Multimodal fusion of imaging and genomics for lung cancer recurrence prediction

Lung cancer has a high rate of recurrence in early-stage patients. Predicting the post-surgical recurrence in lung cancer patients has traditionally been approached using single modality information of genomics or radiology images. We investigate the potential of multimodal fusion for this task. By...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-02
Main Authors: Subramanian, Vaishnavi, Do, Minh N, Syeda-Mahmood, Tanveer
Format: Article
Language:English
Subjects:
Computed tomography
Datasets
Genomics
Health risk assessment
Lung cancer
Medical imaging
Multilayers
Neural networks
Performance enhancement
Predictions
Radiology
Regularization
Statistical models
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Lung cancer has a high rate of recurrence in early-stage patients. Predicting the post-surgical recurrence in lung cancer patients has traditionally been approached using single modality information of genomics or radiology images. We investigate the potential of multimodal fusion for this task. By combining computed tomography (CT) images and genomics, we demonstrate improved prediction of recurrence using linear Cox proportional hazards models with elastic net regularization. We work on a recent non-small cell lung cancer (NSCLC) radiogenomics dataset of 130 patients and observe an increase in concordance-index values of up to 10%. Employing non-linear methods from the neural network literature, such as multi-layer perceptrons and visual-question answering fusion modules, did not improve performance consistently. This indicates the need for larger multimodal datasets and fusion techniques better adapted to this biological setting.
ISSN:2331-8422