The natural language processing of radiology requests and reports of chest imaging: Comparing five transformer models' multilabel classification and a proof-of-concept study.

BACKGROUND: Radiology requests and reports contain valuable information about diagnostic findings and indications, and transformer-based language models are promising for more accurate text classification. METHODS: In a retrospective study, 2256 radiologist-annotated radiology requests (8 classes) and reports (10 classes) were divided into training and testing datasets (90% and 10%, respectively) and used to train 32 models. Performance metrics were compared by model type (LSTM, Bertje, RobBERT, BERT-clinical, BERT-multilingual, BERT-base), text length, data prevalence, and training strategy. The best models were used to predict the remaining 40,873 cases' categories of the datasets of requests and reports. RESULTS: The RobBERT model performed the best after 4000 training iterations, resulting in AUC values ranging from 0.808 [95% CI (0.757-0.859)] to 0.976 [95% CI (0.956-0.996)] for the requests and 0.746 [95% CI (0.689-0.802)] to 1.0 [95% CI (1.0-1.0)] for the reports. The AUC for the classification of normal reports was 0.95 [95% CI (0.922-0.979)]. The predicted data demonstrated variability of both diagnostic yield for various request classes and request patterns related to COVID-19 hospital admission data. CONCLUSION: Transformer-based natural language processing is feasible for the multilabel classification of chest imaging request and report items. Diagnostic yield varies with the information in the requests.

Diagnostic reliability of low dose multidetector CT and cone beam CT in maxillofacial trauma-an experimental blinded and randomized study.

OBJECTIVES: To assess the diagnostic reliability of low dose multidetector CT (MDCT) and cone beam CT (CBCT) for zygomaticomaxillary fracture diagnosis. METHODS: Unilateral zygomaticomaxillary fractures were inflicted on four out of six fresh frozen human cadaver head specimens. All specimens were scanned using four MDCT and two CBCT imaging protocols of which the radiation exposure was systematically reduced. A blinded diagnostic routine was simulated at which 16 radiologists and 8 oral and maxillofacial (OMF) surgeons performed randomized image assessments. We considered the findings during an open operative approach of the zygomatic region as the gold standard. RESULTS: Zygomaticomaxillary fractures were correctly diagnosed in 90.3% (n = 130) of the image assessments. The zygomatic arch was most often correctly diagnosed (91.0%). The zygomatic alveolar crest showed the lowest degree of correct diagnosis (65.3%). Dose reduction did not significantly affect the objective visualization of fractures of the zygomaticomaxillary complex. The sensitivity and specificity also remained consistent among the low dose scan protocols. Dose reduction did not decrease the ability to assess dislocation, comminution, orbital volume, volume rendering and soft tissues. OMF surgeons considered the low dose protocols sufficient for treatment planning. CONCLUSIONS: Dose reduction did not decrease the diagnostic reliability of MDCT and CBCT for the diagnosis of zygomaticomaxillary fractures.