EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

K‐means clustering‐based analysis of quantitative ultrafast DCE‐MRI for predicting breast cancer response to neoadjuvant chemotherapy

Zhen Ren iD, Xiaobing Fan iD, Milica Medved, Frederick M Howard, Rita Nanda, Hiroyuki Abe, Kirti Kulkarni, Anna Biernacka, Nan Chen, Gregory S Karczmar

Journal of Applied Clinical Medical Physics · 2026-01 · 27 (1)

DOI: 10.1002/acm2.70439 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Clinical Medical Physics, online erschienen am 28.12.2025. Verfasst von Zhen Ren und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, The University of Chicago, Chicago, Illinois, USA. Hauptthemen laut MEDLINE: Breast Neoplasms, Neoadjuvant Therapy, Magnetic Resonance Imaging, Contrast Media. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Cancer Institute of the National Institutes of Health, the University of Chicago Cancer Center, the Breast Cancer Research Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Achieving a pathologic complete response (pCR) following neoadjuvant chemotherapy (NAC) is strongly associated with improved survival. This study investigates whether bilateral asymmetry of quantitative perfusion parameters in normal parenchyma from ultrafast dynamic contrast‐enhanced MRI (DCE‐MRI), measured using k‐means clustering (KMC) before NAC, can predict pCR in breast cancer patients. Materials and methods Fifty‐six breast cancer patients undergoing NAC with pretreatment ultrafast DCE‐MRI (3–9 s/image at 3T) were enrolled. KMC was used to classify tumor and normal parenchymal voxels into five clusters based on maximum enhancement rate ( A·α ). Ipsilateral‐to‐contralateral (I/C) ratios of background parenchymal enhancement kinetics (kBPE) and tumor kinetics (kT) were compared between pCR and nonpCR groups. Logistic regression models were developed to predict pCR. Statistical tests included bootstrapping, z‐test, chi‐square, and Wilcoxon rank‐sum.

Results

Patients with residual disease showed significantly higher kBPE in the normal‐appearing parenchyma of the ipsilateral breast compared to the contralateral side. Parameters including enhancement rate α, A·α , area under the enhancement curve for 30 s AUC30 , volume transfer constant K tran s , and rate constant of contrast transfer, K ep , were significantly higher, while extravascular extracellular space fractional volume, v e , was significantly lower in the ipsilateral breast parenchyma versus contralateral breast parenchyma for women who have residual disease ( p < 0.05). A prediction model using kBPE asymmetry alone achieved an area under the curve (AUC) of 0.83. Including tumor kinetics improved the AUC to 0.85.

Conclusions

Bilateral asymmetry of kBPE parameters derived from ultrafast DCE‐MRI using KMC before NAC initiation can predict pCR with high accuracy, providing a new minimal‐invasive biomarker for treatment response.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsNeoadjuvant TherapyMagnetic Resonance ImagingContrast MediaImage Processing, Computer-AssistedHumansFemaleMiddle AgedAdultAgedCluster AnalysisPrognosisAntineoplastic Combined Chemotherapy ProtocolsRetrospective StudiesDynamic Contrast Enhanced Magnetic Resonance Imaging

Stichwörter der Autor:innen

bilateral parenchymal enhancement asymmetrybreast cancerdynamic contrast enhanced magnetic resonance imagingk‐means clusteringneoadjuvant chemotherapy

Substanzen

Contrast Media

Autor:innen und Institutionen

  • Department of Radiology, The University of Chicago, Chicago, Illinois, USA.
  • Section of Hematology and Oncology, Department of Medicine, The University of Chicago, Chicago, Illinois, USA.
  • Department of Pathology, The University of Chicago, Chicago, Illinois, USA.

ORCID-Profile: Zhen Ren, Xiaobing Fan

Förderung

  • National Cancer Institute of the National Institutes of Health
  • the University of Chicago Cancer Center
  • the Breast Cancer Research Foundation
  • NCI NIH HHS
  • CAPSBRACA
  • Cancer Prevention and Research Institute of Texas
  • Dr. Olufunmilayo Olopade
  • Doris Duke Charitable Foundation

Zitieren

APA

Ren, Z., Fan, X., Medved, M., Howard, F. M., Nanda, R., Abe, H., Kulkarni, K., Biernacka, A., Chen, N., & Karczmar, G. S. (2026). K‐means clustering‐based analysis of quantitative ultrafast DCE‐MRI for predicting breast cancer response to neoadjuvant chemotherapy. Journal of Applied Clinical Medical Physics, 27(1). https://doi.org/10.1002/acm2.70439

Vancouver

Ren Z, Fan X, Medved M, Howard FM, Nanda R, Abe H, et al. K‐means clustering‐based analysis of quantitative ultrafast DCE‐MRI for predicting breast cancer response to neoadjuvant chemotherapy. Journal of Applied Clinical Medical Physics. 2026;27(1). doi:10.1002/acm2.70439

BibTeX
@article{Ren2026,
  author = {Ren, Zhen and Fan, Xiaobing and Medved, Milica and Howard, Frederick M and Nanda, Rita and Abe, Hiroyuki and Kulkarni, Kirti and Biernacka, Anna and Chen, Nan and Karczmar, Gregory S},
  title = {K‐means clustering‐based analysis of quantitative ultrafast DCE‐MRI for predicting breast cancer response to neoadjuvant chemotherapy},
  journal = {Journal of Applied Clinical Medical Physics},
  year = {2026},
  volume = {27},
  number = {1},
  doi = {10.1002/acm2.70439}
}
Kostenlos starten →