Innovation in bridging computational imaging science and cancer research

Shepherd Research Lab is led by Dr. John A. Shepherd at the University of Hawai‘i Cancer Center. Our studies include research into breast cancer detection using breast density, predicting health risks through body assessments, and utilizing deep learning for AI-assisted diagnosis.

LATEST NEWS

Loading RSS Feed

Aloha!

At SRL, we are a group of research scientists innovating the ways that we detect cancer and metabolic risk. Along with how this benefits all areas of health, we are especially proud of the benefits that our studies can bring to our local community on O‘ahu.

RESEARCH & INNOVATION

Our work includes a number of active human studies and technology development projects.

predicting breast cancer risk from breast density and tissue thickness
using body analysis and imaging technology to predict metabolic health status and disease risk
utilizing deep learning to improve AI-assisted diagnosis
Latest publications
1.
Merritt MA, Lim U, Lampe JW, Kaenkumchorn T, Boushey CJ, Wilkens LR, et al. Dietary intake and visceral adiposity in older adults: The Multiethnic Cohort Adiposity Phenotype study. Obesity Science & Practice [Internet]. 2024 Feb 1 [cited 2024 Feb 21];10(1):e734. Cite
1.
Leong LT, Wong MC, Liu YE, Glaser Y, Quon BK, Kelly NN, et al. Generative deep learning furthers the understanding of local distributions of fat and muscle on body shape and health using 3D surface scans. Communications Medicine [Internet]. 2024 Jan 30;4(1):13. Cite
1.
Bradfield JP, Kember RL, Ulrich A, Balkiyarova Z, Alyass A, Aris IM, et al. Trans-ancestral genome-wide association study of longitudinal pubertal height growth and shared heritability with adult health outcomes. Genome Biology [Internet]. 2024 Jan 16;25(1):22. Cite

FEATURED RESEARCH

A brief look at one of our ongoing projects.

Fig. 3: Graphs showing improved performance on unseen test set when adding 3CB compositional information.

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.

Fig. 3: Improved performance on unseen test set when adding 3CB compositional information.

a Adding three-compartment breast (3CB) features to computer-aided detection (CAD) (orange) results in an area under the receiver operating characteristic (ROC) curve (AUC) of 0.81, standard deviation (SD) of 0.03, when compared to CAD alone (blue), AUC of 0.69, SD of 0.04. Mean curves (solid lines) and 95% confidence intervals (shaded regions) were computed via 1000 bootstrap samples. 

b The integrated sensitivity (IS), black shaded region between solid and dashed lines, indicates the change in sensitivity with the addition of 3CB. The integrated 1-specificity (IP), red shaded region between solid and dashed lines, indicates the change in specificity with the addition of 3CB. The integrated discrimination improvement (IDI) is the sum of the IS and IP (−1.06 + 13.17) which is 12.11 and a positive IDI indicates that predictive models benefit from the addition of 3CB. The borders of the Breast Imaging-Reporting and Data System (BI-RADS) assessment categories are indicated by the vertical dashed lines. Net reclassification improvement (NRI) for events or cancers (black) and non-events or benigns (red) are calculated at each BI-RADS border to demonstrate 3CBs effect on specificity with respect to each BI-RADS category.

Related News

Loading RSS Feed

Latest Publications

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
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. Cite
1.
Hinton B, Ma L, Mahmoudzadeh AP, Malkov S, Fan B, Greenwood H, et al. Derived mammographic masking measures based on simulated lesions predict the risk of interval cancer after controlling for known risk factors: a case-case analysis. Med Phys [Internet]. 2019 Mar;46(3):1309–16. Cite Download
1.
Drukker K, Giger ML, Joe BN, Kerlikowske K, Greenwood H, Drukteinis JS, et al. Combined Benefit of Quantitative Three-Compartment Breast Image Analysis and Mammography Radiomics in the Classification of Breast Masses in a Clinical Data Set. Radiology [Internet]. 2019;290(3):621–8. Cite

Contact us