AI and Cancer Research ── Breast ── 2026-11-14
Breast cancer: treatment, trials and AI
- Abstract
Upstaging from pure ductal carcinoma in situ (DCIS) to invasive carcinoma occurs in a significant proportion of patients diagnosed by core needle biopsy, which alters surgical management, particularly the need for sentinel lymph node biopsy. Although preoperative MRI is widely used to detect occult invasion, its diagnostic performance remains controversial, with reported sensitivities and specificities varying significantly across the literature. Therefore, this systematic review and meta-analysis aimed to assess the diagnostic performance of conventional MRI semantic features and MRI-based AI models in predicting the upstaging of DCIS to invasive carcinoma. The results of this study will clarify the clinical utility of MRI in preoperative risk stratification and inform future related studies.
Journal IF: unknown (could not be matched)Reference: [No authors listed]. From Conventional MRI Features to Artificial Intelligence: A Systematic Review and Meta-analysis of MRI Predictors for Occult Invasion in Biopsy-confirmed Ductal Carcinoma in Situ. Open Science Framework. [Epub ahead of print]. doi:10.17605/osf.io/7qgmd.Checked: Abstract only - Abstract
Accurate molecular subtyping of breast cancer is essential for personalized therapy, yet inconsistencies between biopsy and postoperative immunohistochemistry (IHC) due to tumor heterogeneity and sampling limitations pose clinical challenges. We developed Ultrasound-Guided Pathomic Subtyping (US-GPS), a cross-modal framework enabling subtype prediction using ultrasound (US) alone, guided by IHC-stained whole-slide images (WSIs) during training. A total of 1283 patients from four centers were retrospectively included, with 454 cases (paired US and WSIs) for model training/validation and 829 US-only cases for external testing. US-GPS aligned WSI-derived patch- and region-level features (from HER2, ER, PR, Ki-67 IHC stains) with handcrafted and deep US features via co-attention and contrastive learning. Using US alone, the model achieved an AUROC of 0. 966 (95% CI 0.960-0.991) in internal validation, comparable to pathology-only (0. 971) and joint models (0.980), and superior to US-only (0.861). Performance remained robust across both internal (AUROC range: 0.930-0.942) and all external cohorts (AUROC range: 0.915-0.963). US-GPS enables scalable, non-invasive, and interpretable subtype classification, with potential for both pre-treatment decision-making and longitudinal monitoring of molecular phenotypic shifts.
Journal IF-equivalent: 9.8 (OpenAlex 2-year mean citedness, value as of 2026-11-04, retrieved 2026-11-05; not the official Clarivate IF)Reference: Zou WJ, Zheng LF, Feng BJ, Yao JC, Wu YX, Lv LJ, et al. Ultrasound-guided deep learning framework with whole slide images for molecular subtyping of breast cancer: a multicentre, retrospective study. NPJ Precis Oncol. 2026 Jul 22;10(1):435. doi:10.1038/s41698-026-01612-w. PMID: 43015298.Checked: Abstract only