Automated Knee X-ray Report Generation
This addresses the problem of reducing manual annotation burdens for radiologists in medical imaging, though it is incremental as it builds on existing language generation models.
The authors tackled the challenge of generating diagnostic reports for knee X-ray exams by learning the correspondence between images and reports from past radiological data, resulting in auto-generated reports that correlate well with radiologist-generated ones.
Gathering manually annotated images for the purpose of training a predictive model is far more challenging in the medical domain than for natural images as it requires the expertise of qualified radiologists. We therefore propose to take advantage of past radiological exams (specifically, knee X-ray examinations) and formulate a framework capable of learning the correspondence between the images and reports, and hence be capable of generating diagnostic reports for a given X-ray examination consisting of an arbitrary number of image views. We demonstrate how aggregating the image features of individual exams and using them as conditional inputs when training a language generation model results in auto-generated exam reports that correlate well with radiologist-generated reports.