Breast Cancer: Habitat imaging based on intravoxel incoherent motion for predicting pathologic complete response to neoadjuvant chemotherapy
Brustkrebs: Habitat-Bildgebung auf Basis von intravoxel incoherent motion zur Vorhersage einer pathologischen Komplettremission nach neoadjuvanter Chemotherapie
Medical Physics · 2025-06 · 52 (6) · 3711-3722
DOI: 10.1002/mp.17813 ↗Auf einen Blick
Bei 143 Frauen mit Stadium II–III sagte ein Modell auf Basis von Habitat-Bildgebung die pathologische Komplettremission vor NAC vorher. In der Testgruppe erreichte das kombinierte Modell eine AUC von 0,891.
Fragestellung
Können aus Habitat-Bildgebung abgeleitete Merkmale Frauen mit Brustkrebs identifizieren, die von neoadjuvanter Chemotherapie profitieren?
Methode
143 Frauen mit Stadium II–III; 3-T-MRT vor NAC; Modelle auf Basis von Whole-tumor-Radiomics, IVIM-Habitat-Bildgebung, konventionellen MRI-Merkmalen und IHC; Vergleich per ROC/AUC, DCA und DeLong-Test.
Ergebnisse
Trainingssatz/Testsatz-AUCs: WH 0,895/0,549; Habitats 0,757/0,708; CF 0,705/0,700; IHC 0,807/0,788; Habitats+CF 0,800/0,745; CF+IHC 0,856/0,909; Habitats+CF+IHC 0,891/0,891. IHC vs. Habitats+CF: p=0,695; Habitats+CF+IHC vs. CF+IHC: p=0,382; IHC vs. Habitats+CF+IHC: p=0,043.
Schlussfolgerung der Autor:innen
Das aus First-order-Features, konventionellen MRI-Merkmalen und IHC-Funden gebildete Habitat-Modell sagte pCR vor NAC genau voraus und kann die individualisierte Therapieentscheidung unterstützen.
Kernaussagen
- 143 Frauen mit Stadium II–III wurden vor NAC per 3-T-MRT untersucht.
- Das kombinierte Modell Habitats+CF+IHC erreichte im Testsatz eine AUC von 0,891.
- Zwischen IHC und Habitats+CF+IHC bestand ein signifikanter Unterschied (p=0,043).
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, online erschienen am 11.04.2025. Verfasst von Hui Zhang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Shengli Clinical College of Fujian Medical University & Department of Surgical Oncology, Fujian Provincial Hospital, Fuzhou University Affiliated Pro…. Hauptthemen laut MEDLINE: Breast Neoplasms, Neoadjuvant Therapy, Magnetic Resonance Imaging, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Joint Funds for the innovation of science and Technology, Fujian province, Natural Science Foundation of Fujian Province of China, Young and Middle-aged Talents Training Project of Fujian Provincial Health Commission.
Themen: Onkologische Pflege
Abstract (Originalsprache)
Background
Radiomics research based on whole tumors is limited by the unclear biological significance of radiomics features, which therefore lack clinical interpretability.
Purpose
We aimed to determine whether features extracted from subregions defined by habitat imaging, reflecting tumor heterogeneity, could identify breast cancer patients who will benefit from neoadjuvant chemotherapy (NAC), to optimize treatment.
Methods
143 women with stage II–III breast cancer were divided into a training set (100 patients, 36 with pathologic complete response [pCR]) and a test set (43 patients, 16 with pCR). Patients underwent 3‐T magnetic resonance imaging (MRI) before NAC. With the pathological results as the gold standard, we used the training set to build models for predicting pCR based on whole‐tumor radiomics (Model WH ), intravoxel incoherent motion (IVIM)‐based habitat imaging (Model Habitats ), conventional MRI features (Model CF ), and immunohistochemical findings (Model IHC ). We also built the combined models Model Habitats+CF and Model Habitats+CF+IHC . In the test set, we compared the performance of the combined models with that of the invasive Model IHC by using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). Receiver operating characteristic (ROC) curve analysis was performed to evaluate the predictive value of the model. The DeLong test was used to compare diagnostic efficiency across different parameters.
Results
In the prediction of pCR, Model WH , Model Habitats , Model CF , Model IHC , Model Habitats+CF , Model CF+IHC and Model Habitats+CF+IHC achieved AUCs of 0.895, 0.757, 0.705, 0.807, 0.800, 0.856, and 0.891 respectively, in the training set and 0.549, 0.708, 0.700, 0.788, 0.745, 0.909, and 0.891 respectively, in the test set. The DeLong test revealed no significant difference between Model IHC versus Model Habitats+CF ( p = 0.695) and Model Habitats+CF+IHC versus Model CF+IHC ( p = 0.382) but showed a significant difference between Model IHC and Model Habitats+CF+IHC ( p = 0.043).
Conclusion
The habitat model we established from first‐order features combined with conventional MRI features and IHC findings accurately predicted pCR before NAC. This model can facilitate decision‐making during individualized treatment for breast cancer.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Shengli Clinical College of Fujian Medical University & Department of Surgical Oncology, Fujian Provincial Hospital, Fuzhou University Affiliated Provincial Hospital, Fuzhou, China.
- Shengli Clinical College of Fujian Medical University & Department of Radiology, Fujian Provincial Hospital, Fuzhou University Affiliated Provincial Hospital, Fuzhou, China.
- Shanghai Key Laboratory of Magnetic Resonance, East China Normal University, Shanghai, China.
- MR Scientific Marketing, Siemens Healthineers Ltd., Shanghai, China.
Förderung
- Joint Funds for the innovation of science and Technology, Fujian province
- Natural Science Foundation of Fujian Province of China
- Young and Middle-aged Talents Training Project of Fujian Provincial Health Commission
- Joint Funds for the Innovation of Science and Technology of Fujian Province, China
Zitieren
APA
Zhang, H., Zheng, Y., Zhang, M., Wang, A., Song, Y., Wang, C., Yang, G., Ma, M., & He, M. (2025). Breast Cancer: Habitat imaging based on intravoxel incoherent motion for predicting pathologic complete response to neoadjuvant chemotherapy. Medical Physics, 52(6), 3711-3722. https://doi.org/10.1002/mp.17813
Vancouver
Zhang H, Zheng Y, Zhang M, Wang A, Song Y, Wang C, et al. Breast Cancer: Habitat imaging based on intravoxel incoherent motion for predicting pathologic complete response to neoadjuvant chemotherapy. Medical Physics. 2025;52(6):3711-3722. doi:10.1002/mp.17813
BibTeX
@article{Zhang2025,
author = {Zhang, Hui and Zheng, Yunyan and Zhang, Mingzhe and Wang, Ailing and Song, Yang and Wang, Chenglong and Yang, Guang and Ma, Mingping and He, Muzhen},
title = {Breast Cancer: Habitat imaging based on intravoxel incoherent motion for predicting pathologic complete response to neoadjuvant chemotherapy},
journal = {Medical Physics},
year = {2025},
volume = {52},
number = {6},
pages = {3711--3722},
doi = {10.1002/mp.17813}
}
EUVIMED