Automated Protocol Suggestions for Cranial MRI Examinations Using Locally Fine-tuned BERT Models

TL;DR

This paper explores using BERT-based language models to automatically suggest MRI protocols based on patient referrals, aiming to improve efficiency and accuracy in radiology.

Contribution

The study introduces locally fine-tuned BERT models for automated cranial MRI protocol selection, showing improved performance with limited data.

Findings

The medBERT.de model with local fine-tuning achieved 81% protocol prediction accuracy.

Local language fine-tuning improved performance across all tested BERT-based models.

BERT-based models show potential for streamlining radiological protocol selection in clinical settings.

Abstract

Selection of appropriate imaging sequences protocols for cranial magnetic resonance imaging (MRI) is crucial to address the medical question and adequately support patient care. Inappropriate protocol selection can compromise diagnostic accuracy, extend scan duration, and increase the risk of misdiagnosis. Typically, radiologists determine scanning protocols based on their expertise, a process that can be time-consuming and subject to variability. Language models offer the potential to streamline this process. This study investigates the capability of bidirectional encoder representations from transformers (BERT)-based models to suggest appropriate MRI protocols based on referral information.

A total of 410 anonymized electronic referrals for cranial MRI from a local order-entry system were categorized into nine protocol classes by an experienced neuroradiologist. A locally hosted instance of four different, pre-trained BERT-based classifiers (BERT, ModernBERT, GottBERT, and medBERT.de) were trained to classify protocols based on referral entries, including preliminary diagnoses, prior treatment history, and clinical questions. Each model was additionally fine-tuned for local language on a large dataset of electronic referrals.

The model based on medBERT.de with local language fine-tuning was the best-performing model and correctly predicted 81% of all protocols, achieving a macro-F1 score of 0.71, macro-precision and macro-recall values of 0.73 and 0.71, respectively. Moreover, we were able to show that local language fine-tuning led to performance improvements across all models.

These results demonstrate the potential of language models to predict MRI protocols, even with limited training data. This approach could accelerate and standardize radiological protocol selection, offering significant benefits for clinical workflows.

Figures