Automated Spinal MRI Labelling from Reports Using a Large Language Model

Abstract

We propose a general pipeline to automate the extraction of labels from radiology reports using large language models, which we validate on spinal MRI reports. The efficacy of our labelling method is measured on five distinct conditions: spinal cancer, stenosis, spondylolisthesis, cauda equina compression and herniation. Using open-source models, our method equals or surpasses GPT-4 on a held-out set of reports. Furthermore, we show that the extracted labels can be used to train imaging models to classify the identified conditions in the accompanying MR scans. All classifiers trained using automated labels achieve comparable performance to models trained using scans manually annotated by clinicians. Code can be found at https://github.com/robinyjpark/AutoLabelClassifier.

Accepted to Medical Image Computing and Computer Assisted Intervention (MICCAI 2024, Spotlight). 11 pages plus appendix

References in corpus (6)

• BioBERT: a pre-trained biomedical language representation model for biomedical text mining
• Training language models to follow instructions with human feedback
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining
• Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing
• Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine