Evaluation study demonstrates domain-adapted language models accurately predict Deauville scores from PET/CT reports, highlighting artificial intelligence utility in nuclear medicine.
Purpose: To evaluate the impact of domain adaptation on the performance of language models in predicting five-point Deauville scores on the basis of clinical fluorine 18 fluorodeoxyglucose PET/CT reports. Materials and Methods: testing. A physician given the task on a subset of the data had a five-class accuracy of 66%. Conclusion: .
No takes yet. Share an insight, caveat, or question.
Huemann et al. (2023) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: