Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Jul 25:11:100512.
doi: 10.1016/j.ejro.2023.100512. eCollection 2023 Dec.

Natural language processing to convert unstructured COVID-19 chest-CT reports into structured reports

Salvatore Claudio Fanni  1 , Chiara Romei  2 , Giovanni Ferrando  3 , Federica Volpi  1 , Caterina Aida D'Amore  1 , Claudio Bedini  4 , Sandro Ubbiali  3 , Salvatore Valentino  3 , Emanuele Neri  1
Affiliations

Natural language processing to convert unstructured COVID-19 chest-CT reports into structured reports

Salvatore Claudio Fanni et al. Eur J Radiol Open. .

Abstract

Background: Structured reporting has been demonstrated to increase report completeness and to reduce error rate, also enabling data mining of radiological reports. Still, structured reporting is perceived by radiologists as a fragmented reporting style, limiting their freedom of expression.

Purpose: A deep learning-based natural language processing method was developed to automatically convert unstructured COVID-19 chest CT reports into structured reports.

Methods: Two hundred-two COVID-19 chest CT were retrospectively reviewed by two experienced radiologists, who wrote for each exam a free-form text radiological report and coherently filled the template provided by the Italian Society of Medical and Interventional Radiology, used as ground-truth. A semi-supervised convolutional neural network was implemented to extract 62 categorical variables from the report. Two iterations were carried-out, the first without fine-tuning, the second one performing a fine-tuning. The performance was measured using the mean accuracy and the F1 mean score. An error analysis was performed to identify errors entirely attributable to incorrect processing of the model.

Results: The algorithm achieved a mean accuracy of 93.7% and an F1 score 93.8% in the first iteration. Most of the errors were exclusively attributable to wrong inference (46%). In the second iteration the model achieved for both parameters 95,8% and percentage of errors attributable to wrong inference decreased to 26%.

Conclusions: The convolutional neural network achieved an optimal performance in the automated conversion of free-form text into structured radiological reports, overcoming all the limitation attributed to structured reporting and finally paving the way for data mining of radiological report.

Keywords: Artificial intelligence; COVID-19; Deep learning; Natural language processing; Structured reporting.

PubMed Disclaimer

Conflict of interest statement

The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Giovanni Ferrando, Claudio Bedini, Sandro Ubbiali and Salvatore Valentino declare personal fees from Ebit s.r.l. Esaote group. The other authors of this manuscript declare no conflict of interest.

Figures

Fig. 1
Fig. 1
Final architecture of the solution.
See this image and copyright information in PMC

References

    1. Nobel J.M., Kok E.M., Robben S.G.F. Redefining the structure of structured reporting in radiology. Insights Imaging. 2020;11 doi: 10.1186/s13244-019-0831-6. - DOI - PMC - PubMed
    1. Reiner, B.I., Knight, N., Siegel, E.L., 2007, Radiology Reporting, Past, Present, and Future: The Radiologist’s Perspective. Journal of the American College of Radiology 4:313–319. https://doi.org/10.1016/j.jacr.2007.01.015. - PubMed
    1. Barbisan C.C., Andres M.P., Torres L.R., et al. Structured MRI reporting increases completeness of radiological reports and requesting physicians’ satisfaction in the diagnostic workup for pelvic endometriosis. Abdom. Radiol. 2021;46:3342–3353. doi: 10.1007/s00261-021-02966-4. - DOI - PubMed
    1. Ernst B.P., Katzer F., Künzel J., et al. Impact of structured reporting on developing head and neck ultrasound skills. BMC Med Educ. 2019:19. doi: 10.1186/s12909-019-1538-6. - DOI - PMC - PubMed
    1. Stanzione A., Ponsiglione A., Cuocolo R., et al. Chest CT in COVID-19 patients: Structured vs conventional reporting. Eur. J. Radio. 2021:138. doi: 10.1016/j.ejrad.2021.109621. - DOI - PMC - PubMed

LinkOut - more resources