Pragmatic Radiology Report Generation
This work addresses the challenge of generating more accurate and context-aware radiology reports for radiologists and patients, though it is incremental as it builds on existing report generation methods by adding pragmatic elements.
The paper tackled the problem of generating radiology reports that incorporate pragmatic intents, such as including negative observations based on patient indications, and introduced a framework to reduce hallucinations by cleaning groundtruth reports. The result showed that pragmatic models outperformed existing methods, with improvements of +4.3 in Negative F1, +6.3 in Positive F1, and +11.0 in BLEU-2.
When pneumonia is not found on a chest X-ray, should the report describe this negative observation or omit it? We argue that this question cannot be answered from the X-ray alone and requires a pragmatic perspective, which captures the communicative goal that radiology reports serve between radiologists and patients. However, the standard image-to-text formulation for radiology report generation fails to incorporate such pragmatic intents. Following this pragmatic perspective, we demonstrate that the indication, which describes why a patient comes for an X-ray, drives the mentions of negative observations and introduce indications as additional input to report generation. With respect to the output, we develop a framework to identify uninferable information from the image as a source of model hallucinations, and limit them by cleaning groundtruth reports. Finally, we use indications and cleaned groundtruth reports to develop pragmatic models, and show that they outperform existing methods not only in new pragmatics-inspired metrics (+4.3 Negative F1) but also in standard metrics (+6.3 Positive F1 and +11.0 BLEU-2).