Contact Us
(910) 584-6193

Outcomes and Accomplishments

Within AI, Deep Learning (DL) is a set of computational methods that allow an algorithm to program itself by learning from a large set of examples that demonstrate the desired behavior, removing the need to specify rules explicitly. In this project a DL algorithm was created to automatically detect Covid-19 in eye images. A specific type of artificial neural network (a large mathematical function with millions of parameters) optimized for image classification called a deep Convolutional Neural Network (CNN) was trained to classify eye images into one of two classes (also known as labels). The function computes Covid-19 positive class or Covid-19 negative class from the intensities of the pixels in an eye image. Creating or “training” this function requires a large set of images for which the true labels are already known (training set). During the training process, the parameters of the neural network are initially set to random values or values learned by training on a generic dataset. Then, for each image, the label given by the function is compared with the known label from the training set, and parameters of the function are then modified slightly to decrease the error on that image. This process is repeated for every image in the training set many times over, and the function “learns” how to accurately compute labels from the pixel intensities of the image for all images in the training set. With the right training data, the result is a neural network general enough to compute labels on new and unseen images.

Data preprocessing protocols, hyperparameter search, neural network training protocols, and results are described here in narrative form with quantitative information presented in the attachments. A specific CNN named the InceptionResnet is used in this research. Data preprocessing was performed to address the problems of class imbalance (less images of Covid-19 positive than negative), small dataset and biased learning (the CNN predicts everything as Covid-19 negative). Data augmentation was used to balance the datasets, with more augmentations applied to the class with less data. Geometric rotation, injection of Gaussian noise and focal loss were used as augmentation techniques, with focal loss providing additional control on the problem of bias. In AI, a hyperparameter is a parameter whose value is used to control the learning process. By contrast, the values of other parameters are derived via training. One of the most important part of neural network modeling is selection of quality hyperparameters, or more simply: the selection of parameters that the model is unable to change and optimize on its own, such as learning rate and momentum. The difficulty with making a quality selection of hyperparameters is the breadth of the search space, which is nearly infinite. This important part of the research was carried out using the Bayesian hyperparameter optimization algorithm to find the best set of hyperparameter values. Bayesian techniques differ from other, less efficient techniques like random and grid searches in that they use past evaluation results to choose the next values to evaluate. In practice, this allows the Bayesian technique to find better values of hyperparameters in less time. Another important contribution of this research is the interpretation of the results of the CNN. In general, to develop trust in an AI technique with explaining the predictions of the model, it is important to understand the underlying mechanics of that technique, and any potential pitfalls associated with it. The Local Interpretable Model- agnostic Explanations (LIME) method was used to interpret the inner workings of the CNN when predicting the label of an image. The LIME method essentially produces a graphical overlay of a heatmap on the original image to highlight portions of the image that influence its decision in labeling that image as either Covid-19 positive or negative.

OSBM NCPRO – Attachment A-1 Effective: 5/31/20

The attached CNN Performance Report on the results provides evidence that the product of this research, namely the trained CNN has high accuracy, precision and sensitivity on the training dataset and is showing increasing performance on the same metrics on the test dataset which is currently of limited size. These quantitative results are very encouraging, and they strongly suggest that further research is warranted to determine the feasibility of applying this algorithm in the clinical setting and to determine whether use of the algorithm could lead to improved care and outcomes compared with current methods of Covid-19 assessment.

Sambit Bhattacharya, Ph.D.
Professor of Computer Science Director of the Intelligent Systems Lab Fayetteville State University
North Carolina Policy Collaboratory at the University of North Carolina at Chapel Hill
iDetect Covid-19 rapid test
310 Dick St. Suite D
Fayetteville NC 28301

phone-square linkedin facebook pinterest youtube rss twitter instagram facebook-blank rss-blank linkedin-blank pinterest youtube twitter instagram