ABSTRACT
Novel COVID-19 or commonly known as Corona-Virus epidemic which was identified in Nov–Dec 2019, needs special consideration due to its future outbreaks and a possible threat to the world. Ever since, apart from clinical prognosis and diagnosis, AI (Artificial Intelligence) provides a novel paradigm for health-care, ML (Machine Learning) algorithms are employed in evaluating data and decision making processes. This means that AI–ML driven models help in identifying COVID-19 epidemic as well as predict their nature of spread across the world. Unlikely other health-care issues, for Corona-virus or COVID-19, for its detection, AI/ML-driven prediction models are anticipated to work as cross-population train and test models are the main perseverance of this chapter. The objective of this chapter is to know the novel COVID-19 epidemiology, its major prevention from spreading, and to assess the machine/deep learning-based architecture performance that is proposed in the present year for classification of COVID-19 images such as, X-Ray and CT. Especially, deep-learning centered algorithms known as the Convolutional Neural Network, which plays an excessive effect on mining highly essential features, mostly in terms of medical images. The performance of the technique is shown to be impressive with X-Ray and CT image scans, has been adopted in most of the recently published articles on the COVID-19/Coronavirus with notable results. Also, according to this chapter, that machine learning, as well as deep learning technology, has prospective clinical solicitations. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
Although, recently convolutional neural networks (CNNs) based prognostic models have been developed for COVID-19 severity prediction, most of these studies have analyzed characteristics of lung infiltrates (ground-glass opacities and consolidations) on chest radiographs or CT. However, none of the studies have explored the possible lung deformations due to the disease. Our hypothesis is that more severe disease results in more pronounced deformation. The key contributions of this work are three-fold: (1) A new lung deformation based biomarker analyzing regions of differential distensions between COVID-19 patients with mild and severe disease. (2) Integrating 3D-CNN characterization of lung deformation regions and lung infiltrates on lung CT into a novel framework (LuMiRa) for prognosticating COVID-19 severity. (3) Validating LuMiRa on one of the largest multi-institutional cohort till date (N = 948 patients). We found that majority of the shape deformations were observed in the mediastinal surface of both the lungs and in left interior lobe. On a testing cohort based on two institutions, Av (N = 419) and Bv (N = 113), LuMiRa yielded an area under the receiver operating characteristic curve (AUC) of 0.89 and 0.77 respectively showing significant improvement over a 3D-CNN trained over just lung infiltrates (AUC = 0.85 (p < 0.001), AUC = 0.75 (p = 0.01)). Additionally, LuMiRa performed significantly better than machine learning models trained on clinical and radiomic features (0.82, 0.78 and 0.72, 0.72 on Av and Bv respectively). © 2021, Springer Nature Switzerland AG.