The SRL is an academic research group with extensive collaborations around the world. Below you will find links to our current studies led by Dr. Shepherd and the SRL. In addition, you will see a list of the studies where the SRL collaborates by providing services, measures, or expertise. Additional studies related to Quality Assurance can be found on our Quality Assurance page. For links to our publications and presentation, see Publications.
Shape Up! Studies
The purpose of the Shape Up! Study is to explore and develop ways to measure health and body composition from 2D and 3D images. These new technologies are developed to use shape information on the outside to predict measures of health on the inside, such as body fat percentage and lean muscle mass, which can then provide useful and detailed information about various health and wellness risks. Participants provide the data needed for researchers to continue this study, which will create the largest and most powerful description of optical body shape and its association and relation to body composition, metabolic markers, function, and dietary intake.
Also known as the Space-Feasible Body Composition and Body Shape Analysis for Long Duration Missions, in this project, we propose to monitor frailty risk using 3D optical scans with adjustment for fluid redistribution. 3DO models accurately estimate bone and body composition but lack space acclimation experience. We will perform studies to select hardware, algorithms, and augment models with microgravity analogs. We conclude with making a space-feasible prototype for microgravity testing during parabolic flights.
The TBDXAI Project
Also known as the Deep Learning and Total Body DXA Scans Project, in this project, we attempt to use deep learning methods on total body DXA scans to extract more information than was previously done, and thus, providing more accurate predictions of clinical outcomes, including cardiovascular disease (CVD), CVD death, overall mortality, cancer, cancer death, hip fracture, physical disability, incident insulin-resistant diabetes, and severity of insulin resistance.
The 3CB Lesion Detection Study
The full impacts of digital mammography and computer-aided diagnostic (CAD/QIA) systems on the performance of diagnostic mammography are yet to be realized. Lesion composition as described by its 3 compositional thicknesses of protein, lipid, and water (3CB) was recently discovered to be a strong descriptor of abnormal breast lesions. The long-term goal of this project is to determine if biological diagnostic measures of mammographic lesions can be used to improve current CADe algorithms in estimating the probability of breast cancer.
The Makawalu Study: Breast Cancer Screening in the Pacific using Portable Ultrasound
Advanced stage breast cancer (Stage III/IV) rates in the Pacific are much higher than in the US mainland, especially where mammography services do not exist or have low accessibility. Furthermore, Hawaii and Guam both have high insurance coverage and mammography access similar to the US mainland, so why does this problem still exist? In this study, we aim to identify cofactors (breast density, ethnicity, BMI, etc.) that impact the sensitivity and specificity for malignant breast cancer lesion detection on clinical ultrasound images with AI support for readers of varying backgrounds and experience and in areas where mammography is not available.
Hawaiʻi and Pacific Islands Mammography Registry
The Hawaii & Pacific Islands Mammography Registry (HIPIMR) database aims to maintain a computerized database of women undergoing breast imaging in the state of Hawai’i. It will include demographic, clinical and risk factor information, breast imaging interpretations, cancer outcomes, and vital status obtained through linkage with the Hawai’i Tumor Registry (HTR) and Hawaii State Department of Health and Vital Records (HSDHVR), respectively.
AI Precision Health Institute
Located at the University of Hawai’i Cancer Center in Honolulu, we use advanced technology including AI, machine learning, and deep learning to assess human health and predict the risk of disease.
Also known as the Systematic Melanoma Assessment and Risk Triaging Study, SMART is a prospective pilot feasibility study testing the preliminary effectiveness of a Digital Learning Computer Vision (DLCV) platform to distinguish melanomas from this scored set of biopsy-confirmed images. Our goal is to establish a DLCV method to triage lesions appropriate for biopsy; while providing a platform for increased vigilance of benign lesions.
DaKine Body Composition Study
In this study, we investigate how to isolate hydration status from lean mass measures in multiple methods of body composition. We will also focus on how to account for factors such as skin temperature, skin moisture, differences of intracellular water (ICW) and extracellular water ECW), and skin pad placements.
The Accessible Breast Cancer Screening in the Pacific Study
In this pre-pilot study, we propose to evaluate the effectiveness of the iBreastExam (iBE) as an early detection tool among women of Pacific Islander ancestry. We would also test the acceptance of the technology with an interview of the participants. With the completion of this pilot, we would gain a preliminary understanding of the strengths and limitations of this device and the acceptance of the device in the community.
Accessible Breast Cancer Screening in the Pacific
IMPAACT 2009: Pharmacokinetics, Feasibility, Acceptability, and Safety of Oral Pre-Exposure Prophylaxis for Primary HIV Prevention during Pregnancy and Postpartum in Adolescents and Young Women and their Infants
IMPAACT 2010: Phase III Study of the Virologic Efficacy and Safety of Dolutegravir-Containing versus Efavirenz-Containing Antiretroviral Therapy Regimens in HIV-1-Infected Pregnant Women and their Infants