19) classification using CT images by machine learning methods. arXiv:2003.09424
  29. 29.Punn NS, Agarwal S (2020) Automated diagnosis of COVID-19 with limited posteroanterior chest X-ray images using fine-tuned deep neural networks. https://www.who.int/health-topics/coronavirus6
  30. 30.Afshar P, Heidarian S, Naderkhani F, Oikonomou A, Plataniotis KN, Mohammadi A (2020) COVID-CAPS: a capsule network-based framework for identification of COVID-19 cases from X-ray images. arXiv:2004.02696v2
  31. 31.Narin A, Kaya C, Pamuk Z (2020) Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks. arXiv:2003.10849v1
  32. 32.Cohen JP, Morrison P, Dao L (2020) COVID-19 image data collection. arXiv:2003.11597
  33. 33.Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM (2017) ChestX-Ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, pp 3462–3471. https://doi.org/10.1109/CVPR.2017.369
  34. 34.Mooney P (2018) Chest X-ray images (Pneumonia). Kaggle Repository. https://www.kaggle.com/paultimothymooney/chest-xray-pnemonia
  35. 35.Yildirim O, Talo M, Ay B, Baloglu UB, Aydin G, Acharya UR (2019) Automated detection of diabetic subject using pre-trained 2D-CNN models with frequency spectrum images extracted from heart rate signals. Comput Biol Med 113:103387
  36. 36.Saba T, Mohamed AS, El-Affendi M, Amin J, Sharif M (2020) Brain tumor detection using fusion of hand crafted and deep learning features. Cogn Syst Res 59:221–230
  37. 37.Dorj UO, Lee KK, Choi JY, Lee M (2018) The skin cancer classification using deep convolutional neural network. Multimed Tools Appl 77(8):9909–9924
  38. 38.Kassani SH, Kassani PH (2019) A comparative study of deep learning architectures on melanoma detection. Tissue Cell 58:76–83
  39. 39.Ribli D, Horváth A, Unger Z, Pollner P, Csabai I (2018) Detecting and classifying lesions in mammograms with deep learning. Sci Rep 8:4165
  40. 40.Celik Y, Talo M, Yildirim O, Karabatak M, Acharya UR (2020) Automated invasive ductal carcinoma detection based using deep transfer learning with whole-slide images. Pattern Recogn Lett 133:232–239
  41. 41.Yu X, Kang C, Guttery DS, Kadry S, Chen Y, Zhang Y-D (2020) ResNet-SCDA-50 for breast abnormality classification. In: IEEE/ACM transactions on computational biology and bioinformatics, pp 1–8. https://doi.org/10.1109/TCBB.2020.2986544
  42. 42.Jmour N, Zayen S, Abdelkrim A (2018) Convolutional neural networks for image classification. In: International conference on advanced systems and electric technologies (IC_ASET), Hammamet, Tunisia, pp 397–402
  43. 43.LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://www.nationalgeographic.com/science/2020/02/here-is-what-coronavirus-does-to-the-body/2
  44. 44.Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929–1958
  45. 45.Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359
  46. 46.Lu J, Behbood V, Hao P, Zuo H, Xue S, Zhang G (2015) Transfer learning using computational intelligence: a survey. Knowl Based Syst 80:14–23
  47. 47.Huang Z, Pan Z, Lei B (2017) Transfer learning with deep convolutional neural network for sar target classification with limited labeled data. Remote Sens 9(9):907
  48. 48.Wu Z, Shen C, Van Den Hengel A (2019) Wider or deeper: revisiting the ResNet model for visual recognition. Pattern Recogn 90:119–133
  49. 49.Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S et al (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115:211–252
  50. 50.Ahn JM, Kim S, Ahn KS, Cho SH, Lee KB, Kim US (2018) A deep learning model for the detection of both advanced and early glaucoma using fundus photography. PLoS ONE 13(11):e0207982
  51. 51.Byra M, Styczynski G, Szmigielski C, Kalinowski P, Michalowski L, Paluszkiewicz R et al (2018) Transfer learning with deep convolutional neural network for liver steatosis assessment in ultrasound images. Int J Comput Assist Radiol Surg 13(12):1895–1903
  52. 52.Singh D, Kumar V, Yadav V, Kaur M (2020) Deep convolutional neural networks based classification model for COVID-19 infected patients using chest X-ray images. Int J Pattern Recognit Artif Intell. https://doi.org/10.1142/S0218001421510046

Citation

MLA
Narin, A., et al. “Automatic Detection of Coronavirus Disease (COVID-19) Using X-ray Images and Deep Convolutional Neural Networks”. Pattern Analysis and Applications, vol. 24, no. 3, 2021, pp. 1207–20, https://doi.org/10.1007/s10044-021-00984-y.
APA
Narin, A., Kaya, C., & Pamuk, Z. (2021). Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks. Pattern Analysis and Applications, 24(3), 1207–1220. https://doi.org/10.1007/s10044-021-00984-y
Chicago
Narin, A., C. Kaya, and Z. Pamuk. 2021. “Automatic Detection of Coronavirus Disease (COVID-19) Using X-ray Images and Deep Convolutional Neural Networks”. Pattern Analysis and Applications 24 (3): 1207–20. https://doi.org/10.1007/s10044-021-00984-y.
Harvard
Narin, A., Kaya, C. and Pamuk, Z. (2021) “Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks”, Pattern Analysis and Applications, 24(3), pp. 1207–1220. Available at: https://doi.org/10.1007/s10044-021-00984-y.
Vancouver
1. Narin A, Kaya C, Pamuk Z (2021) Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks. Pattern Analysis and Applications 24:1207–1220

BibTeX

@article{Narin_2021, title={Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks}, volume={24}, ISSN={1433-755X}, url={http://dx.doi.org/10.1007/s10044-021-00984-y}, DOI={10.1007/s10044-021-00984-y}, number={3}, journal={Pattern Analysis and Applications}, publisher={Springer Science and Business Media LLC}, author={Narin, Ali and Kaya, Ceren and Pamuk, Ziynet}, year={2021}, month=May, pages={1207–1220} }
Metadata:Crossref

Access the Paper

This paper is available from its original source. Click below to access the PDF.

Open PDF