EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-supported approaches for mammography single and double reading: A controlled multireader study

Beniamino Brancato, Veronica Magni, Calogero Saieva, Gabriella Gemma Risso, Francesca Buti, Sandra Catarzi, Fiorella Ciuffi, Francesca Peruzzi, Francesco Regini, Daniela Ambrogetti, Giuseppe Alabiso, Anna Cruciani und 20 weitere

European Journal of Radiology · 2025

DOI: 10.1016/j.ejrad.2025.112101 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Radiology, 2025. Verfasst von Beniamino Brancato und 31 weiteren Autor:innen. Beteiligte Einrichtung: Unit of Breast Imaging, Istituto per lo Studio, la Prevenzione e la Rete Oncologica (ISPRO), Florence, Italy. Electronic address: b.brancato@ispro.to…. Hauptthemen laut MEDLINE: Mammography, Breast Neoplasms, Artificial Intelligence, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: To assess the impact of artificial intelligence (AI) on the diagnostic performance of radiologists with varying experience levels in mammography reading, considering single and simulated double reading approaches. METHODS: In this retrospective study, 150 mammography examinations (30 with pathology-confirmed malignancies, 120 without malignancies [confirmed by 2-year follow-up]) were reviewed according to five approaches: A) human single reading by 26 radiologists of varying experience; B) AI single reading (Lunit INSIGHT MMG; C) human single reading with simultaneous AI support; D) simulated human-human double reading; E) simulated human-AI double reading, with AI as second independent reader flagging cases with a cancer probability ≥10 %. Sensitivity and specificity were calculated and compared using McNemar's test, univariate and multivariable logistic regression. RESULTS: Compared to single reading without AI support, single reading with simultaneous AI support improved mean sensitivity from 69.2 % (standard deviation [SD] 15.6) to 84.5 % (SD 8.1, p < 0.001), providing comparable mean specificity (91.8 % versus 90.8 %, p = 0.06). The sensitivity increase provided by the AI-supported single reading was largest in the group of radiologists with a sensitivity below the median in the non-supported single reading, from 56.7 % (SD 12.1) to 79.7 % (SD 10.2, p < 0.001). In the simulated human-AI double reading approach, sensitivity further increased to 91.8 % (SD 3.4), surpassing that of the human-human simulated double reading (87.4 %, SD 8.8, p = 0.016), with comparable mean specificity (from 84.0 % to 83.0 %, p = 0.17). CONCLUSION: AI support significantly enhanced sensitivity across all reading approaches, particularly benefiting worse performing radiologists. In the simulated double reading approaches, AI incorporation as independent second reader significantly increased sensitivity without compromising specificity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MammographyBreast NeoplasmsArtificial IntelligenceRadiographic Image Interpretation, Computer-AssistedHumansFemaleSensitivity and SpecificityRetrospective StudiesMiddle AgedObserver VariationAgedAdultReproducibility of Results

Stichwörter der Autor:innen

Artificial intelligenceBreast neoplasmsMammographyRadiologistsSensitivity and specificity

Autor:innen und Institutionen

  • Unit of Breast Imaging, Istituto per lo Studio, la Prevenzione e la Rete Oncologica (ISPRO), Florence, Italy. Electronic address: b.brancato@ispro.toscana.it.
  • Postgraduate School in Radiodiagnostics, Università degli Studi di Milano, Milan, Italy. Electronic address: veronica.magni@unimi.it.
  • Cancer Risk Factors and Lifestyle Epidemiology Unit, Istituto per lo Studio, la Prevenzione e la Rete Oncologica (ISPRO), Florence, Italy. Electronic address: c.saieva@ispro.toscana.it.
  • Unit of Breast Imaging, Istituto per lo Studio, la Prevenzione e la Rete Oncologica (ISPRO), Florence, Italy. Electronic address: g.risso@ispro.toscana.it.
  • Unit of Breast Imaging, Istituto per lo Studio, la Prevenzione e la Rete Oncologica (ISPRO), Florence, Italy. Electronic address: f.buti@ispro.toscana.it.
  • Unit of Breast Imaging, Istituto per lo Studio, la Prevenzione e la Rete Oncologica (ISPRO), Florence, Italy. Electronic address: sandracatarzi@me.com.

Zitieren

APA

Brancato, B., Magni, V., Saieva, C., Risso, G. G., Buti, F., Catarzi, S., Ciuffi, F., Peruzzi, F., Regini, F., Ambrogetti, D., Alabiso, G., Cruciani, A., Doronzio, V., Frati, S., Giannetti, G. P., Guerra, C., Valente, P., Vignoli, C., Atzori, S., …, & Cozzi, A. (2025). AI-supported approaches for mammography single and double reading: A controlled multireader study. European Journal of Radiology. https://doi.org/10.1016/j.ejrad.2025.112101

Vancouver

Brancato B, Magni V, Saieva C, Risso GG, Buti F, Catarzi S, et al. AI-supported approaches for mammography single and double reading: A controlled multireader study. European Journal of Radiology. 2025. doi:10.1016/j.ejrad.2025.112101

BibTeX
@article{Brancato2025,
  author = {Brancato, Beniamino and Magni, Veronica and Saieva, Calogero and Risso, Gabriella Gemma and Buti, Francesca and Catarzi, Sandra and Ciuffi, Fiorella and Peruzzi, Francesca and Regini, Francesco and Ambrogetti, Daniela and Alabiso, Giuseppe and Cruciani, Anna and Doronzio, Valeria and Frati, Sara and Giannetti, Gian Piero and Guerra, Claudio and Valente, Pietro and Vignoli, Chiara and Atzori, Stefano and Carrera, Valentina and D'Agostino, Giulia and Fazzini, Giulia and Picano, Eugenia and Turini, Francesca Maria and Vani, Vanina and Fantozzi, Federica and Vietro, Dario De and Cavallero, Diletta and Vietro, Fabrizio De and Plataroti, Dario and Schiaffino, Simone and Cozzi, Andrea},
  title = {AI-supported approaches for mammography single and double reading: A controlled multireader study},
  journal = {European Journal of Radiology},
  year = {2025},
  doi = {10.1016/j.ejrad.2025.112101}
}
Kostenlos starten →