Year: 2020
Type: conference-paper
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. 1
Authors: Justin Lovelace, Bobak Mortazavi
Institutions: Carnegie Mellon University, Texas A&M University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W3104371371
