Although structured reporting (SR) is recommended in the field of radiology compared to free-text reporting (FTR), the use of SR still experiences obstacles due to insufficient integration of speech recognition. Furthermore, SR templates are time-consuming as they have to be completed using a traditional mouse and keyboard. New technologies within the realm of artificial intelligence, such as natural language processing (NLP) offer endless possibilities to help facilitate imaging workflow.
In this study, the authors aimed to utilize the potential of NLP to combine the advantages of SR and speech recognition by developing a reporting tool that uses NLP to automatically convert dictated free text into a structured report.
Key points
- We developed an NLP-based reporting tool that converts free text into structured reports.
- The reporting tool sends visual feedback if relevant findings are missed.
- Testing with text samples and original free-text reports revealed excellent NLP recognition.
- The reporting tool successfully enables the integration of speech into structured reporting.
Authors: Tobias Jorg, Benedikt Kämpgen, Dennis Feiler, Lukas Müller, Christoph Düber, Peter Mildenberger & Florian Jungmann