Artificial Intelligence Applied to COVID-19 Lung Infection Segmentation from CT Images
Artificial Intelligence Applied to COVID-19 Lung Infection Segmentation from CT Images |
||
 |
 |
|
| © 2023 by IJETT Journal | ||
| Volume-71 Issue-7 |
||
| Year of Publication : 2023 | ||
| Author : Amal Azeroual, Mohamed Chala, Benayad Nsiri, Rachid Oulad Haj Thami, Ittimade Nassar, Brahim Benaji |
||
| DOI : 10.14445/22315381/IJETT-V71I7P213 | ||
How to Cite?
Amal Azeroual, Mohamed Chala, Benayad Nsiri, Rachid Oulad Haj Thami, Ittimade Nassar, Brahim Benaji, "Artificial Intelligence Applied to COVID-19 Lung Infection Segmentation from CT Images," vol. 71, no. 7, pp. 124-131, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I7P213
Abstract
COVID-19 poses an exceptional health crisis to the world. Given its enormous effect on human health, it is imperative to provide a quick and efficient diagnosis to mitigate the pressure healthcare systems face. Numerous imaging methods, such as computed tomography (CT), are employed to diagnose COVID-19. This research paper introduces an approach for the automated segmentation of lung infections caused by COVID-19 in CT images. To achieve this objective, utilizing deep convolutional neural networks is suggested to study the most widely used architectures in the medical imaging field that rely on encoder/decoder models. Adopting an artificial intelligence data collection called the COVID-19 CT Segmentation Dataset; the suggested model is executed in areas framework in Python. Afterwards, models description, training with data augmentation, validation, and predictions are provided. Finally, the results are contrasted with existing labelled data. The trained model is tested with new images. Compared to manual expert segmentation, prediction results generated values of 0.884, 0.755, and 0.982 for metrics area under the ROC curve, Dice similarity, and accuracy, respectively. Ultimately, a summary is presented for future work, including integrating the suggested model within a consistent framework in medical image processing for clinical is given.
Keywords
COVID-19, Deep Learning, Convolutional Neural Network, Image Segmentation, Chest CT Scan.
References
[1] WHO/Europe, Home. [Online]. Available: https://www.who.int/europe/home?v=welcome
[2] Covid-19 Disease (New Coronavirus), Institut Pasteur. [Online]. Available: https://www.pasteur.fr/fr/centre-medical/fiches-maladies/maladie-covid-19-nouveau-coronavirus
[3] Ali Abbasian Ardakani et al., “COVIDiag: A Clinical CAD System to Diagnose COVID-19 Pneumonia based on CT Findings,” European Radiology, vol. 31, pp. 121–130, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[4] COVID - Coronavirus Statistics - Worldometer. [Online]. Available: https://www.worldometers.info/coronavirus/
[5] Thomas C. Kwee, and Robert M. Kwee, “Chest CT in covid-19: What the Radiologist Needs to Know,” Radiographics, vol. 40, no. 7, pp. 1848–1865, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Wassim W. Labaki et al., “The Role of Chest Computed Tomography in the Evaluation and Management of the Patient with Chronic Obstructive Pulmonary Disease,” American Journal of Respiratory and Critical Care Medicine, vol. 196, no. 11, pp. 1372–1379, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Scott Simpson et al., “Radiological Society of North America Expert Consensus Document on Reporting Chest CT Findings Related to COVID-19: Endorsed by the Society of Thoracic Radiology, the American College of Radiology, and RSNA,” Radiology: Cardiothoracic Imaging, vol. 2, no. 2, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Ali Abbasian Ardakani et al., “Application of Deep Learning Technique to Manage COVID-19 in Routine Clinical Practice using CT Images: Results of 10 Convolutional Neural Networks,” Computers in Biology and Medicine, vol. 121, p. 103795, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Afshin Shoeibi et al., “Automated Detection and Forecasting of COVID-19 using Deep Learning Techniques: A Review,” Machine Learning, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Y. Lecun et al., “Gradient-based Learning Applied to Document Recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2323, 1998.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Mark Tygert et al., “A Mathematical Motivation for Complex-Valued Convolutional Networks,” Neural Computation, vol. 28, no. 5, pp. 815-825, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Dumitru Erhan et al., “Scalable Object Detection using Deep Neural Networks,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2147-2154, 2014.
