Program Information

Challenges in Radiomics and Big Data

K Drukker¹*, (1) University Chicago, Chicago , IL

Presentations

8:30 AM : Challenges in Radiomics and Big Data - K Drukker, Presenting Author

TU-B-207B-0 (Tuesday, August 2, 2016) 8:30 AM - 9:30 AM Room: 207B

The general learning objectives are to get a better understanding of
• The pitfalls along the radiomics/radiogenomics (imaging genomics) pipeline
• The crucial role of statistics in the design and evaluation of radiomics/radiogenomics phenotypes and systems
• The special challenges associated with big data

1. Introduction
a.Basic statistical concepts
b.Association, correlation, and causality
c.Know when your numbers are significant

2. Reproducibility
a.Replication studies
i.The extent of the problem
ii.Curse of dimensionality, overfitting, multiple hypothesis testing
iii.Sample size, P-value variability

3. “Big Data”
a.“Big data” vs. “medium data” vs. “small data”
b.Training and testing data sets
c.Harmonization

Funding Support, Disclosures, and Conflict of Interest: KD receives royalties from Hologic

Handouts

115-31985-387514-119648.pdf (K Drukker)

Contact Email: