John Cisler

Benjamin Paulson, Theodore Colwell, Natalia Bukowski et al.

Current methods for diagnosing the progression of multiple types of cancer within patients rely on interpreting stained needle biopsies. This process is time-consuming and susceptible to error throughout the paraffinization, Hematoxylin and Eosin (H&E) staining, deparaffinization, and annotation stages. Fourier Transform Infrared (FTIR) imaging has been shown to be a promising alternative to staining for appropriately annotating biopsy cores without the need for deparaffinization or H&E staining with the use of Fourier Transform Infrared (FTIR) images when combined with machine learning to interpret the dense spectral information. We present a machine learning pipeline to segment white blood cell (lymphocyte) pixels in hyperspectral images of biopsy cores. These cells are clinically important for diagnosis, but some prior work has struggled to incorporate them due to difficulty obtaining precise pixel labels. Evaluated methods include Support Vector Machine (SVM), Gaussian Naive Bayes, and Multilayer Perceptron (MLP), as well as analyzing the comparatively modern convolutional neural network (CNN).

Benjamin Paulson, Joshua Goldshteyn, Sydney Balboni et al.

Computed tomography (CT) is a beneficial imaging tool for diagnostic purposes. CT scans provide detailed information concerning the internal anatomic structures of a patient, but present higher radiation dose and costs compared to X-ray imaging. In this paper, we build on previous research to convert orthogonal X-ray images into simulated CT volumes by exploring larger datasets and various model structures. Significant model variations include UNet architectures, custom connections, activation functions, loss functions, optimizers, and a novel back projection approach.

Sydney Balboni, Grace Ivey, Brett Storoe et al.

Price volatility in global food commodities is a critical signal indicating potential disruptions in the food market. Understanding forthcoming changes in these prices is essential for bolstering food security, particularly for nations at risk. The Food and Agriculture Organization of the United Nations (FAO) previously developed sophisticated statistical frameworks for the proactive prediction of food commodity prices, aiding in the creation of global early warning systems. These frameworks utilize food security indicators to produce accurate forecasts, thereby facilitating preparations against potential food shortages. Our research builds on these foundations by integrating robust price security indicators with cutting-edge deep learning (DL) methodologies to reveal complex interdependencies. DL techniques examine intricate dynamics among diverse factors affecting food prices. Through sophisticated time-series forecasting models coupled with a classification model, our approach enhances existing models to better support communities worldwide in advancing their food security initiatives.