Download PDF
CC BY-NC-ND 4.0 · Indian J Radiol Imaging 2025; 35(01): 043-049
DOI: 10.1055/s-0044-1788589
Original Article

Enhancing Radiological Reporting in Head and Neck Cancer: Converting Free-Text CT Scan Reports to Structured Reports Using Large Language Models

Amit Gupta
1   Department of Radiodiagnosis, All India Institute of Medical Sciences New Delhi, New Delhi, India
,
Hema Malhotra
2   Department of Radiology, Dr. Bhim Rao Ambedkar Institute Rotary Cancer Hospital, All India Institute of Medical Sciences New Delhi, India
,
Amit K. Garg
3   Indian Institute of Technology, New Delhi, India
,
Krithika Rangarajan
2   Department of Radiology, Dr. Bhim Rao Ambedkar Institute Rotary Cancer Hospital, All India Institute of Medical Sciences New Delhi, India
› Author Affiliations Funding We acknowledge the support from the Ministry of Education, Government of India, Central Project Management Unit, IIT Jammu with grant sanction number IITJMU/CPMU-AI/2024/0002.
› Further Information
Also available at
   Permissions and Reprints

Abstract

Objective The aim of this study was to assess efficacy of large language models (LLMs) for converting free-text computed tomography (CT) scan reports of head and neck cancer (HNCa) patients into a structured format using a predefined template.

Materials and Methods A retrospective study was conducted using 150 CT reports of HNCa patients. A comprehensive structured reporting template for HNCa CT scans was developed, and the Generative Pre-trained Transformer 4 (GPT-4) was initially used to convert 50 CT reports into a structured format using this template. The generated structured reports were then evaluated by a radiologist for instances of missing or misinterpreted information and any erroneous additional details added by GPT-4. Following this assessment, the template was refined for improved accuracy. This revised template was then used for conversion of 100 other HNCa CT reports into structured format using GPT-4. These reports were then reevaluated in the same manner.

Results Initially, GPT-4 successfully converted all 50 free-text reports into structured reports. However, there were 10 places with missing information: tracheostomy tube (n = 3), noninclusion of involvement of sternocleidomastoid muscle (n = 2), extranodal tumor extension (n = 3), and contiguous involvement of the neck structures by nodal mass rather than the primary (n = 2). Few instances of nonsuspicious lung nodules were misinterpreted as metastases (n = 2). GPT-4 did not indicate any erroneous additional findings. Using the revised reporting template, GPT-4 converted all the 100 CT reports into a structured format with no repeated or additional mistakes.

Conclusion LLMs can be used for structuring free-text radiology reports using plain language prompts and a simple yet comprehensive reporting template.

Key Points

  • Structured radiology reports in oncological patients, although advantageous, are not used widely in practice due to perceived drawbacks like interference with routine radiology workflow and scan interpretation.

  • We found that GPT-4 is highly efficient in converting conventional CT reports of HNCa patients to structured reports using a predefined template.

  • This application of LLMs in radiology can help in enhancing the acceptability and clinical utility of structured radiology reports in oncological imaging.

Summary Statement

Large language models can successfully and accurately convert conventional radiology reports for oncology scans into a structured format using a comprehensive predefined template and thus can enhance the utility and integration of these reports in routine clinical practice.

Keywords

GPT-4 - large language models - structured reporting - head and neck cancer

Ethical Approval

Ethical approval was obtained from the institutional review board. Patient consent was not applicable for this study and was waived off by the ethics committee.


Supplementary Material



Publication History

Article published online:
01 August 2024

© 2024. Indian Radiological Association. This is an open access article published by Thieme under the terms of the Creative Commons Attribution-NonDerivative-NonCommercial License, permitting copying and reproduction so long as the original work is given appropriate credit. Contents may not be used for commercial purposes, or adapted, remixed, transformed or built upon. (https://creativecommons.org/licenses/by-nc-nd/4.0/)

Thieme Medical and Scientific Publishers Pvt. Ltd.
A-12, 2nd Floor, Sector 2, Noida-201301 UP, India

 

