EUVIMEDEUVIMED entdecken
Crossref

Vision Transformer for Pretreatment Prediction of Pathologic Complete Response in Multi-center Breast DCE-MRI

Naomi Fridman, Bubby Solway, Tomer Fridman, Itamar Barnea, Anat Goldstein

Academic Radiology · 2026-10

DOI: 10.1016/j.acra.2026.09.024 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Radiology, 2026-10. Verfasst von Naomi Fridman und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Industrial Engineering and Management, Ariel University, Ariel, Israel (N.F., A.G.). Electronic address: naominoe.fridman@msmail.ariel.…. Die Arbeit nennt 34 Literaturangaben. Gefördert von: Israel Ministry of Innovation Science & Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RATIONALE AND OBJECTIVES: Pretreatment prediction of pathologic complete response (pCR) is clinically important for guiding neoadjuvant chemotherapy (NAC), but robust multi-center benchmarks with standardized evaluation protocols remain limited. We evaluated a Vision Transformer (ViT) approach for pCR prediction from breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). MATERIALS AND METHODS: We used BreastDCEDL, a public multi-center dataset comprising 2070 patients from the I-SPY1, I-SPY2, and Duke cohorts with predefined splits. Pre-contrast, early post-contrast, and late post-contrast phases were mapped to RGB channels for transfer learning from ImageNet-pretrained backbones. The held-out test set (n=175) included 32 pCR+ in I-SPY2 (99), 8 in Duke (41), and 12 in I-SPY1 (35). For I-SPY2, ViT scores were combined with clinical variables (age, HR/HER2 status, tumor volume, genomic score, treatment arm) via a Random Forest classifier. RESULTS: The ViT achieved AUC 0.72 (95% CI 0.64-0.80), sensitivity 0.27 (95% CI 0.15-0.40), and specificity 0.96 (95% CI 0.92-0.99). Performance varied across cohorts (AUC: I-SPY2 0.78, 95% CI 0.68-0.86, I-SPY1 0.68, 95% CI 0.46-0.89, Duke 0.54, 95% CI 0.27-0.80). In I-SPY2, clinical variables increased AUC to 0.85 overall (n=99), a difference that was not statistically significant (DeLong P=0.06). CONCLUSION: Cross-cohort variation highlights challenges in developing generalizable pretreatment response models under real-world heterogeneity. The high specificity supports potential utility for identifying non-responders, enabling earlier transition to alternative strategies. Code, data, and predefined splits are publicly available, establishing a reproducible benchmark.

Schlagwörter

Stichwörter der Autor:innen

Breast cancerDynamic contrast-enhanced MRINeoadjuvant chemotherapyPathologic complete responseVision Transformer

Autor:innen und Institutionen

  • Department of Industrial Engineering and Management, Ariel University, Ariel, Israel (N.F., A.G.). Electronic address: naominoe.fridman@msmail.ariel.ac.il.
  • NF Algorithms & AI, Tel Aviv, Israel (B.S., T.F., I.B.).
  • Department of Industrial Engineering and Management, Ariel University, Ariel, Israel (N.F., A.G.). Electronic address: anatgo@ariel.ac.il.

Förderung

  • Israel Ministry of Innovation Science & Technology

Zitieren

APA

Fridman, N., Solway, B., Fridman, T., Barnea, I., & Goldstein, A. (2026). Vision Transformer for Pretreatment Prediction of Pathologic Complete Response in Multi-center Breast DCE-MRI. Academic Radiology. https://doi.org/10.1016/j.acra.2026.09.024

Vancouver

Fridman N, Solway B, Fridman T, Barnea I, Goldstein A. Vision Transformer for Pretreatment Prediction of Pathologic Complete Response in Multi-center Breast DCE-MRI. Academic Radiology. 2026. doi:10.1016/j.acra.2026.09.024

BibTeX
@article{Fridman2026,
  author = {Fridman, Naomi and Solway, Bubby and Fridman, Tomer and Barnea, Itamar and Goldstein, Anat},
  title = {Vision Transformer for Pretreatment Prediction of Pathologic Complete Response in Multi-center Breast DCE-MRI},
  journal = {Academic Radiology},
  year = {2026},
  doi = {10.1016/j.acra.2026.09.024}
}
Kostenlos starten →