Surgical Planning Laboratory - Brigham & Women's Hospital - Boston, Massachusetts USA - a teaching affiliate of Harvard Medical School

Surgical Planning Laboratory

The Publication Database hosted by SPL

All Publications | Upload | Advanced Search | Gallery View | Download Statistics | Help | Import | Log in

Generative Method to Discover Genetically Driven Image Biomarkers

1Surgical Planning Laboratory, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA.
2Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA.
IPMI 2015
Publication Date:
Inf Process Med Imaging
Volume Number:
Inf Process Med Imaging. 2015 Jun;24:30-42.
PubMed ID:
Appears in Collections:
R25 CA089017/CA/NCI NIH HHS/United States
K25 HL104085/HL/NHLBI NIH HHS/United States
R01 HL116473/HL/NHLBI NIH HHS/United States
R01 HL116931/HL/NHLBI NIH HHS/United States
K08 HL097029/HL/NHLBI NIH HHS/United States
P41 EB015902/EB/NIBIB NIH HHS/United States
P41 RR013218/RR/NCRR NIH HHS/United States
R01 HL089856/HL/NHLBI NIH HHS/United States
R01 HL089897/HL/NHLBI NIH HHS/United States
R01 HL113264/HL/NHLBI NIH HHS/United States
U54 EB005149/EB/NIBIB NIH HHS/United States
Generated Citation:
Batmanghelich K.N., Saeedi A., Cho M., San Jose Estepar R., Golland P. Generative Method to Discover Genetically Driven Image Biomarkers. Inf Process Med Imaging. 2015 Jun;24:30-42. PMID: 26221665. PMCID: PMC4527679.
Downloaded: 779 times. [view map]
Paper: Download, View online
Export citation:
Google Scholar: link

We present a generative probabilistic approach to discovery of disease subtypes determined by the genetic variants. In many diseases, multiple types of pathology may present simultaneously in a patient, making quantification of the disease challenging. Our method seeks common co-occurring image and genetic patterns in a population as a way to model these two different data types jointly. We assume that each patient is a mixture of multiple disease subtypes and use the joint generative model of image and genetic markers to identify disease subtypes guided by known genetic influences. Our model is based on a variant of the so-called topic models that uncover the latent structure in a collection of data. We derive an efficient variational inference algorithm to extract patterns of co-occurrence and to quantify the presence of heterogeneous disease processes in each patient. We evaluate the method on simulated data and illustrate its use in the context of Chronic Obstructive Pulmonary Disease (COPD) to characterize the relationship between image and genetic signatures of COPD subtypes in a large patient cohort.

Additional Material
1 File (19.223kB)
Batmanghelich-IPMI2015-fig3.jpg (19.223kB)