Classification of COVID-19 using Deep Learning and Radiomic Texture Features extracted from CT scans of Patients Lungs

COVID-19 is an air-borne viral infection, which infects the respiratory system in the human body, and it became a global pandemic in early March 2020. The damage caused by the COVID-19 disease in a human lung region can be identified using Computed Tomography (CT) scans. We present a novel approach in classifying COVID-19 infection and normal patients using a Random Forest (RF) model to train on a combination of Deep Learning (DL) features and Radiomic texture features extracted from CT scans of patient's lungs. We developed and trained DL models using CNN architectures for extracting DL features. The Radiomic texture features are calculated using CT scans and its associated infection masks. In this work, we claim that the RFs classification using the DL features in conjunction with Radiomic texture features enhances prediction performance. The experiment results show that our proposed models achieve a higher True Positive rate with the average Area Under the Receiver Curve (AUC) of 0.9768, 95% Confidence Interval (CI) [0.9757, 0.9780]. © 2021 IEEE.

Automatic Hyperparameter Optimization for Arbitrary Neural Networks in Serverless AWS Cloud

Deep Neural Networks are the most efficient method to solve many challenging problems. The importance of the subject can be demonstrated by the fact that the 2019 Turing Award was given to the godfathers of AI (and Neural Networks) Yoshua Bengio, Geoffrey Hinton, and Yann LeCun. In spite of the numerous advancements in the field, most of the models are being tuned manually. Accurate models became especially important during the novel coronavirus pandemic.Many day-to-day decisions depend on the model predictions affecting billions of people. We implemented a flexible automatic real-time hyperparameter tuning approach for arbitrary DNN models written in Python and Keras without manual steps. All of the existing tuning libraries require manual steps (like hyperopt, Scikit-Optimize or SageMaker). We provide an innovative methodology to automate hyper-parameter tuning for an arbitrary Neural Network model source code, utilizing Serverless Cloud and implementing revolutionary microservices, security, interoperability and orchestration. Our methodology can be used in numerous applications, including Information and Communication Systems. © 2021 IEEE.

Toward Generating Synthetic CT Volumes using a 3D-Conditional Generative Adversarial Network

Network (cGAN) architecture that is capable of generating 3D Computed Tomography scans in voxels from noisy and/or pixelated approximations and with the potential to generate full synthetic 3D scan volumes. We believe conditional cGAN to be a tractable approach to generate 3D CT volumes, even though the problem of generating full resolution deep fakes is presently impractical due to GPU memory limitations. We present results for autoencoder, denoising, and depixelating tasks which are trained and tested on two novel COVID19 CT datasets. Our evaluation metrics, Peak Signal to Noise ratio (PSNR) range from 12.53 - 46.46 dB, and range from 0.89 to 1. © 2020 IEEE.

Generating Realistic COVID-19 x-rays with a Mean Teacher plus Transfer Learning GAN

COVID-19 is a novel infectious disease responsible for over 1.2 million deaths worldwide as of November 2020. The need for rapid testing is a high priority and alternative testing strategies including x-ray image classification are a promising area of research. However, at present, public datasets for COVID-19 x-ray images have low data volumes, making it challenging to develop accurate image classifiers. Several recent papers have made use of Generative Adversarial Networks (GANs) in order to increase the training data volumes. But realistic synthetic COVID-19 x-rays remain challenging to generate. We present a novel Mean Teacher + Transfer GAN (MTT-GAN) that generates COVID-19 chest x-ray images of high quality. In order to create a more accurate GAN, we employ transfer learning from the Kaggle pneumonia x-ray dataset, a highly relevant data source orders of magnitude larger than public COVID-19 datasets. Furthermore, we employ the Mean Teacher algorithm as a constraint to improve stability of training. Our qualitative analysis shows that the MTT-GAN generates x-ray images that are greatly superior to a baseline GAN and visually comparable to real x-rays. Although board-certified radiologists can distinguish MTT-GAN fakes from real COVID-19 x-rays, quantitative analysis shows that MTT-GAN greatly improves the accuracy of both a binary COVID-19 classifier as well as a multi-class pneumonia classifier as compared to a baseline GAN. Our classification accuracy is favorable as compared to recently reported results in the literature for similar binary and multi-class COVID-19 screening tasks.