Pretraining using masked language modeling improves label noise robustness on the metadata standardization task

Motivation: The lack of standardization in MRI metadata increases radiologist workload. Goal(s): To demonstrate an approach to standardize the image contrast and the body part examined information in the DICOM header and to understand the benefits of self-supervised pretraining on the metadata standardization task in the presence of label noise. Approach: Masked language modeling was used for pretraining. At the fine-tuning stage, a transformer model was used to predict the image contrast and body part from both the text and numerical DICOM tags. Results: Pretraining improves robustness to label noise, with there being no loss in performance at 20% label noise. Impact: Pretraining using masked language modeling is effective at rendering a metadata stanardization system robust to label noise. Such a system can be used to standardize MRI metadata and therefore reduce radiologist workload. Future work should investigate class conditional label noise.