A Fusion NLP Model for the Inference of Standardized Thyroid Nodule Malignancy Scores from Radiology Report Text.
Thiago Santos, Omar N. Kallas, Janice M. Newsome, Daniel L. Rubin, Judy Wawira Gichoya, Imon Banerjee · PubMed · 2021
Radiology reports are a rich resource for advancing deep learning applications for medical images, facilitating the generation of large-scale annotated image databases. Although the ambiguity and subtlety of natural language poses a significant challenge to information extraction from radiology reports. Thyroid Imaging Reporting and Data Systems (TI-RADS) has been proposed as a system to standardize ultrasound imaging reports for thyroid cancer screening and diagnosis, through the implementation of structured templates and a standardized thyroid nodule malignancy risk scoring system; however there remains significant variation in radiologist practice when it comes to diagnostic thyroid ultrasound interpretation and reporting. In this work, we propose a computerized approach using a contextual embedding and fusion strategy for the large-scale inference of TI-RADS final assessment categories from narrative ultrasound (US) reports. The proposed model has achieved high accuracy on an internal data set, and high performance scores on an external validation dataset.