  • References

  • 1 Marcovici PA, Taylor GA. Journal club: structured radiology reports are more complete and more effective than unstructured reports. Am J Roentgenol 2014; 203 (06) 1265-1271
    CrossrefPubMedSearch in Google Scholar
  • 2 European Society of Radiology (ESR). ESR paper on structured reporting in radiology. Insights Imaging 2018; 9 (01) 1-7
    CrossrefPubMedSearch in Google Scholar
  • 3 European Society of Radiology (ESR). ESR paper on structured reporting in radiology-update 2023. Insights Imaging 2023; 14 (01) 199
    CrossrefPubMedSearch in Google Scholar
  • 4 Goldberg-Stein S, Chernyak V. Adding value in radiology reporting. J Am Coll Radiol 2019; 16 (9, Pt B): 1292-1298
    CrossrefPubMedSearch in Google Scholar
  • 5 Pinto Dos Santos D, Baeßler B. Big data, artificial intelligence, and structured reporting. Eur Radiol Exp 2018; 2 (01) 42
    CrossrefPubMedSearch in Google Scholar
  • 6 Shea LAG, Towbin AJ. The state of structured reporting: the nuance of standardized language. Pediatr Radiol 2019; 49 (04) 500-508
    CrossrefPubMedSearch in Google Scholar
  • 7 Weiss DL, Langlotz CP. Structured reporting: patient care enhancement or productivity nightmare?. Radiology 2008; 249 (03) 739-747
    CrossrefPubMedSearch in Google Scholar
  • 8 Harris D, Yousem DM, Krupinski EA, Motaghi M. Eye-tracking differences between free text and template radiology reports: a pilot study. J Med Imaging (Bellingham) 2023; 10 (Suppl. 01) S11902
    PubMedSearch in Google Scholar
  • 9 Elkassem AA, Smith AD. Potential use cases for ChatGPT in radiology reporting. AJR Am J Roentgenol 2023; 221 (03) 373-376
    CrossrefPubMedSearch in Google Scholar
  • 10 Lyu Q, Tan J, Zapadka ME. et al. Translating radiology reports into plain language using ChatGPT and GPT-4 with prompt learning: results, limitations, and potential. Vis Comput Ind Biomed Art 2023; 6 (01) 9
    CrossrefPubMedSearch in Google Scholar
  • 11 Amin KS, Davis MA, Doshi R, Haims AH, Khosla P, Forman HP. Accuracy of ChatGPT, Google Bard, and Microsoft Bing for simplifying radiology reports. Radiology 2023; 309 (02) e232561
    CrossrefPubMedSearch in Google Scholar
  • 12 Bhayana R, Bleakney RR, Krishna S. GPT-4 in radiology: improvements in advanced reasoning. Radiology 2023; 307 (05) e230987
    CrossrefPubMedSearch in Google Scholar
  • 13 Haver HL, Ambinder EB, Bahl M, Oluyemi ET, Jeudy J, Yi PH. Appropriateness of breast cancer prevention and screening recommendations provided by ChatGPT. Radiology 2023; 307 (04) e230424
    CrossrefPubMedSearch in Google Scholar
  • 14 Rahsepar AA, Tavakoli N, Kim GHJ, Hassani C, Abtin F, Bedayat A. How AI responds to common lung cancer questions: ChatGPT vs Google Bard. Radiology 2023; 307 (05) e230922
    CrossrefPubMedSearch in Google Scholar
  • 15 Spandorfer A, Branch C, Sharma P. et al. Deep learning to convert unstructured CT pulmonary angiography reports into structured reports. Eur Radiol Exp 2019; 3 (01) 37
    CrossrefPubMedSearch in Google Scholar
  • 16 Moezzi SAR, Ghaedi A, Rahmanian M, Mousavi SZ, Sami A. Application of deep learning in generating structured radiology reports: a transformer-based technique. J Digit Imaging 2023; 36 (01) 80-90
    CrossrefPubMedSearch in Google Scholar
  • 17 Adams LC, Truhn D, Busch F. et al. Leveraging GPT-4 for post hoc transformation of free-text radiology reports into structured reporting: a multilingual feasibility study. Radiology 2023; 307 (04) e230725
    CrossrefPubMedSearch in Google Scholar
  • 18 Mahajan A, Agarwal U, Gupta A. et al. Synoptic reporting in head and neck cancers—Head and Neck Cancer Imaging Reporting and Data Systems (HN-CIRADS): The journey ahead for standardization of imaging in head and neck cancer staging. Cancer Res Stat Treat 2022; 5 (02) 322
    CrossrefSearch in Google Scholar
  • 19 Strauss SB, Aiken AH, Lantos JE, Phillips CD. Best practices: application of NI-RADS for posttreatment surveillance imaging of head and neck cancer. Am J Roentgenol 2021; 216 (06) 1438-1451
    CrossrefPubMedSearch in Google Scholar