EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Simple and Robust MRI Radiomics Feature for Predicting Pathological Complete Response: A Proof‐of‐Concept Study in Breast Cancer Neoadjuvant Chemotherapy

Hongen Li iD, Li Zhang iD, Yihui Zeng iD, Yuanyuan Chen iD, Xiaosong Jiang iD, Ruoxian Zhang iD, Yan Zhang iD

Cancer Reports · 2026-05 · 9 (5)

DOI: 10.1002/cnr2.70562 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cancer Reports, online erschienen am 22.05.2026. Verfasst von Hongen Li und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Guangdong Women and Children Hospital/Women and Children's Hospital, Southern University of Science and Technology, Guangzho…. Hauptthemen laut MEDLINE: Radiomics, Neoadjuvant Therapy, Breast Neoplasms, Antineoplastic Combined Chemotherapy Protocols. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangzhou Municipal Science and Technology Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Early prediction of pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer remains challenging. This study aimed to explore the value of a radiomics model based on dynamic contrast‐enhanced magnetic resonance imaging (DCE‐MRI) acquired after the second cycle of NAC for early prediction of pCR. Methods and Results A retrospective analysis was conducted on 119 breast cancer patients who underwent NAC at our hospital between March 2020 and August 2023. Patients were categorized into pCR and non‐pCR groups based on postoperative Miller–Payne pathological grading as the gold standard. Tumor regions of interest (ROIs) were manually delineated on phase‐three DCE‐MRI sequences. PyRadiomics extracted 851 features. A rigorous dimensionality reduction process—including stability screening, intergroup differential analysis, and decorrelation analysis—yielded 88 key features. LASSO regression (10‐fold cross‐validation) ultimately selected three optimal wavelet‐based texture features that formed the core components of our radiomics signature: wavelet. LLH_glcm_Idn (inverse difference normalized), wavelet. LLH_glcm_MCC (maximum correlation coefficient), and wavelet. LHL_firstorder_Skewness. The dataset was randomly split into a training set (83 cases) and a validation set (36 cases) at a 7:3 ratio. A support vector machine (SVM) classifier was constructed, and model performance and clinical utility were evaluated using receiver operating characteristic (ROC) curves and decision curve analysis. Among 119 patients, 43(36.13%) achieved pCR. The constructed radiomics model demonstrated an area under the curve (AUC) of 0.667 and 0.647 in the training and validation sets, respectively, with accuracy rates of 66.27% and 73.49%. Decision curve analysis suggested potential clinial utility under hypothetical scenarios when the probability threshold exceeded 0.3, although this finding is exploratory and requires prospective validation.

Conclusion

This study developed and internally validated a minimalist radiomics model based on mid‐treatment MRI, demonstrating moderate and stable predictive capability for pCR after NAC in breast cancer and showing potential for aiding clinical decision‐making. As an exploratory proof‐of‐concept study, the findings underscore the necessity for future multicenter external validation and integration of multimodal features.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RadiomicsNeoadjuvant TherapyBreast NeoplasmsAntineoplastic Combined Chemotherapy ProtocolsHumansFemalePathologic Complete ResponseRetrospective StudiesDynamic Contrast Enhanced Magnetic Resonance ImagingMiddle AgedProof of Concept StudyAdultChemotherapy, AdjuvantPredictive Value of TestsBreastMagnetic Resonance ImagingROC Curve

Stichwörter der Autor:innen

breast cancercomplete pathological remissionmagnetic resonance imagingneoadjuvant chemotherapyradiomics

Autor:innen und Institutionen

  • Department of Radiology, Guangdong Women and Children Hospital/Women and Children's Hospital, Southern University of Science and Technology, Guangzhou, China.

ORCID-Profile: Hongen Li, Li Zhang, Yihui Zeng, Yuanyuan Chen, Xiaosong Jiang, Ruoxian Zhang, Yan Zhang

Förderung

  • Guangzhou Municipal Science and Technology Project

Zitieren

APA

Li, H., Zhang, L., Zeng, Y., Chen, Y., Jiang, X., Zhang, R., & Zhang, Y. (2026). A Simple and Robust MRI Radiomics Feature for Predicting Pathological Complete Response: A Proof‐of‐Concept Study in Breast Cancer Neoadjuvant Chemotherapy. Cancer Reports, 9(5). https://doi.org/10.1002/cnr2.70562

Vancouver

Li H, Zhang L, Zeng Y, Chen Y, Jiang X, Zhang R, et al. A Simple and Robust MRI Radiomics Feature for Predicting Pathological Complete Response: A Proof‐of‐Concept Study in Breast Cancer Neoadjuvant Chemotherapy. Cancer Reports. 2026;9(5). doi:10.1002/cnr2.70562

BibTeX
@article{Li2026,
  author = {Li, Hongen and Zhang, Li and Zeng, Yihui and Chen, Yuanyuan and Jiang, Xiaosong and Zhang, Ruoxian and Zhang, Yan},
  title = {A Simple and Robust MRI Radiomics Feature for Predicting Pathological Complete Response: A Proof‐of‐Concept Study in Breast Cancer Neoadjuvant Chemotherapy},
  journal = {Cancer Reports},
  year = {2026},
  volume = {9},
  number = {5},
  doi = {10.1002/cnr2.70562}
}
Kostenlos starten →