Automated Spinal MRI Labelling from Reports Using a Large Language Model
This work addresses the need for efficient and accurate medical data labeling in radiology, though it is incremental as it applies existing LLM techniques to a specific domain.
The authors tackled the problem of automating label extraction from radiology reports using large language models, specifically validating on spinal MRI reports, and achieved performance equal to or better than GPT-4 on a held-out set while enabling trained imaging models to match clinician-annotated performance.
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.