Radiomics Analysis Using Stability Selection Supervised Principal Component Analysis for Right-Censored Survival Data

• Activity Number: 297 - SPEED: Food, Environment, Biomedical Imaging and Physical System Visualization/Learning, Part 1
• Type: Contributed
• Date/Time: Tuesday, July 30, 2019 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistics in Imaging
• Author(s): Kang Yan* and Xiaofei Wang and Wendy Lam and Varut Vardhanabhuti and Anne W.M. Lee and Herbert Pang
• Companies: School of Public Health, Li Ka Shing Faculty of Medicine,The University of Hong Kong and Duke University School of Medicine and School of Public Health, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Ho and Li Ka Shing Faculty of Medicine, The University of Hon and The University of Hong and School of Public Health, Li Ka Shing Faculty of Medicine, The University of Hong Kong
• Keywords: Data Mining; Dimensionality Reduction; Machine Learning; Probabilistic and Statistical Methods; Radiomics

Abstract

Radiomics is a newly emerging field that provides a noninvasive approach for personalized therapy decision by identifying distinctive imaging features for predicting prognosis and therapeutic response. So far, many of the published radiomics studies utilize existing algorithms to identify the prognostic markers from biomedical images that are not specific to radiomics data. To better utilize biomedical image, we propose a novel machine learning approach, stability selection supervised principal component analysis (SSSuperPCA) that identifies stable features from radiomics big data coupled with dimension reduction for right censored survival outcomes. The proposed approach allows us to identify a set of stable features that are highly associated with the survival outcomes, control the per-family error rate, and predict the survival in a simple yet meaningful manner. We evaluate the performance of SSSuperPCA using simulations and real data sets for non-small cell lung cancer and head and neck cancer, and compare it with other machine learning algorithms. The results demonstrate that our method has a competitive edge over other existing methods for right-censored survival outcomes.