Skip to content

Our Team

Leadership

John Shepherd, PhD

Principal Investigator

I am a Researcher/Professor at the UH Cancer Center, a Fulbright Scholar and an expert in mining biomarkers from medical imaging using advanced machine learning techniques; PI of the NIH-funded Shape Up! Studies on how 3D optical body shape relates to human health in children and adults; Director of the Hawaii Pacific Island Mammography Registry, the Body Composition Exercise Physiology and Energy Metabolism CORE lab, and the Shepherd Research Lab; 2017 President of the International Society for Clinical Densitometry; ISCD’s John Bilezikian Global Leadership and Oscar Gluck Humanitarian Awards for his IAEA contributions. I have chaired 10 international workshops on quantitative imaging and have over 200 peer-reviewed publications that have been referenced over 10,000 times.

Peter Sadowski, PhD

Co-Director, Machine Learning

My background is in machine learning, computational science, and data analysis. During my PhD and Postdoc, I became an expert in deep learning, and I have applied it to problems in bioinformatics, chemoinformatics, and high-energy physics, where I was the first to use deep learning for particle collider experiments. I am an Assistant Professor in the UH Computer Science department with a lab specializing in robust machine learning techniques for scientific data analysis, in which we use deep learning to model high-dimensional data such as graphs, images, and videos. I have a particular interest in applying these techniques to medical imaging and health informatics.

Lynne Wilkens, PhD

Co-Director, Medical Data Curation

Dr. Wilkens has a DrPH from the University of North Carolina in Biostatistics and has worked in health research for over 30 years including over 25 years in cancer research. Much of this effort has focused on prevention in the domains of epidemiology and intervention research. A primary focus for Dr. Wilkens at UHCC has been in the quantification of cancer incidence and mortality rates for the multiethnic populations of Hawaiʻi and the US affiliated Pacific, and studying the underlying causes of differences in cancer risks between ethnic groups. Genetic as well as lifestyle factors, including diet, physical activity, smoking and neighborhood environment, have been considered. Dr. Wilkens has published over 300 publications from these efforts.

Peter Washington, PhD

AI Expert, Mentor

I am an Assistant Professor in the Information & Computer Sciences department at the University of Hawaiʻi at Mānoa (UHM). Prior to joining UHM, I completed by PhD in Bioengineering at Stanford University, MS in Computer Science at Stanford University, and BA in Computer Science at Rice University. My research interests include developing data science methods to support machine learning for health and wellbeing, crowdsourcing for precision health, and precise digital interventions. I am interested in applying these methods to a variety of healthcare problems.

Advisory Board

Margaretta Colangelo

Co-founder & CEO Jthereum

Margaretta Colangelo is a native San Franciscan with over 30 years of experience working in the software industry in Silicon Valley. She has a deep and multifaceted understanding of business, science, and technology, and is highly adept at tracking and forecasting innovation in technology. Margaretta is Co-founder and CEO of Jthereum an enterprise Blockchain company and President of U1 Technologies. She was a core member of the team that developed the first Java based secure messaging software for stock trading platforms used by the world’s top multinational investment banks, and influenced important technical specifications and standards, including JDBC and JMS, that have helped advance the technology industry. She has published over 200 articles on AI and has spoken at AI conferences in the US, Singapore, Switzerland, Brazil, Mexico, Saudi Arabia, Oman, and Tanzania. 

Members & Students

Thomas Wolfgruber

Postdoc, Shepherd Research Lab

I am a post-doctoral researcher primarily studying mammography for risk detection using machine learning. As a data scientist and software engineer I support the general scientific and technological goals of the group. My experience ranges from co-authoring scientific papers published in peer-reviewed journals to more day-to-day tasks like server administration.

1.
Glaser Y. Deep-learning-derived all-cause mortality predictor significantly correlated with bone mineral density in males. Oral presented at: International Workshop on Quantitative Musculoskeletal Imaging; 2022 Jun 13; Noordwijk, Netherlands. Cite
1.
Glaser Y, Shepherd J, Leong L, Wolfgruber T, Lui LY, Sadowski P, et al. Deep learning predicts all-cause mortality from longitudinal total-body DXA imaging. Communications Medicine. 2022; Cite
1.
Glaser Y, Sadowski P, Wolfgruber T, Lui LY, Cummings S, Shepherd J. Hip Fracture Risk Modelling Using DXA and Artificial Intelligence. American Society for Bone Mineral and Research Annual Meeting; 2020 Sep 11; Virtual. Cite Download
1.
Leong LT, Malkov S, Drukker K, Niell BL, Sadowski P, Wolfgruber T, et al. Dual-energy three-compartment breast imaging for compositional biomarkers to improve detection of malignant lesions. Communications Medicine [Internet]. 2021 Aug 31;1(1):29. Cite Download

