Lab Members

Kristy K. Brock, PhD

Principal Investigator, Morfeus Lab
Professor, Depts of Imaging Physics and Radiation Physics
Executive Director, Image Guided Cancer Therapy Research Program

Guillaume Cazoulat, PhD

Research Assistant Professor

Anne-Cecile Lesage, Ph.D.

Research Scientist

Anne-Cecile is a research scientist who joined the Morfeus lab in 2018. She received her Master's degree in Fluid Mechanics from the University of Toulouse (France) and her Ph.D. in Finite Element Numerical Analysis from the University of Nice-Sophia Antipolis (France). In her spare time, she enjoys cycling for fundraising, kickboxing and theater in French with the association “Et Voilà Théâtre”.

Her research expertise is in the fields of Applied Mathematics (e.g., numerical analysis, finite elements, finite difference, inverse methods) and Applied Physics (e.g., hydraulics, hydrodynamics, solid mechanics, geophysics). Her current research works at MD Anderson focus on modeling soft tissue mechanics for medical applications. More specifically, she is developing patient-specific finite element modeling workflows to predict tissue deformations for applications in brain and lung cancer surgery.

Mais Al Taie, MD, PhD

Research Investigator

Muhammad Awais, PhD

Postdoctoral Fellow

Yulun He

GSBS PhD Student

Yulun is a Ph.D. candidate in the Medical Physics Graduate Program at The University of Texas MD Anderson Cancer Center UTHealth Houston Graduate School of Biomedical Sciences. Prior to joining the program, he earned his dual bachelors degree in Mechanical Engineering and Physics from Worcester Polytechnic Institute. In his spare time, he loves to sample the diverse culinary landscape and explore new places in Houston and abroad.

Yulun's dissertation project focuses on advancing clinical understanding of the dose-response relationship for non-small cell lung cancer patients treated with photon or proton radiotherapy. With advanced image registration methods, he is performing longitudinal dose accumulation and voxel-level biological modelling.

McKell Woodland, BS

Rice University PhD Student

McKell is a Ph.D. candidate in the Computer Science Program at Rice University. She received her B.S. in Applied and Computational Mathematics with a minor in Computer Science from Brigham Young University. She has interned in data science roles at Microsoft, Lawrence Livermore National Laboratory, 3M Health Information Systems, and the National Security Agency. In her free time, she enjoys outdoor adventures and tutoring K-12 students in coding through the non-profit organization The Coding School.

Deep learning models typically fail on inputs that are far from the model’s training distribution. McKell’s research focuses on utilizing generative adversarial networks (GANs) to detect these out-of-distribution inputs. Her research has applications in warning clinicians when a deep learning-based segmentation model likely failed, flagging which images should be reviewed when large amounts of data are automatically segmented, determining which images in large cohorts of data would have the most utility to label, and improving datasets and model capabilities over time by diversifying data.

Aashish Gupta, MS

GSBS PhD Student

Erin Snoddy

GSBS PhD Student

Brandon Reber, B.S.

GSBS Ph.D. Student

Brandon is a Medical Physics Ph.D. student in the Morfeus Lab. He obtained his Bachelor of Science degree in Physics at the University of British Columbia in Vancouver, Canada. His undergraduate research project focused on validating a machine learning technique for the identification of Parkinson's disease in individuals using PET images. He feels like project was a great introduction to medical imaging and machine learning, and how they can be used to solve problems in the clinic. In his spare time, he currently enjoys exploring Houston and trying out the many (many!) restaurants the city has to offer.

Brandon's Ph.D. project uses machine learning methods to predict osteoradionecrosis (ORN) resulting from head and neck cancer radiation therapy. These machine learning methods include traditional techniques such as support-vector machines as well as more recent methods such as convolutional neural networks (CNNs). First, his project will look at using data acquired prior to the start of radiation treatment for ORN prediction. This data can include radiation treatment plans and treatment planning computed tomography (CT) images. Next, he will examine functional imaging for this task. These imaging modalities can capture physiological changes in patients associated with ORN. Finally, the last portion of his project will examine using changes in imaging features from different treatment timepoints for ORN prediction. At the conclusion of this project, he hopes to improve the early identification of ORN resulting from head and neck cancer radiation therapy, allowing for earlier interventions, alternative treatment strategies, and improved patient quality of life post-treatment.

John Wood, MS

Computational Scientist

Austin Castelo, BS

Associate Systems Analyst

Emma McCollum, BS

Research Assistant I

Androniki Mitrou, MS

Physics Assistant

Caleb O'Connor, MS

Physics Assistant

Jun Hong, PhD

Imaging Physics Resident

Jun is an Imaging Physics Fellow in the Department of Imaging Physics. She received her PhD in nuclear physics from Michigan State University. She became very interested in applying physics into medicine and had postdoctoral training on modeling cancer metastasis at Yale University, as well as on AI assistance for adaptive radiotherapy and toxicity analysis at Memorial Sloan Kettering Cancer Center. In her free time, she enjoys playing games with her family, oil painting, and cheering for her favorite college football team.

Her current research project involves image guided liver ablation using imaging technologies to achieve more accurate and personalized treatment for the patients. The project aims to help establish the artificial Intelligence workflow with biomechanical modeling, assess the automatic segmentation of critical regions of interest and image registration performance, and analyze the clinical outcome.