Automated Labelling using an Attention model for Radiology reports of MRI scans (ALARM)

TL;DR

This paper introduces a transformer-based model that automates labeling MRI scans by classifying radiology reports, achieving expert-level accuracy and facilitating large dataset annotation for deep learning in medical imaging.

Contribution

The study presents a novel transformer-based approach for MRI report classification that automates dataset labeling, outperforming expert physicians and enabling scalable data annotation.

Findings

Model performance comparable to expert radiologists

Automates labeling process for large MRI datasets

Code made publicly available for research use

Abstract

Labelling large datasets for training high-capacity neural networks is a major obstacle to the development of deep learning-based medical imaging applications. Here we present a transformer-based network for magnetic resonance imaging (MRI) radiology report classification which automates this task by assigning image labels on the basis of free-text expert radiology reports. Our model's performance is comparable to that of an expert radiologist, and better than that of an expert physician, demonstrating the feasibility of this approach. We make code available online for researchers to label their own MRI datasets for medical imaging applications.