On Friday (December 1), the Computer Science Department hosts another event of the Fall CS Seminar Series. This event featured a talk by Ms. Gunda Mertin (University of Lübeck, Loyola University Chicago) and Ms. Rachel Gordon (Loyola University Chicago)
- My Internship at Loyola - Learning About TLA+ and More
Talk By: Ms. Gunda Mertin (Loyola University Chicago, University of Lübeck)
- Advancing HDR Brachytherapy Treatment Planning with Enhanced CT-to-MRI Synthesis
Talk By: Ms. Rachel Gordon (Loyola University Chicago)
Speakers and Talks:
My Internship at Loyola - Learning About TLA+ and More
Talk By: Gunda Mertin (Loyola University Chicago, University of Lübeck)
Abstract: Professor Konstantin Läufer and I will be talking about my experience as a student-intern from Germany, here at the Computer Science Department at Loyola. We will give a short overview of the workshop paper we are working on called "Teaching Formal Methods in Higher Education Using TLA+". We will also briefly introduce the formal specification language TLA+ with a few examples and explain how it may be used in future courses on Formal Methods
Speaker Bio: Gunda Mertin is a Computer Science graduate student from Luebeck, Germany. She has a bachelor's in mathematics and is especially interested in Formal Methods and Theoretical Computer Science. She organized an internship with Professor Konstantin Läufer from September - December 2023 with a focus on research on Formal Methods.
Advancing HDR Brachytherapy Treatment Planning with Enhanced CT-to-MRI Synthesis
Talk By: Rachel Gordon (Loyola University Chicago)
Abstract: High-dose-rate (HDR) brachytherapy is a radiation treatment modality that places radioactive sources directly in cancerous regions. Radiation treatment planning for HDR prostate brachytherapy utilizes both CT and MRI to visualize the path of radioactive source and prostate gland, respectively. This talk introduces GAN-CM, a method for conditional CT-to-MRI translation that is based on Generative Adversarial Networks (GANs). Exploring various experimental settings, we show that training GANs for this task requires careful considerations for preparing the data, such as normalizing and distributing the pixel values of input images. In this talk, I will cover the data preprocessing methods, GAN-CM architecture, and results comparing GAN-CM performance to other state-of-the-art image-to-image translation methods.
Speaker Bio: Rachel Gordon is a graduate student in the Data Science program at Loyola University Chicago. Her research interests include computer vision, natural language processing, generative AI, and deep-learning-based healthcare applications. Her current research focuses on increasing the accessibility of accurate and clinically relevant MRI-quality images for high-dose-radiation (HDR) prostate brachytherapy treatment planning to developing methods specifically designed for CT-to-MRI synthesis.