A novel reporting workflow for automated integration of artificial intelligence results into structured radiology reports.
Artificial intelligence
Chest X-ray
Radiology workflow
Structured reporting
Journal
Insights into imaging
ISSN: 1869-4101
Titre abrégé: Insights Imaging
Pays: Germany
ID NLM: 101532453
Informations de publication
Date de publication:
19 Mar 2024
19 Mar 2024
Historique:
received:
29
12
2023
accepted:
25
02
2024
medline:
19
3
2024
pubmed:
19
3
2024
entrez:
19
3
2024
Statut:
epublish
Résumé
Artificial intelligence (AI) has tremendous potential to help radiologists in daily clinical routine. However, a seamless, standardized, and time-efficient way of integrating AI into the radiology workflow is often lacking. This constrains the full potential of this technology. To address this, we developed a new reporting pipeline that enables automated pre-population of structured reports with results provided by AI tools. Findings from a commercially available AI tool for chest X-ray pathology detection were sent to an IHE-MRRT-compliant structured reporting (SR) platform as DICOM SR elements and used to automatically pre-populate a chest X-ray SR template. Pre-populated AI results could be validated, altered, or deleted by radiologists accessing the SR template. We assessed the performance of this newly developed AI to SR pipeline by comparing reporting times and subjective report quality to reports created as free-text and conventional structured reports. Chest X-ray reports with the new pipeline could be created in significantly less time than free-text reports and conventional structured reports (mean reporting times: 66.8 s vs. 85.6 s and 85.8 s, respectively; both p < 0.001). Reports created with the pipeline were rated significantly higher quality on a 5-point Likert scale than free-text reports (p < 0.001). The AI to SR pipeline offers a standardized, time-efficient way to integrate AI-generated findings into the reporting workflow as parts of structured reports and has the potential to improve clinical AI integration and further increase synergy between AI and SR in the future. With the AI-to-structured reporting pipeline, chest X-ray reports can be created in a standardized, time-efficient, and high-quality manner. The pipeline has the potential to improve AI integration into daily clinical routine, which may facilitate utilization of the benefits of AI to the fullest. • A pipeline was developed for automated transfer of AI results into structured reports. • Pipeline chest X-ray reporting is faster than free-text or conventional structured reports. • Report quality was also rated higher for reports created with the pipeline. • The pipeline offers efficient, standardized AI integration into the clinical workflow.
Identifiants
pubmed: 38502298
doi: 10.1186/s13244-024-01660-5
pii: 10.1186/s13244-024-01660-5
doi:
Types de publication
Journal Article
Langues
eng
Pagination
80Informations de copyright
© 2024. The Author(s).
Références
Ranschaert E, Topff L, Pianykh O (2021) Optimization of radiology workflow with artificial intelligence. Radiol Clin North Am 59:955–966
doi: 10.1016/j.rcl.2021.06.006
pubmed: 34689880
Neri E, de Souza N, Brady A, et al (2019) What the radiologist should know about artificial intelligence – an ESR white paper. Insights Imaging 10. https://doi.org/10.1186/s13244-019-0738-2
Kapoor N, Lacson R, Khorasani R (2020) Workflow applications of artificial intelligence in radiology and an overview of available tools. J Am Coll Radiol 17:1363–1370. https://doi.org/10.1016/j.jacr.2020.08.016
doi: 10.1016/j.jacr.2020.08.016
pubmed: 33153540