Lambert Leong

PhD Student, Shepherd Research Lab

I am a PhD student in the Molecular Bioscience and Bio-Engineering (MBBE) department at the University of Hawaii. I received my Masters in computer science where I focused on high performance computing and simulation. My Bachelors degree is in biology and I have three years of work experience in the bio-tech industry developing an artificial cornea for transplant. My work with the Shepherd Research Lab focuses on breast imagining and the use of machine learning and artificial intelligence for cancer risk analysis and detection. More information about me, my projects and works can be found at lambertleong.com.

1.
Bennett JP, Leong LT, Liu YE, Kelly NN, Glaser Y, Sadowski P, et al. Use of Artificial Intelligence Regional Hallucinations to Correct Body Composition Predictions in Individuals with Metal Implants and Poor Positioning. Oral Presentation presented at: International Workshop on Quantitative Musculoskeletal Imaging; 2022 Jun 13; Noordwijk, Netherlands.
1.
Glaser Y, Shepherd J, Leong L, Wolfgruber T, Lui LY, Sadowski P, et al. Deep learning predicts all-cause mortality from longitudinal total-body DXA imaging. Commun Med [Internet]. 2022 Aug 16;2. Download
1.
Glaser Y, Sehpherd J, Leong L, Wolfgruber T, Lui LY, Cummings SR. Deep-learning-derived all-cause mortality predictor significantly correlated with bone mineral density in males. Poster presented at: International Workshop on Quantitative Musculoskeletal Imaging; 2022 Jun 13; Noordwijk, Netherlands.
1.
Leong L. Modular artificial intelligence models for body composition research. Poster presented at: 2022 Biomedical Sciences & Health Disparities Symposium; 2022 Apr 7; Honolulu, HI. Download
1.
Leong L, Giger M, Drukker K, Kerlikowske K, Joe B, Greenwood H, et al. Three compartment breast machine learning model for improving computer-aided detection. In Leuven, Belgium: International Society for Optics and Photonics; 2020.
1.
Leong L, Wong M, Piazza M, Garry S, Heymsfield S, Shepherd J. Creating Accurate Representations of DXA Scans from 3D Optical Body Surface Scans for Arbitrary Regional Body Composition Analysis. In Lugano, Switzerland (Hybrid); 2021.
1.
Leong LT, Malkov S, Drukker K, Niell BL, Sadowski P, Wolfgruber T, et al. Dual-energy three-compartment breast imaging for compositional biomarkers to improve detection of malignant lesions. Communications Medicine [Internet]. 2021 Aug 31;1(1):29. Download
1.
Leong L, Wong MC, Liu YE, Kelly NN, Glaser Y, Sadowski P, et al. Artificial Intelligence Generates Real Analyzable Dual Energy X-ray Absorptiometry Scans from Three-Dimensional Body Scans. Oral Presentation presented at: International Workshop on Quantitative Musculoskeletal Imaging; 2022 Jun 13; Noordwijk, Netherlands.
1.
Leong LT, Wong MC, Glaser Y, Wolfgruber T, Heymsfield SB, Sadwoski P, et al. Quantitative Imaging Principles Improves Medical Image Learning. 2022 Jul 1; Download
1.
Wong MC, Leong LT, Glaser Y, Sadowski P, Cummings S, Shepherd JA. Artificial Intelligence Predicts Spine and Hip BMD from Whole-Body Dual Energy Xray Absorptiometry Scans. Oral Presentation presented at: International Workshop on Quantitative Musculoskeletal Imaging; 2022 Jun 13; Noordwijk, Netherlands.
1.
Zhu X, Wolfgruber TK, Leong L, Jensen M, Scott C, Winham S, et al. Deep Learning Predicts Interval and Screening-detected Cancer from Screening Mammograms: A Case-Case-Control Study in 6369 Women. Radiology [Internet]. 2021 Dec;301(3):550–8.

Yannik Glaser

MS Student, UH Manoa ICS

I am a Computer Science Master’s student at the UH ICS department, hoping to also earn my PhD there afterwards. I work at the UH Machine Learning Lab as a research assistant, applying machine learning techniques to various problems from different disciplines. I’m particularly passionate about deep learning algorithms and their application to the natural sciences. My work with the Cancer Center focuses on applying deep learning to medical image analysis.

