EUVIMEDEUVIMED entdecken
Crossref

AI assistance improves radiology resident reader performance in CT diagnosis of intracranial hemorrhage

Philipp Reschke, Leon D Gruenewald, Vitali Koch, Jennifer Gotta, Elena Höhne, Andreea-Ioana Nica, Ibrahim Yel, Tommaso D'Angelo, Giorgio Ascenti, Giuseppe M Bucolo, Ludovica R M Lanzafame, Erando Jubica und 3 weitere

La radiologia medica · 2025

DOI: 10.1007/s11547-025-02119-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift La radiologia medica, 2025. Verfasst von Philipp Reschke und 14 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Diagnostic and Interventional Radiology, Goethe University Frankfurt, University Hospital, Frankfurt Am Main, Germany. Hauptthemen laut MEDLINE: Internship and Residency, Intracranial Hemorrhages, Tomography, X-Ray Computed, Artificial Intelligence. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 28 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: Accurate detection of intracranial hemorrhage (ICH) on non-contrast CT is critical in emergency settings, where missed diagnoses may delay treatment and worsen outcomes. While artificial intelligence (AI) models demonstrate high standalone performance, their additive value as a second reader for radiology residents is not well-established. MATERIAL AND METHODS: This retrospective study included 1,337 non-contrast head CT scans from 2015 to 2019 (670 ICH-positive and 667 ICH-negative). A previously validated AI model was used for ICH detection. Two radiology residents reviewed all scans in consensus, first without and later with AI support after a 30-day washout. Ground truth was established by expert consensus. Diagnostic performance metrics were calculated. RESULTS: AI assistance significantly improved radiology residents' diagnostic performance. Sensitivity increased from 0.85 to 0.94 and specificity from 0.87 to 0.97 (both p < 0.01), ROC-AUC rose from 0.86 to 0.95, and PR-AUC from 0.83 to 0.95 (p < 0.0001). The number of false negatives dropped from 101 to 41 with AI support. The greatest benefit was observed in subdural hematomas (SDH), where misses declined from 32 to 9 (20.3-5.7%; p < 0.001), corresponding to a 72% relative risk reduction. Misses also decreased for intraparenchymal hemorrhages (IPH: 37-20; RRR 46%) and subarachnoid hemorrhages (SAH: 30-11; RRR 63%). AI support reduced common error sources: small hemorrhage volume (48-21), atypical locations (30-12), and image-degrading artifacts (23-8). False positives fell from 87 to 21. CONCLUSION: By reducing diagnostic errors and supporting learning, AI serves as a valuable second reader for radiology residents-enhancing both patient safety and resident training in ICH detection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Internship and ResidencyIntracranial HemorrhagesTomography, X-Ray ComputedArtificial IntelligenceClinical CompetenceRadiologyHumansRetrospective StudiesMaleFemaleSensitivity and SpecificityMiddle AgedAged

Stichwörter der Autor:innen

AlgorithmsAutomated pattern recognitionComputed tomographyComputer ScienceLearning algorithmsMachine learning

Autor:innen und Institutionen

  • Institute for Diagnostic and Interventional Radiology, Goethe University Frankfurt, University Hospital, Frankfurt Am Main, Germany.
  • Department of Biomedical Sciences and Morphological and Functional Imaging, University Hospital Messina, Messina, Italy. tommasodang@gmail.com.
  • Department of Biomedical Sciences and Morphological and Functional Imaging, University Hospital Messina, Messina, Italy.

Zitieren

APA

Reschke, P., Gruenewald, L. D., Koch, V., Gotta, J., Höhne, E., Nica, A. I., Yel, I., D'Angelo, T., Ascenti, G., Bucolo, G. M., Lanzafame, L. R. M., Jubica, E., Eichler, K., Vogl, T. J., & Booz, C. (2025). AI assistance improves radiology resident reader performance in CT diagnosis of intracranial hemorrhage. La radiologia medica. https://doi.org/10.1007/s11547-025-02119-3

Vancouver

Reschke P, Gruenewald LD, Koch V, Gotta J, Höhne E, Nica AI, et al. AI assistance improves radiology resident reader performance in CT diagnosis of intracranial hemorrhage. La radiologia medica. 2025. doi:10.1007/s11547-025-02119-3

BibTeX
@article{Reschke2025,
  author = {Reschke, Philipp and Gruenewald, Leon D and Koch, Vitali and Gotta, Jennifer and Höhne, Elena and Nica, Andreea-Ioana and Yel, Ibrahim and D'Angelo, Tommaso and Ascenti, Giorgio and Bucolo, Giuseppe M and Lanzafame, Ludovica R M and Jubica, Erando and Eichler, Katrin and Vogl, Thomas J and Booz, Christian},
  title = {AI assistance improves radiology resident reader performance in CT diagnosis of intracranial hemorrhage},
  journal = {La radiologia medica},
  year = {2025},
  doi = {10.1007/s11547-025-02119-3}
}
Kostenlos starten →