Radiology Artificial Intelligence · 2022 · 34 citations · 19 references
ComputingBiomedical InformaticsHealth InformaticsClinical EngineeringClinical InformaticsElectronic Health RecordsMedical Device ClassificationModel EvaluationCross-validationCross-validation StudiesData AnnotationPredictive Model ValidationSwan-ganz CatheterizationTraining Transfer EvaluationTransformer ModelsTransformer-based Prediction Models
Purpose: To develop and evaluate domain-specific and pretrained bidirectional encoder representations from transformers (BERT) models in a transfer learning task on varying training dataset sizes to annotate a larger overall dataset. Materials and Methods: The authors retrospectively reviewed 69 095 anonymized adult chest radiograph reports (reports dated April 2020-March 2021). From the overall cohort, 1004 reports were randomly selected and labeled for the presence or absence of each of the following devices: endotracheal tube (ETT), enterogastric tube (NGT, or Dobhoff tube), central venous catheter (CVC), and Swan-Ganz catheter (SGC). Pretrained transformer models (BERT, PubMedBERT, DistilBERT, RoBERTa, and DeBERTa) were trained, validated, and tested on 60%, 20%, and 20%, respectively, of these reports through fivefold cross-validation. Additional training involved varying dataset sizes with 5%, 10%, 15%, 20%, and 40% of the 1004 reports. The best-performing epochs were used to assess area under the receiver operating characteristic curve (AUC) and determine run time on the overall dataset. Results: The highest average AUCs from fivefold cross-validation were 0.996 for ETT (RoBERTa), 0.994 for NGT (RoBERTa), 0.991 for CVC (PubMedBERT), and 0.98 for SGC (PubMedBERT). DeBERTa demonstrated the highest AUC for each support device trained on 5% of the training set. PubMedBERT showed a higher AUC with a decreasing training set size compared with BERT. Training and validation time was shortest for DistilBERT at 3 minutes 39 seconds on the annotated cohort. Conclusion: . ©RSNA, 2022See also the commentary by Zech in this issue.
19
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Adam Paszke, Sam Gross, Francisco Massa et al. · arXiv (Cornell University) · 2019 · 16.2K citations · Full text
Preparing Medical Imaging Data for Machine Learning
Martin J. Willemink, Wojciech A. Koszek, Cailin Hardell et al. · Radiology · 2020 · 976 citations · Full text
Deep Learning to Classify Radiology Free-Text Reports
Matthew C. Chen, Robyn L. Ball, Lingyao Yang et al. · Radiology · 2017 · 223 citations