Optical Surgical Navigation: A Promising Low-cost Alternative.

State-of-the-art computer-assisted surgery relies on infrared-based cameras for precise positional measurements. However, the cost of purchasing these systems acts as a barrier for smaller healthcare facilities to adopt them. Recently, low-cost optical tracking with cameras has emerged as a promising alternative, but differences in operating room conditions and patient anatomy can cause inconsistencies between procedures. Therefore, it is essential to identify and evaluate individual factors that may affect a procedure. In this study, we evaluate fiducial ArUco markers as a low-cost alternative to traditional markers. To evaluate their effectiveness, we designed a ground truth testing platform, which enables us to measure the real-time difference between the predicted and actual positions. We investigated the effects of warping, line-of-sight obstruction, and operating room lighting as variables that could influence marker tracking in the operating room. Each variable was isolated and simplified to quantifiable modifications to the physical marker and X-Y platform environment. We find that our navigation system is a promising approach for use in computer-navigated surgery, and future work will focus on implementing image processing techniques to improve the accuracy of optical marker tracking.

A Machine Learning Approach to COVID-19 Detection via Graphene Field-Effect-Transistor (GFET).

In the wake of the COVID-19 pandemic, there has been a need for reliable diagnostic testing. However, state-of-the-art detection methods rely on laboratory tests and also vary in accuracy. We evaluate that the usage of a graphene field-effect-transistor (GFET) coupled with machine learning can be a promising alternate diagnostic testing method. We processed the current-voltage data gathered from the GFET sensors to assess information about the presence of COVID-19 in biosamples. We perform binary classification using the following machine learning algorithms: Linear Discriminant Analysis (LDA), Support Vector Machines (SVM) with the Radial Basis Function (RBF) kernel, and K-Nearest Neighbors (KNN) in conjunction with Principal Component Analysis (PCA). We find that LDA and SVM with RBF proved to be the most accurate in identifying positive and negative samples, with accuracies of 99% and 98.5%, respectively. Based on these results, there is promise to develop a bioelectronic diagnostic method for COVID-19 detection by combining GFET technology with machine learning.