skip to main content

SciTech ConnectSciTech Connect

Title: Pattern Search in Multi-structure Data: A Framework for the Next-Generation Evidence-based Medicine

With the advent of personalized and evidence-based medicine, the need for a framework to analyze/interpret quantitative measurements (blood work, toxicology, etc.) with qualitative descriptions (specialist reports after reading images, bio-medical knowledge-bases) to predict diagnostic risks is fast emerging. Addressing this need, we pose and address the following questions (i) How can we jointly analyze both qualitative and quantitative data ? (ii) Is the fusion of multi-structure data expected to provide better insights than either of them individually ? We present experiments on two bio-medical data sets - mammography and traumatic brain studies to demonstrate architectures and tools for evidence-pattern search.
 [1] ;  [1]
  1. ORNL
Publication Date:
OSTI Identifier:
DOE Contract Number:
Resource Type:
Resource Relation:
Conference: SPIE Medical Imaging, San Diego, CA, USA, 20140215, 20140220
Research Org:
Oak Ridge National Laboratory (ORNL)
Sponsoring Org:
ORNL LDRD Seed-Money; ORNL LDRD Director's R&D
Country of Publication:
United States
data fusion; image understandings; pattern search; structured data; unstructured data