BACKGROUND AND THEORETICAL FOUNDATIONS OF A 2.5D DEEP LEARNING FRAMEWORK FOR COVID-19 CT DIAGNOSIS

Zhang H. .


Annotatsiya

This paper presents the theoretical foundations of a lightweight, efficient, and interpretable 2.5D deep learning framework for automated COVID 19 classification using chest CT images. The need for such systems is motivated by the high burden on healthcare systems and the limitations of RT PCR diagnostics. Key components are reviewed: convolutional neural networks, transfer learning, the 2.5D strategy, traditional pooling methods and their shortcomings for sparse lesions. An adaptive Top K pooling mechanism based on the L2 norm of feature vectors is proposed, which automatically selects the most informative CT slices and aggregates them for classification. Mixed precision training (AMP) is introduced to reduce GPU memory consumption and accelerate computation. Grad CAM applied to the Top K selected slices provides model interpretability. This work lays the theoretical groundwork for a practically validated system presented in subsequent chapters of the dissertation.


Adabiyotlar

  1. Shi F., Wang J., Shi J., et al., “Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation, and Diagnosis for COVID 19,” IEEE Reviews in Biomedical Engineering, vol. 14, pp. 4–15, 2021. DOI: 10.1109/RBME.2020.2987975
  2. Li Y. and Xia L., “Coronavirus Disease 2019 (COVID 19): Role of Chest CT in Diagnosis and Management,” American Journal of Roentgenology, vol. 214, no. 6, pp. 1280–1286, 2020. DOI: 10.2214/AJR.20.22954
  3. Li L., Qin L., Xu Z., et al., “Artificial Intelligence Distinguishes COVID 19 from Community Acquired Pneumonia on Chest CT,” Radiology, vol. 296, no. 2, pp. E65–E71, 2020. DOI: 10.1148/radiol.2020200905
  4. Huang G., Liu Z., van der Maaten L., Weinberger K.Q., “Densely Connected Convolutional Networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. DOI: 10.1109/CVPR.2017.243
  5. Schlemper J., Oktay O., Schaap M., et al., “Attention gated networks for improving ultrasound scan plane detection,” in Proceedings of Medical Imaging with Deep Learning (MIDL), 2018.
  6. Zhou B., Khosla A., Lapedriza A., Oliva A., Torralba A., “Learning Deep Features for Discriminative Localization,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. DOI: 10.1109/CVPR.2016.319
  7. Pan S.J. and Yang Q., “A Survey on Transfer Learning,” IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345–1359, 2010. DOI: 10.1109/TKDE.2009.191
  8. Yosinski J., Clune J., Bengio Y., Lipson H., “How Transferable Are Features in Deep Neural Networks?” in Advances in Neural Information Processing Systems (NeurIPS), 2014.
  9. Raghu M., Zhang C., Kleinberg J., Bengio S., “Transfusion: Understanding Transfer Learning for Medical Imaging,” in Advances in Neural Information Processing Systems (NeurIPS), 2019.
  10. Tajbakhsh N., Shin J.Y., Gurudu S.R., et al., “Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?” IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1299–1312, 2016. DOI: 10.1109/TMI.2016.2535302
  11. Cruz L.B. da, Dias Júnior D.A., Diniz J.O.B., et al., “Kidney Tumor Segmentation from CT Images Using a 2.5D Residual Aggregation Network,” in Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2020. DOI: 10.1109/SMC42975.2020.9282972
  12. Ning Z., Tian S., Wang S., et al., “Omnidirectional 2.5D Representation for COVID 19 Diagnosis Using Chest CTs,” arXiv preprint, 2020. arXiv:2011.06709
  13. Hassan S.A., Khaliq A., Raza M., et al., “2.5D CNN for COVID 19 Diagnosis from CT Images,” in 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2020.
  14. Gao Z., Wang L., Zhou L., Zhang J., “HEp 2 Cell Image Classification with Deep Convolutional Neural Networks,” IEEE Journal of Biomedical and Health Informatics, vol. 21, no. 2, pp. 416–425, 2017. DOI: 10.1109/JBHI.2016.2526604
  15. Ilse M., Tomczak J., Welling M., “Attention based Deep Multiple Instance Learning,” in Proceedings of the 35th International Conference on Machine Learning (ICML), 2018.
  16. [16] Micikevicius P., Narang S., Alben J., et al., “Mixed Precision Training,” in International Conference on Learning Representations (ICLR), 2018.
  17. Selvaraju R.R., Cogswell M., Das A., Vedantam R., Parikh D., Batra D., “Grad CAM: Visual Explanations from Deep Networks via Gradient Based Localization,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017. DOI: 10.1109/ICCV.2017.74
  18. Reyes M., Meier R., Pereira S., et al., “On the Interpretability of Artificial Intelligence in Radiology: Challenges and Opportunities,” Radiology: Artificial Intelligence, vol. 2, no. 3, p. e190043, 2020. DOI: 10.1148/ryai.2020190043
  19. Sokolova M. and Lapalme G., “A systematic analysis of performance measures for classification tasks,” Information Processing & Management, vol. 45, no. 4, pp. 427–437, 2009. DOI: 10.1016/j.ipm.2009.03.002
  20. Bradley A.P., “The Use of the Area Under the ROC Curve in the Evaluation of Machine Learning Algorithms,” Pattern Recognition, vol. 30, no. 7, pp. 1145–1159, 1997. DOI: 10.1016/S0031-3203(96)00142-2
  21. Topol E.J., “High performance medicine: the convergence of human and artificial intelligence,” Nature Medicine, vol. 25, no. 1, pp. 44–56, 2019. DOI: 10.1038/s41591-018-0300-7