Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Robust and Interpretable COVID-19 Diagnosis on Chest X-ray Images using Adversarial Training (2311.14227v1)

Published 23 Nov 2023 in eess.IV, cs.CV, and cs.LG

Abstract: The novel 2019 Coronavirus disease (COVID-19) global pandemic is a defining health crisis. Recent efforts have been increasingly directed towards achieving quick and accurate detection of COVID-19 across symptomatic patients to mitigate the intensity and spread of the disease. AI algorithms applied to chest X-ray (CXR) images have emerged as promising diagnostic tools, and previous work has demonstrated impressive classification performances. However, such methods have faced criticisms from physicians due to their black-box reasoning process and unpredictable nature. In contrast to professional radiologist diagnosis, AI systems often lack generalizability, explainability, and robustness in the clinical decision making process. In our work, we address these issues by first proposing an extensive baseline study, training and evaluating 21 convolutional neural network (CNN) models on a diverse set of 33,000+ CXR images to classify between healthy, COVID-19, and non-COVID-19 pneumonia CXRs. Our resulting models achieved a 3-way classification accuracy, recall, and precision of up to 97.03\%, 97.97\%, and 99.95\%, respectively. Next, we investigate the effectiveness of adversarial training on model robustness and explainability via Gradient-weighted Class Activation Mapping (Grad-CAM) heatmaps. We find that adversarially trained models not only significantly outperform their standard counterparts on classifying perturbed images, but also yield saliency maps that 1) better specify clinically relevant features, 2) are robust against extraneous artifacts, and 3) agree considerably more with expert radiologist findings.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. Correlation of chest CT and RT-PCR testing for coronavirus disease 2019 (COVID-19) in China: a report of 1014 cases. Radiology, 296, E32–E40.
  2. Covid-qu-ex dataset. URL: https://www.kaggle.com/dsv/3122958. doi:10.34740/KAGGLE/DSV/3122958.
  3. COVID-19: automatic detection from x-ray images utilizing transfer learning with convolutional neural networks. Physical and engineering sciences in medicine, 43, 635–640.
  4. Prediction of COVID-19 using genetic deep learning convolutional neural network (GDCNN). IEEE Access, 8, 177647–177666.
  5. Deep learning for screening COVID-19 using chest X-ray images. In 2020 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 2521–2527). IEEE.
  6. Boudrioua, M. S. (2020). COVID-19 detection from chest X-ray images using CNNs models: Further evidence from Deep Transfer Learning. The University of Louisville Journal of Respiratory Infections, 4.
  7. A transfer learning-based approach with deep cnn for covid-19-and pneumonia-affected chest x-ray image classification. SN Computer Science, 3, 1–10.
  8. Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1251–1258).
  9. Chollet, F. et al. (2015). Keras. URL: https://github.com/fchollet/keras.
  10. Duncan, D. (2021). COVID-19 data sharing and collaboration. Communications in Information and Systems, 21.
  11. An optimized deep learning architecture for the diagnosis of COVID-19 disease based on gravitational search optimization. Applied Soft Computing, 98, 106742.
  12. Sensitivity of chest CT for COVID-19: comparison to RT-PCR. Radiology, 296, E115–E117.
  13. Now you see it, now you dont: adversarial vulnerabilities in computational pathology. arXiv preprint arXiv:2106.08153, .
  14. Efficient and visualizable convolutional neural networks for COVID-19 classification using Chest CT. Expert Systems with Applications, 195, 116540.
  15. Adversarial attacks and adversarial robustness in computational pathology. Nature communications, 13, 5711.
  16. Explaining and Harnessing Adversarial Examples. arXiv e-prints, (p. arXiv:1412.6572). doi:10.48550/arXiv.1412.6572. arXiv:1412.6572.
  17. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770--778).
  18. Identity mappings in deep residual networks. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14 (pp. 630--645). Springer.
  19. Improving the performance of CNN to predict the likelihood of COVID-19 using chest X-ray images with preprocessing algorithms. International journal of medical informatics, 144, 104284.
  20. Covidx-net: A framework of deep learning classifiers to diagnose COVID-19 in X-ray images. arXiv preprint arXiv:2003.11055, .
  21. A COVID-19 Visual Diagnosis Model Based on Deep Learning and GradCAM. IEEJ Transactions on Electrical and Electronic Engineering, 17, 1038--1047.
  22. Multi-Scale Dense Networks for Resource Efficient Image Classification. arXiv e-prints, (p. arXiv:1703.09844). doi:10.48550/arXiv.1703.09844. arXiv:1703.09844.
  23. CoroDet: A deep learning based classification for COVID-19 detection using chest X-ray images. Chaos, Solitons & Fractals, 142, 110495.
