Feature Disentanglement to Aid Imaging Biomarker Characterization for Genetic Mutations

Padmaja Jonnalagedda, Brent Weinberg, Jason Allen, Bir Bhanu
; Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:349-364, 2020.

Abstract

Various mutations have been shown to correlate with prognosis of High-Grade Glioma (Glioblastoma). Overall prognostic assessment requires analysis of multiple modalities: imaging, molecular and clinical. To optimize this assessment pipeline, this paper develops the first deep learning-based system that uses MRI data to predict 19/20 co-gain, a mutation that indicates median survival. It addresses two key challenges when dealing with deep learning algorithms and medical data: lack of data and high data imbalance. To tackle these challenges, we propose a unified approach that consists of a Feature Disentanglement based Generative Adversarial Network (FeaD-GAN) for generating synthetic images. FeaD-GAN projects disentangled features into a high dimensional space and re-samples them from a pseudo-large data distribution to generate synthetic images from very limited data. A thorough analysis is performed to (a) characterize aspects of visual manifestation of 19/20 co-gain to demonstrate the effectiveness of FeaD-GAN and (b) demonstrate that not only do the imaging biomarkers of 19/20 co-gain exist, but also that they are reproducible.

Cite this Paper


BibTeX
@InProceedings{pmlr-v121-jonnalagedda20a, title = {Feature Disentanglement to Aid Imaging Biomarker Characterization for Genetic Mutations}, author = {Jonnalagedda, Padmaja and Weinberg, Brent and Allen, Jason and Bhanu, Bir}, pages = {349--364}, year = {2020}, editor = {Tal Arbel and Ismail Ben Ayed and Marleen de Bruijne and Maxime Descoteaux and Herve Lombaert and Christopher Pal}, volume = {121}, series = {Proceedings of Machine Learning Research}, address = {Montreal, QC, Canada}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/jonnalagedda20a/jonnalagedda20a.pdf}, url = {http://proceedings.mlr.press/v121/jonnalagedda20a.html}, abstract = {Various mutations have been shown to correlate with prognosis of High-Grade Glioma (Glioblastoma). Overall prognostic assessment requires analysis of multiple modalities: imaging, molecular and clinical. To optimize this assessment pipeline, this paper develops the first deep learning-based system that uses MRI data to predict 19/20 co-gain, a mutation that indicates median survival. It addresses two key challenges when dealing with deep learning algorithms and medical data: lack of data and high data imbalance. To tackle these challenges, we propose a unified approach that consists of a Feature Disentanglement based Generative Adversarial Network (FeaD-GAN) for generating synthetic images. FeaD-GAN projects disentangled features into a high dimensional space and re-samples them from a pseudo-large data distribution to generate synthetic images from very limited data. A thorough analysis is performed to (a) characterize aspects of visual manifestation of 19/20 co-gain to demonstrate the effectiveness of FeaD-GAN and (b) demonstrate that not only do the imaging biomarkers of 19/20 co-gain exist, but also that they are reproducible.} }
Endnote
%0 Conference Paper %T Feature Disentanglement to Aid Imaging Biomarker Characterization for Genetic Mutations %A Padmaja Jonnalagedda %A Brent Weinberg %A Jason Allen %A Bir Bhanu %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-jonnalagedda20a %I PMLR %J Proceedings of Machine Learning Research %P 349--364 %U http://proceedings.mlr.press %V 121 %W PMLR %X Various mutations have been shown to correlate with prognosis of High-Grade Glioma (Glioblastoma). Overall prognostic assessment requires analysis of multiple modalities: imaging, molecular and clinical. To optimize this assessment pipeline, this paper develops the first deep learning-based system that uses MRI data to predict 19/20 co-gain, a mutation that indicates median survival. It addresses two key challenges when dealing with deep learning algorithms and medical data: lack of data and high data imbalance. To tackle these challenges, we propose a unified approach that consists of a Feature Disentanglement based Generative Adversarial Network (FeaD-GAN) for generating synthetic images. FeaD-GAN projects disentangled features into a high dimensional space and re-samples them from a pseudo-large data distribution to generate synthetic images from very limited data. A thorough analysis is performed to (a) characterize aspects of visual manifestation of 19/20 co-gain to demonstrate the effectiveness of FeaD-GAN and (b) demonstrate that not only do the imaging biomarkers of 19/20 co-gain exist, but also that they are reproducible.
APA
Jonnalagedda, P., Weinberg, B., Allen, J. & Bhanu, B.. (2020). Feature Disentanglement to Aid Imaging Biomarker Characterization for Genetic Mutations. Proceedings of the Third Conference on Medical Imaging with Deep Learning, in PMLR 121:349-364

Related Material