Text to brain: predicting the spatial distribution of neuroimaging observations from text reports

TL;DR

This paper introduces a method to extract and predict the spatial distribution of brain regions from medical text reports, leveraging a novel risk minimization approach to improve accuracy in unseen documents.

Contribution

It presents a new distribution learning framework that models anatomical terms from text to brain spatial mappings, outperforming traditional methods.

Findings

Semantic variation affects model accuracy

Voxel-wise parameterization improves location prediction

Least-deviation cost outperforms least-square

Abstract

Despite the digital nature of magnetic resonance imaging, the resulting observations are most frequently reported and stored in text documents. There is a trove of information untapped in medical health records, case reports, and medical publications. In this paper, we propose to mine brain medical publications to learn the spatial distribution associated with anatomical terms. The problem is formulated in terms of minimization of a risk on distributions which leads to a least-deviation cost function. An efficient algorithm in the dual then learns the mapping from documents to brain structures. Empirical results using coordinates extracted from the brain-imaging literature show that i) models must adapt to semantic variation in the terms used to describe a given anatomical structure, ii) voxel-wise parameterization leads to higher likelihood of locations reported in unseen documents, iii) least-deviation cost outperforms least-square. As a proof of concept for our method, we use our model of spatial distributions to predict the distribution of specific neurological conditions from text-only reports.