[Google Scholar] [Publisher Link]
[13] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Dan C. Cireşan et al., “Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images,” Advances in Neural Information Processing Systems, 2012.
[Google Scholar] [Publisher Link]
[15] Bharath Hariharan et al., “Simultaneous Detection and Segmentation,” Lecture Notes in Computer Science, pp. 297–312, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Mark Everingham et al., “The Pascal Visual Object Classes (VOC) Challenge,” International Journal of Computer Vision, vol. 88, pp. 303–338, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Ross Girshick et al., “Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 580–587, 2014.
[Google Scholar] [Publisher Link]
[18] Jonathan Long, Evan Shelhamer, and Trevor Darrell, “Fully Convolutional Networks for Semantic Segmentation,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440, 2015.
[Google Scholar] [Publisher Link]
[19] Nahian Siddique et al., “U-net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications,” IEEE Access, vol. 9, pp. 82031–82057, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Olaf Ronneberger, Philipp Fischer, and Thomas Brox, “U-Net : Convolutional Networks for Biomedical Image Segmentation,” Medical Image Computing and Computer-Assisted Intervention, pp. 234–241, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Chala Mohamed et al., “Health Vigilance for Medical Imaging Diagnostic Optimization: Automated Segmentation of COVID-19 Lung Infection from CT Images,” E3S Web of Conferences, vol. 319, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Christian Szegedy et al., “Going Deeper with Convolutions,” Conference on Computer Vision and Pattern Recognition, pp. 1–9, 2015.
[Google Scholar] [Publisher Link]
[23] Karen Simonyan, and Andrew Zisserman, “Very Deep Convolutional Networks for Large-scale Image Recognition,” Computer Vision and Pattern Recognition, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Kaiming He et al., “Deep Residual Learning for Image Recognition,” Conference on Computer Vision and Pattern Recognition, pp. 770–778, 2016.
[Google Scholar] [Publisher Link]
25] Deng-Ping Fan et al., “Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images,” IEEE Transactions on Medical Imaging, vol. 39, no. 8, pp. 2626–2637, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Longxi Zhou et al., “A Rapid, Accurate and Machine-Agnostic Segmentation and Quantification Method for CT-Based COVID-19 Diagnosis,” IEEE Transactions on Medical Imaging, vol. 39, no. 8, pp. 2638–2652, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Xinggang Wang et al., “A Weakly-Supervised Framework for COVID-19 Classification and Lesion Localization from Chest CT,” IEEE Transactions on Medical Imaging, vol. 39, no. 8, pp. 2615–2625, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[28] COVID-19 - Medical Segmentation. [Online]. Available: http://medicalsegmentation.com/COVID19/
[29] SIRM. [Online]. Availbale: https://sirm.org/en/
[30] Håvard Bjørke Jenssen, Covid-19 Radiology — Data Collection and Preparation for Artificial Intelligence, Medium. [Online]. Available: https://medium.com/@hbjenssen/covid-19-radiology-data-collection-and-preparation-for-artificial-intelligence-4ecece97bb5b
[31] Chala Mohamed et al., “Deep Convolutional Networks for Image Segmentation: Application to Optic Disc detection,” 2020 International Conference on Electrical and Information Technologies, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Lee R. Dice, “Measures of the Amount of Ecologic Association between Species,” Ecology, vol. 26, no. 3, pp. 297–302, 1945.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Chigozie Nwankpa et al., “Activation Functions: Comparison of trends in Practice and Research for Deep Learning,” Machine Learning, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Xavier Glorot, and Yoshua Bengio, “Understanding the Difficulty of Training deep Feedforward Neural Networks,” Journal of Machine Learning Research, vol. 9, pp. 249–256, 2010.
[Google Scholar] [Publisher Link]
[35] S. Deepa, and S. Shakila, “Optimized Convolutional Neural Networks for Detecting Covid-19 from Chest X-Ray,” International Journal of Engineering Trends and Technology, vol. 70, no. 12, pp. 210-218, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Francisco Melo, Area under the ROC Curve, Encyclopedia of Systems Biology, Springer, New York, pp. 38–39, 2013.
[CrossRef] [Publisher Link]