Müller L, Kloeckner R, Mähringer-Kunz A et al (2022) Fully automated AI-based splenic segmentation for predicting survival and estimating the risk of hepatic decompensation in TACE patients with HCC. Eur Radiol 32:6302–6313. https://doi.org/10.1007/s00330-022-08737-z
doi: 10.1007/s00330-022-08737-z
pubmed: 35394184
Qin C, Yao D, Shi Y, Song Z (2018) Computer-aided detection in chest radiography based on artificial intelligence: a survey. Biomed Eng Online 17:1–23. https://doi.org/10.1186/s12938-018-0544-y
doi: 10.1186/s12938-018-0544-y
Liu K, Li Q, Ma J, et al (2019) Evaluating a fully automated pulmonary nodule detection approach and its impact on radiologist performance. Radiol Artif Intell 1. https://doi.org/10.1148/ryai.2019180084
van Leeuwen KG, de Rooij M, Schalekamp S et al (2023) Clinical use of artificial intelligence products for radiology in the Netherlands between 2020 and 2022. Eur Radiol. https://doi.org/10.1007/s00330-023-09991-5
doi: 10.1007/s00330-023-09991-5
pubmed: 37737870
van Leeuwen KG, Schalekamp S, Rutten MJCM et al (2021) Artificial intelligence in radiology: 100 commercially available products and their scientific evidence. Eur Radiol 31:3797–3804. https://doi.org/10.1007/s00330-021-07892-z
doi: 10.1007/s00330-021-07892-z
pubmed: 33856519
Blezek DJ, Olson-Williams L, Missert A, Korfiatis P (2021) AI integration in the clinical workflow. J Digit Imaging 34:1435–1446. https://doi.org/10.1007/s10278-021-00525-3
doi: 10.1007/s10278-021-00525-3
pubmed: 34686923
Wiggins WF, Magudia K, Sippel Schmidt TM, et al (2021) Imaging AI in practice: a demonstration of future workflow using integration standards. Radiol Artif Intell 3. https://doi.org/10.1148/ryai.2021210152
Dargan R (2020) Integrating AI with PACS key to improving workflow efficiency. In: RSNA News. https://www.rsna.org/news/2020/march/integrating-ai-with-pacs
Dunnick NR, Langlotz CP (2008) The radiology report of the future: a summary of the 2007 Intersociety Conference. J Am Coll Radiol 5:626–629
doi: 10.1016/j.jacr.2007.12.015
pubmed: 18442766
Brook OR, Brook A, Vollmer CM, Kent TS (2015) Health policy and practice: structured reporting of multiphasic CT for pancreatic cancer. Brook et al. Radiology 274:464–472. https://doi.org/10.1148/radiol.14140206
doi: 10.1148/radiol.14140206
pubmed: 25286323
Schoeppe F, Sommer WH, Nörenberg D et al (2018) Structured reporting adds clinical value in primary CT staging of diffuse large B-cell lymphoma. Eur Radiol 28:3702–3709. https://doi.org/10.1007/s00330-018-5340-3
doi: 10.1007/s00330-018-5340-3
pubmed: 29600475
Jorg T, Heckmann JC, Mildenberger P et al (2021) Structured reporting of CT scans of patients with trauma leads to faster, more detailed diagnoses: an experimental study. Eur J Radiol 144:109954. https://doi.org/10.1016/j.ejrad.2021.109954
doi: 10.1016/j.ejrad.2021.109954
pubmed: 34563796
Fink MA, Mayer VL, Schneider T et al (2022) CT angiography clot burden score from data mining of structured reports for pulmonary embolism. Radiology 302:175–184. https://doi.org/10.1148/radiol.2021211013
doi: 10.1148/radiol.2021211013
pubmed: 34581626
Dos Santos DP, Scheibl S, Arnhold G, et al (2018) A proof of concept for epidemiological research using structured reporting with pulmonary embolism as a use case. Br J Radiol 91. https://doi.org/10.1259/bjr.20170564
Jorg T, Halfmann MC, Rölz N, et al (2023) Structured reporting in radiology enables epidemiological analysis through data mining: urolithiasis as a use case. Abdom Radiol (NY). https://doi.org/10.1007/s00261-023-04006-9
Hempel JM, Pinto dos Santos D (2021) Structured reporting and artificial intelligence. Radiologe 61:999–1004
doi: 10.1007/s00117-021-00920-5
