Labelling imaging datasets on the basis of neuroradiology reports: a validation study
This work addresses the need for reliable automated labeling in medical imaging for researchers, though it is incremental as it validates existing approaches rather than introducing new methods.
The study tackled the problem of validating natural language processing for labeling neuroradiology MRI datasets from reports, finding that binary labeling (normal vs. abnormal) is highly accurate, but granular labeling accuracy varies by category, and non-specialist labeling reduces downstream model performance.
Natural language processing (NLP) shows promise as a means to automate the labelling of hospital-scale neuroradiology magnetic resonance imaging (MRI) datasets for computer vision applications. To date, however, there has been no thorough investigation into the validity of this approach, including determining the accuracy of report labels compared to image labels as well as examining the performance of non-specialist labellers. In this work, we draw on the experience of a team of neuroradiologists who labelled over 5000 MRI neuroradiology reports as part of a project to build a dedicated deep learning-based neuroradiology report classifier. We show that, in our experience, assigning binary labels (i.e. normal vs abnormal) to images from reports alone is highly accurate. In contrast to the binary labels, however, the accuracy of more granular labelling is dependent on the category, and we highlight reasons for this discrepancy. We also show that downstream model performance is reduced when labelling of training reports is performed by a non-specialist. To allow other researchers to accelerate their research, we make our refined abnormality definitions and labelling rules available, as well as our easy-to-use radiology report labelling app which helps streamline this process.