AI-supported approaches for mammography single and double reading: A controlled multireader study
Year: 2025
Type: article
Abstract: 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.
Source: European Journal of Radiology
Authors: 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, Valeria Doronzio, Sara Frati, Gian Piero Giannetti, Claudio Guerra, Pietro Valente, Chiara Vignoli, Stefano Atzori, Valentina Carrera, Giulia D’Agostino, Giulia Fazzini, Eugenia Picano, Francesca Maria Turini, Vanina Vani, Federica Fantozzi, Dario De Vietro, Diletta Cavallero, Fabrizio De Vietro, Dario Plataroti, Simone Schiaffino, Andrea Cozzi
Institutions: Istituto per lo Studio e la Prevenzione Oncologica, University of Milan, Azienda Usl Toscana Centro, Azienda USL Toscana Nord Ovest, Azienda Ospedaliera Universitaria Pisana, Azienda Ospedaliera Universitaria Senese, University of Florence, University of Pisa, Ente Ospedaliero Cantonale, Istituto Imaging della Svizzera Italiana, Università della Svizzera italiana
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,440
OpenAlex ID: W4409252759