Maimone, S. I.

Abstract Background: Artificial intelligence (AI) algorithms based on deep learning approaches show promise in improving breast cancer (BC) detection on mammography and may also improve prediction of future BC risk compared with clinical risk prediction models. Historical clinical risk prediction models underperform among women with BBD; however, AI models for BC detection on mammography have not been tested among women at elevated BC risk due to benign breast disease (BBD). We evaluated if an AI cancer detection algorithm can aid BC risk prediction among women with BBD. Methods: We examined women without a prior BC who had an initial BBD biopsy at Mayo Clinic, Rochester, between 2002 and 2013. Incident BC occurring after BBD was identified using the Mayo Tumor Registry and supplemented by follow-up questionnaires. Only women with a full field digital mammogram at least 2 years prior to BC diagnosis were eligible. A breast pathologist evaluated BBD according to increasing severity, as non-proliferative (NP), proliferative disease without atypia (PDWA) or atypical hyperplasia (AH). AI malignancy scores derived from the Transpara detection algorithm (1-10) and volumetric percent density (VPD) from Volpara (per one standard deviation, SD) were assessed from mammograms close to BBD diagnosis. Cox proportional hazards regression models were applied to estimate hazard ratios (HRs) with 95% Confidence Intervals (CIs), adjusted for age and BMI. C-statistics were estimated to assess the contribution of each factor to BC risk prediction. Likelihood ratio tests (LRTs) and bootstrapping methods were used to compare model performance with the addition of AI malignancy score. Results: The BBD cohort with mammography consisted of 3,125 women followed for a median 12.9 years, with 250 incident BC. Of these, 221 BC occurred at least two years after the mammogram and were used in analyses. As expected, increased BC risk was associated with BBD severity [for AH HR=3.18 (95%CI: 2.04, 4.95) and for PDWA HR=1.59 (95%CI: 1.17, 2.14) compared to NP] and with higher VPD [HR=1.24 per SD (95% CI: 1.05, 1.45)] (Table ). The AI-malignancy score alone was also associated with BC risk [HR=1.16 per 1 unit score (95%CI: 1.09,1.23)] and showed similar discriminatory accuracy [C-statistic=0.626 (95%CI: 0.586, 0.665)] as the model with BBD severity and VPD combined [C-statistic=0.627, (95%CI: 0.585, 0.669)] (Table ). In models with BBD severity and VPD, the AI-malignancy score was an independent risk factor for BC [HR=1.14 (95%CI: 1.07, 1.21); PLRT<0.001] but only achieved a marginally significant improvement in discriminatory accuracy [C-statistic=0.651 (0.609, 0.693), ΔC-statistic=0.024 (95% CI: 0.000, 0.047)]. Conclusion: In this preliminary study, an AI BC detection algorithm achieved similar performance in predicting future BC risk compared to established risk factors. Citation Format: C. M. Vachon, S. Winham, M. Jensen, D. Hursh, L. Pacheco-Spann, A. Norman, J. Fischer, S. Schrup, L. Seymour, D. Gehling, S. Nyante, M. Troester, N. Karssemeijer, R. Vierkant, D. Radisky, C. Scott, S. I. Maimone, A. Degnim, M. Sherman. An AI algorithm for breast cancer detection improves future BC risk prediction among women with benign breast disease [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2025; 2025 Dec 9-12; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(4 Suppl):Abstract nr PD4-02.

Abstract Objective To compare the pathology outcomes of image-guided breast biopsies across a multistate health care enterprise by the method of detection (MOD), including the positive predictive value (PPV3) and histological types. Methods Biopsies from October 31, 2017, to July 6, 2023, across 18 imaging sites in 4 states were extracted. Radiologists prospectively assigned MODs, including symptomatic presentations (self-examination, clinical examination) and imaging modalities (mammogram, tomosynthesis, US, MRI, contrast-enhanced mammogram, molecular breast imaging, other imaging). For each MOD, the rates of malignancy and cancer subtypes were calculated. Univariate and multivariate logistic regression analyses were performed. Results In 26 932 biopsies on 22 582 patients (mean age 57.6 years ± 14.2 [SD]; 22 416 women), 6068 (81.1%) cancers were detected by screening, and 1144 (15.3%) were detected by symptoms. Symptomatic presentation MODs had a higher PPV3 (43.0% vs 25.6%; P < .001), larger cancer lesion sizes (x̄ = 27.5 mm vs x̄ = 17.8 mm; P < 001), and a higher association with invasive carcinoma (96.7% vs 76.8%; P <.001) compared with screening imaging-based MODs. Methods of detection with higher PPV3s also tended to have higher rates of invasive carcinoma (Spearman’s ρ = 0.83). Conclusion Compared with breast cancers detected after symptomatic presentations, those identified via image-based screening were smaller and less often invasive, confirming the value of screening in early detection. Positive predictive value and the rate of invasive carcinoma varied in parallel across MODs.