BACKGROUND AND PURPOSE: Communication gaps exist between radiologists and referring physicians in conveying diagnostic certainty. We aimed to explore deep learning-based bidirectional contextual language models for automatically assessing diagnostic certainty expressed in the radiology reports to facilitate the precision of communication. MATERIALS AND METHODS: We randomly sampled 594 head MR imaging reports from an academic medical center. We asked 3 board-certified radiologists to read sentences from the Impression section and assign each sentence 1 of the 4 certainty categories: "Non-Definitive," "Definitive-Mild," "Definitive-Strong," "Other." Using the annotated 2352 sentences, we developed and validated a natural language-processing system based on the start-of-the-art bidirectional encoder representations from transformers (BERT), which can capture contextual uncertainty semantics beyond the lexicon level. Finally, we evaluated 3 BERT variant models and reported standard metrics including sensitivity, specificity, and area under the curve. RESULTS: A kappa score of 0.74 was achieved for interannotator agreement on uncertainty interpretations among 3 radiologists. For the 3 BERT variant models, the biomedical variant (BioBERT) achieved the best macro-average area under the curve of 0.931 (compared with 0.928 for the BERT-base and 0.925 for the clinical variant [ClinicalBERT]) on the validation data. All 3 models yielded high macro-average specificity (93.13%-93.65%), while the BERT-base obtained the highest macro-average sensitivity of 79.46% (compared with 79.08% for BioBERT and 78.52% for ClinicalBERT). The BioBERT model showed great generalizability on the heldout test data with a macro-average sensitivity of 77.29%, specificity of 92.89%, and area under the curve of 0.93. CONCLUSIONS: A deep transfer learning model can be developed to reliably assess the level of uncertainty communicated in a radiology report.

Multidisciplinary conferences (MDCs) play a major role in management and care of oncology patients. Hepatocellular carcinoma (HCC) is a complex disease benefiting from multidisciplinary discussions to determine optimal patient management. A multitude of liver-directed locoregional therapies have emerged allowing for more options for treatment of HCC. A radiologist dedicated to HCC-MDC is an important member of the team contributing to patient care in multiple ways. The radiologist plays a key role in image interpretation guiding initial therapy discussions as well as interpreting post-treatment imaging following liver-directed therapy. Standardization of image interpretation can lead to more consistent treatment received by the patient as well as accurate assessment of transplant eligibility. The radiologist can facilitate this process using structured reporting that is also supported by stakeholders involved in interdisciplinary management of liver diseases. The Liver Imaging Reporting and Data System (LI-RADS), is a living document which offers a standardized reporting algorithm for consistent communication of radiologic findings for HCC screening and characterization of liver observations in patients at risk for HCC. The LI-RADS post-treatment algorithm (LR-TR algorithm) has been developed to standardize liver observations following liver-directed locoregional therapy. This review article focuses on the role of the radiologist at HCC-MDC and implementation of the LR-TR algorithm for improving workflow.