1.
Bennett JP, Leong LT, Liu YE, Kelly NN, Glaser Y, Sadowski P, et al. Use of Artificial Intelligence Regional Hallucinations to Correct Body Composition Predictions in Individuals with Metal Implants and Poor Positioning. Oral Presentation presented at: International Workshop on Quantitative Musculoskeletal Imaging; 2022 Jun 13; Noordwijk, Netherlands.
1.
Glaser Y, Shepherd J, Leong L, Wolfgruber T, Lui LY, Sadowski P, et al. Deep learning predicts all-cause mortality from longitudinal total-body DXA imaging. Commun Med [Internet]. 2022 Aug 16;2. Download
1.
Glaser Y, Sehpherd J, Leong L, Wolfgruber T, Lui LY, Cummings SR. Deep-learning-derived all-cause mortality predictor significantly correlated with bone mineral density in males. Poster presented at: International Workshop on Quantitative Musculoskeletal Imaging; 2022 Jun 13; Noordwijk, Netherlands.
1.
Glaser Y, Sadowski P, Wolfgruber T, Lui LY, Cummings S, Shepherd J. Hip Fracture Risk Modelling Using DXA and Artificial Intelligence. Poster presented at: American Society for Bone Mineral and Research Annual Meeting; 2020 Sep 11; Virtual. Download
1.
Leong L. Modular artificial intelligence models for body composition research. Poster presented at: 2022 Biomedical Sciences & Health Disparities Symposium; 2022 Apr 7; Honolulu, HI. Download
1.
Leong L, Wong MC, Liu YE, Kelly NN, Glaser Y, Sadowski P, et al. Artificial Intelligence Generates Real Analyzable Dual Energy X-ray Absorptiometry Scans from Three-Dimensional Body Scans. Oral Presentation presented at: International Workshop on Quantitative Musculoskeletal Imaging; 2022 Jun 13; Noordwijk, Netherlands.
1.
Leong LT, Wong MC, Glaser Y, Wolfgruber T, Heymsfield SB, Sadwoski P, et al. Quantitative Imaging Principles Improves Medical Image Learning. 2022 Jul 1; Download
1.
Wong MC, Leong LT, Glaser Y, Sadowski P, Cummings S, Shepherd JA. Artificial Intelligence Predicts Spine and Hip BMD from Whole-Body Dual Energy Xray Absorptiometry Scans. Oral Presentation presented at: International Workshop on Quantitative Musculoskeletal Imaging; 2022 Jun 13; Noordwijk, Netherlands.

Headshot of Arianna Bunnell

Arianna Bunnell

PhD Student, UH Manoa ICS

I’m a PhD student in the Computer Science (ICS) department at the University of Hawai’i. I have Bachelors degrees in Statistics and Computer Science, and am passionate about the application of data science to healthcare. I currently work as a Research Assistant in the UH Machine Learning Lab, working in applied ML. My work with the Shepherd Research Lab focuses on applying deep learning to breast ultrasound imaging.

Alumni

Xun Zhu

Postdoc, Shepherd Research Lab

I’m a post-doctoral researcher currently focusing on designing Deep Learning solutions to biomedical imaging problems. My background is mathematics (B.S. and M.S.) and bioinformatics (Ph.D.). It is my passion to apply the quantitative skills I learned to improve technologies related to everybody’s life.

1.
Zhu X, Wolfgruber TK, Leong L, Jensen M, Scott C, Winham S, et al. Deep Learning Predicts Interval and Screening-detected Cancer from Screening Mammograms: A Case-Case-Control Study in 6369 Women. Radiology [Internet]. 2021 Dec;301(3):550–8. Cite

Shane Spencer

MS Student, UH Electrical Engineering Systems

I am an Electrical Engineering Systems Masters Student at UH Manoā. My skills include: programming, modeling, and analysis. My interests are embedded electronics, stocks, and skateboarding. Some of my projects include breast tomography and melanoma.

Michael Omori

MS Student, Shepherd Research Lab

I grew up in Seattle, WA in an amazing community of family and friends. I went to Lakeside High School, then did a bachelor’s of science in electrical engineering at the University of Washington and am currently pursuing a master’s degree in computer science in the Aloha state. I have worked as a software engineer and data scientist, most recently at Boeing. I am currently working in the Shepherd Research Lab on measuring body composition using machine learning and deep learning with novel imaging techniques for applications in space.

1.
Omori M. Simulating Microgravity Effects and Changes in Body Shape. Poster presented at: NASA Human Research Program Investigators’ Workshop; 2020 Jan 27; Galvenston, TX. Cite Download