pubmed: 34605945
Chilamkurthy S, Ghosh R, Tanamala S et al (2018) Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. Lancet 392:2388–2396. https://doi.org/10.1016/S0140-6736(18)31645-3
doi: 10.1016/S0140-6736(18)31645-3
pubmed: 30318264
Pinto dos Santos D, Brodehl S, Baeßler B et al (2019) Structured report data can be used to develop deep learning algorithms: a proof of concept in ankle radiographs. Insights Imaging 10:0–7. https://doi.org/10.1186/s13244-019-0777-8
doi: 10.1186/s13244-019-0777-8
Jorg T, Kämpgen B, Feiler D, et al (2023) Efficient structured reporting in radiology using an intelligent dialogue system based on speech recognition and natural language processing. Insights Imaging 14. https://doi.org/10.1186/s13244-023-01392-y
Pinto dos Santos D, Klos G, Kloeckner R et al (2017) Development of an IHE MRRT-compliant open-source web-based reporting platform. Eur Radiol 27:424–430. https://doi.org/10.1007/s00330-016-4344-0
doi: 10.1007/s00330-016-4344-0
pubmed: 27137649
Jorg T, Halfmann MC, Arnhold G et al (2023) Implementation of structured reporting in clinical routine: a review of 7 years of institutional experience. Insights Imaging 14:61. https://doi.org/10.1186/s13244-023-01408-7
doi: 10.1186/s13244-023-01408-7
pubmed: 37037963
Welter P, Gülpers R, Deserno TM et al (2010) Entwurf eines DICOM Structured Report am Beispiel Content-Based Image Retrieval. CEUR Workshop Proceedings. pp 340–344
Graafen D, Stoehr F, Halfmann MC et al (2023) Quantum iterative reconstruction on a photon-counting detector CT improves the quality of hepatocellular carcinoma imaging. Cancer Imaging 23:69. https://doi.org/10.1186/s40644-023-00592-5
doi: 10.1186/s40644-023-00592-5
pubmed: 37480062
Shin HJ, Han K, Ryu L, Kim EK (2023) The impact of artificial intelligence on the reading times of radiologists for chest radiographs. NPJ Digit Med 6. https://doi.org/10.1038/s41746-023-00829-4
Fuchs M, Gonzalez C, Frisch Y, et al (2023) Closing the loop for AI-ready radiology. Rofo 196:154–162
Pierre K, Haneberg AG, Kwak S et al (2023) Applications of artificial intelligence in the radiology roundtrip: process streamlining, workflow optimization, and beyond. Semin Roentgenol 58:158–169. https://doi.org/10.1053/j.ro.2023.02.003
doi: 10.1053/j.ro.2023.02.003
pubmed: 37087136
Letourneau-Guillon L, Camirand D, Guilbert F, Forghani R (2020) Artificial intelligence applications for workflow, process optimization and predictive analytics. Neuroimaging Clin N Am 30:e1–e15
doi: 10.1016/j.nic.2020.08.008
pubmed: 33039002
Adams LC, Truhn D, Busch F et al (2023) Leveraging GPT-4 for post hoc transformation of free-text radiology reports into structured reporting: a multilingual feasibility study. Radiology. https://doi.org/10.1148/radiol.230725
doi: 10.1148/radiol.230725
pubmed: 37093751
Gundogdu B, Pamuksuz U, Chung JH et al (2023) Customized impression prediction from radiology reports using BERT and LSTMs. IEEE Trans Artif Intell 4:744–753. https://doi.org/10.1109/TAI.2021.3086435
doi: 10.1109/TAI.2021.3086435
Kim SH, Mir-Bashiri S, Matthies P et al (2021) Integration of structured reporting into the routine radiological workflow. Radiologe 61:1005–1013
doi: 10.1007/s00117-021-00917-0
pubmed: 34581842
dos Santos DP, Kotter E, Mildenberger P, Martí-Bonmatí L (2023) ESR paper on structured reporting in radiology—update 2023. Insights Imaging 14:199. https://doi.org/10.1186/s13244-023-01560-0
doi: 10.1186/s13244-023-01560-0
Pinto dos Santos D, Cuocolo R, Huisman M (2023) O structured reporting, where art thou? Eur Radiol. https://doi.org/10.1007/s00330-023-10465-x
doi: 10.1007/s00330-023-10465-x
pubmed: 38010379