G-MIND: An End-to-End Multimodal Imaging-Genetics Framework for Biomarker Identification and Disease Classification

TL;DR

G-MIND is a deep learning framework that integrates imaging and genetics data to identify biomarkers and classify diseases, demonstrating improved accuracy and interpretability in schizophrenia studies.

Contribution

The paper introduces a novel end-to-end multimodal neural network with a learnable dropout for interpretable biomarker extraction and handling missing data modalities.

Findings

Achieves better classification accuracy than baseline methods.

Generalizes well across different datasets.

Identifies biomarkers linked to schizophrenia deficits.

Abstract

We propose a novel deep neural network architecture to integrate imaging and genetics data, as guided by diagnosis, that provides interpretable biomarkers. Our model consists of an encoder, a decoder and a classifier. The encoder learns a non-linear subspace shared between the input data modalities. The classifier and the decoder act as regularizers to ensure that the low-dimensional encoding captures predictive differences between patients and controls. We use a learnable dropout layer to extract interpretable biomarkers from the data, and our unique training strategy can easily accommodate missing data modalities across subjects. We have evaluated our model on a population study of schizophrenia that includes two functional MRI (fMRI) paradigms and Single Nucleotide Polymorphism (SNP) data. Using 10-fold cross validation, we demonstrate that our model achieves better classification accuracy than baseline methods, and that this performance generalizes to a second dataset collected at a different site. In an exploratory analysis we further show that the biomarkers identified by our model are closely associated with the well-documented deficits in schizophrenia.