Learning to Generate Clinically Coherent Chest X-Ray Reports

Justin Lovelace, Bobak Mortazavi

3rd Clinical Natural Language Processing Workshop (Clinical NLP 2020) Workshop Paper

You can open the pre-recorded video in a separate window.

Abstract: Automated radiology report generation has the potential to reduce the time clinicians spend manually reviewing radiographs and streamline clinical care. However, past work has shown that typical abstractive methods tend to produce fluent, but clinically incorrect radiology reports. In this work, we develop a radiology report generation model utilizing the transformer architecture that produces superior reports as measured by both standard language generation and clinical coherence metrics compared to competitive baselines. We then develop a method to differentiably extract clinical information from generated reports and utilize this differentiability to fine-tune our model to produce more clinically coherent reports.
NOTE: Video may display a random order of authors. Correct author list is at the top of this page.