  24. Adversarial examples are not bugs, they are features. Advances in neural information processing systems, 32.
  25. A combined deep CNN-LSTM network for the detection of novel coronavirus (COVID-19) using X-ray images. Informatics in medicine unlocked, 20, 100412.
  26. Deep learning approaches for COVID-19 detection based on chest X-ray images. Expert Systems with Applications, 164, 114054.
  27. Deepcovidexplainer: explainable COVID-19 diagnosis from chest X-ray images. In 2020 IEEE international conference on bioinformatics and biomedicine (BIBM) (pp. 1034--1037). IEEE.
  28. Learning distinctive filters for COVID-19 detection from chest X-ray using shuffled residual CNN. Applied Soft Computing, 99, 106744.
  29. Automatic detection of coronavirus disease (COVID-19) in X-ray and CT images: a machine learning based approach. Biocybernetics and Biomedical Engineering, 41, 867--879.
  30. COV19-CNNet and COV19-ResNet: diagnostic inference Engines for early detection of COVID-19. Cognitive Computation, (pp. 1--11).
  31. CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images. Computer methods and programs in biomedicine, 196, 105581.
  32. COVID-19 chest radiography images analysis based on integration of image preprocess, guided grad-CAM, machine learning and risk management. In Proceedings of the 4th International Conference on Medical and Health Informatics (pp. 281--288).
  33. Improving Interpretability in Medical Imaging Diagnosis using Adversarial Training. arXiv e-prints, (p. arXiv:2012.01166). doi:10.48550/arXiv.2012.01166. arXiv:2012.01166.
  34. Automated medical diagnosis of COVID-19 through EfficientNet convolutional neural network. Applied soft computing, 96, 106691.
  35. Deep-COVID: Predicting COVID-19 from chest X-ray images using deep transfer learning. Medical image analysis, 65, 101794.
  36. Shallow convolutional neural network for COVID-19 outbreak screening using chest X-rays. Cognitive Computation, (pp. 1--14).
  37. Deep learning COVID-19 features on CXR using limited training data sets. IEEE transactions on medical imaging, 39, 2688--2700.
  38. Automated detection of COVID-19 cases using deep neural networks with X-ray images. Computers in biology and medicine, 121, 103792.
  39. Vulnerability in deep transfer learning models to adversarial fast gradient sign attack for covid-19 prediction from chest radiography images. Applied Sciences, 11, 4233.
  40. A deep learning and grad-CAM based color visualization approach for fast detection of COVID-19 cases using chest X-ray and CT-Scan images. Chaos, Solitons & Fractals, 140, 110190.
  41. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on computer vision (pp. 618--626).
  42. Efficacy of transfer learning-based resnet models in chest x-ray image classification for detecting covid-19 pneumonia. Chemometrics and Intelligent Laboratory Systems, 224, 104534.
  43. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv e-prints, (p. arXiv:1409.1556). doi:10.48550/arXiv.1409.1556. arXiv:1409.1556.
  44. SmoothGrad: removing noise by adding noise. arXiv e-prints, (p. arXiv:1706.03825). doi:10.48550/arXiv.1706.03825. arXiv:1706.03825.
  45. Axiomatic attribution for deep networks. In International conference on machine learning (pp. 3319--3328). PMLR.
  46. False-positive covid-19 results: hidden problems and costs. The lancet respiratory medicine, 8, 1167--1168.
  47. Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the AAAI conference on artificial intelligence. volume 31.
  48. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818--2826).
  49. Intriguing properties of neural networks. arXiv e-prints, (p. arXiv:1312.6199). doi:10.48550/arXiv.1312.6199. arXiv:1312.6199.
  50. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105--6114). PMLR.
  51. Efficientnetv2: Smaller models and faster training. In International conference on machine learning (pp. 10096--10106). PMLR.
  52. Robustness May Be at Odds with Accuracy. arXiv e-prints, (p. arXiv:1805.12152). doi:10.48550/arXiv.1805.12152. arXiv:1805.12152.
  53. Deep learning COVID-19 detection bias: accuracy through artificial intelligence. International Orthopaedics, 44, 1539--1542.
  54. COVID-NET: A tailored deep convolutional neural network design for detection of COVID-19 cases from chest x-ray images. Scientific reports, 10, 1--12.
  55. Covid-19 testing: the threat of false-negative results. In Mayo clinic proceedings (pp. 1127--1129). Elsevier volume 95.
  56. Interpreting adversarially trained convolutional neural networks. In International conference on machine learning (pp. 7502--7511). PMLR.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Karina Yang (2 papers)
  2. Alexis Bennett (1 paper)
  3. Dominique Duncan (5 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now