What does this research mean for the field?

The AI-based digital pathology tool RlapsRisk BC demonstrates superior prognostic performance compared to genomic signatures EndoPredict and Oncotype DX in early ER+/HER2- breast cancer. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The study aims to evaluate the prognostic performance of an AI-based digital pathology tool versus genomic signatures in early ER+/HER2- breast cancer.

February 19, 2026

Abstract PD11-04: Comparative performance of an AI-based digital pathology tool and genomic signatures in early ER+/HER2- breast cancer

Key Points

The study aims to evaluate the prognostic performance of an AI-based digital pathology tool versus genomic signatures in early ER+/HER2- breast cancer.
Conducted a retrospective analysis of ER+/HER2- early breast cancer patients from two cohorts.
Utilized an AI digital pathology tool (RlapsRisk BC) and compared results with genomic tests (EndoPredict and Oncotype DX).
Evaluated the primary endpoint of five-year distant recurrence-free survival (dRFS).
In the EP cohort, AI achieved an AUC of 0.73 versus 0.57 for EndoPredict.
In the ODX cohort, the AI tool reached an AUC of 0.78 compared to 0.58 for Oncotype DX.
The AI tool classified fewer patients as high risk compared to EndoPredict, while classifying more as high risk compared to Oncotype DX.
Five-year dRFS for low-risk patients was 99.6% with AI versus 98.3% with EndoPredict in the EP cohort.

Abstract

Abstract Background Prognostic tools are important for guiding adjuvant therapy in early breast cancer (EBC), particularly for patients with estrogen receptor-positive, HER2-negative (ER+/HER2-) tumors, where optimizing the treatment strategy, like making a de-escalation decision, remains a clinical challenge (1). Recent advances in artificial intelligence (AI) applied to whole-slide images have opened new possibilities for capturing prognostic information directly from routinely available H35(24):2838-2847. doi:10.1200/JCO.2017.74.04722. Garberis I, Gaury V, Saillard C, et al. Deep learning assessment of metastatic relapse risk from digitized breast cancer histological slides. Nat Commun. 2025;16:5876.3. Dubsky P, Filipits M, Jakesz R, et al. EndoPredict improves the prognostic classification derived from common clinical guidelines in ER-positive, HER2-negative early breast cancer. Ann Oncol. 2012;24(3):640-647. doi:10.1093/annonc/mds3584. Paik S, Shak S, Tang G, et al. A multigene assay to predict recurrence of tamoxifen-treated, node-negative breast cancer. N Engl J Med. 2004;351(27):2817-2826. Citation Format: V. Aubert, V. Gaury, I. Garberis, Z. Vaquette, E. Hocquet, D. Almaraz-Klippel, F. Daidj, D. Drubay, D. Jacobs, N. Arfaoui, L. Guillou, D. Lin, J. Guillon, C. Barcenas, F. Andre, S. Krishnamurthy, M. Lacroix-Triki. Comparative performance of an AI-based digital pathology tool and genomic signatures in early ER+/HER2- breast cancer 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 PD11-04.

AI से पूछें

Bookmark