When: Wednesday, October 3, 2018
Where: PGH 563
Time: 11:00 AM

Toward Efficient Breast Cancer Diagnosis and Survival Prediction Using L-Perceptron

Speaker: Hadi Mansourifar

Breast cancer is the most frequently reported cancer type among the women around the globe and beyond that it has the second highest female fatality rate among all cancer types. Despite all the progresses made in prevention and early intervention, early prognosis and survival prediction rate are still unsatisfactory. In this research, we propose L-Perceptron, a novel type of perceptron which can improve the previous results in terms of accuracy and sensitivity in Wisconsin Breast Cancer dataset (Original) and Haberman's Cancer Survival dataset without any preprocessing or feature extraction.

Bio:

Hadi Mansourifar is a second year PhD student and a Teaching Assistant in UH CS. He received his Master’s degree in Software Engineering from Qazvin Islamic Azad University, Iran in 2012 and immediately employed as instructor in software engineering department PIAU, where he nominated as the best instructor in 2014. His research interests encompass a wide range of area including trigonometry, geometric modeling, computer graphics, numerical analysis, algorithm design and machine learning.

Robust Tracing and Visualization of Heterogeneous Microvascular Networks

Speaker: Pavel Govyadinov

Advances in high-throughput imaging allow researchers to collect three-dimensional images of whole organ microvascular networks. These extremely large images contain networks that are highly complex, time consuming to segment, and difficult to visualize. In this paper, we present a framework for segmenting and visualizing vascular networks from terabyte-sized three-dimensional images collected using high-throughput microscopy. While these images require terabytes of storage, the volume devoted to the fiber network is $\approx$4\% of the total volume size. While the networks themselves are sparse, they are tremendously complex, interconnected, and vary widely in diameter. We describe a parallel GPU-based predictor-corrector method for tracing filaments that is robust to noise and sampling errors common in these data sets. We also propose a number of visualization techniques designed to convey the complex statistical descriptions of fibers across large tissue sections - including commonly studied microvascular characteristics, such as orientation and volume.

Bio:

Pavel Govyadinov received Bachelor's degree in Physics from University of Oregon in 2011 and his Master's degree in Computer Science with a focus on Parallel Computing and Distributed Systems from University of Oregon in 2014. While studying Pavel conducted research at Electrical Geodesic's Inc, developing software to model next generation depression treatment therapy. He is currently working to complete his dissertation focused on the use of high-performance computing analysis, modeling and visualization of data relating to degenerative diseases and brain-related disorders. The future application of this technology is generating simplified, synthetic microvasculature for next-generation printed synthetic organs for transplant patients.