Domain-adapted large language models for classifying nuclear medicine reports

by   Zachary Huemann, et al.

With the growing use of transformer-based language models in medicine, it is unclear how well these models generalize to nuclear medicine which has domain-specific vocabulary and unique reporting styles. In this study, we evaluated the value of domain adaptation in nuclear medicine by adapting language models for the purpose of 5-point Deauville score prediction based on clinical 18F-fluorodeoxyglucose (FDG) PET/CT reports. We retrospectively retrieved 4542 text reports and 1664 images for FDG PET/CT lymphoma exams from 2008-2018 in our clinical imaging database. Deauville scores were removed from the reports and then the remaining text in the reports was used as the model input. Multiple general-purpose transformer language models were used to classify the reports into Deauville scores 1-5. We then adapted the models to the nuclear medicine domain using masked language modeling and assessed its impact on classification performance. The language models were compared against vision models, a multimodal vision language model, and a nuclear medicine physician with seven-fold Monte Carlo cross validation, reported are the mean and standard deviations. Domain adaption improved all language models. For example, BERT improved from 61.3 adaptation. The best performing model (domain-adapted RoBERTa) achieved a five-class accuracy of 77.4 (66 multimodal model's performance (77.2). Domain adaptation improved the performance of large language models in interpreting nuclear medicine text reports.


page 2

page 4

page 5

page 6


Automatic Personalized Impression Generation for PET Reports Using Large Language Models

Purpose: To determine if fine-tuned large language models (LLMs) can gen...

JuriBERT: A Masked-Language Model Adaptation for French Legal Text

Language models have proven to be very useful when adapted to specific d...

Linguistically Informed Masking for Representation Learning in the Patent Domain

Domain-specific contextualized language models have demonstrated substan...

Clinical Text Summarization: Adapting Large Language Models Can Outperform Human Experts

Sifting through vast textual data and summarizing key information impose...

Compartmental analysis of dynamic nuclear medicine data: regularization procedure and application to physiology

Compartmental models based on tracer mass balance are extensively used i...

ChatGPT Makes Medicine Easy to Swallow: An Exploratory Case Study on Simplified Radiology Reports

The release of ChatGPT, a language model capable of generating text that...

Please sign up or login with your details

Forgot password? Click here to reset