EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

MRI-based texture analysis for breast cancer subtype classification in a multi-ethnic population

Nazimah Ab Mumin, Chuin-Hen Liew, Song-Quan Ong, Jeannie Hsiu Ding Wong, Marlina Tanty Ramli Hamid, Kartini Rahmat, Kwan Hoong Ng

Magnetic Resonance Materials in Physics, Biology and Medicine · 2025

DOI: 10.1007/s10334-025-01285-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance Materials in Physics, Biology and Medicine, 2025. Verfasst von Nazimah Ab Mumin und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Faculty of Medicine, Universiti Teknologi MARA, 47000, Sungai Buloh, Selangor, Malaysia. nazimah_mumin@uitm.edu.my. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Breast Neoplasms. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Kementerian Sains, Teknologi dan Inovasi, Universiti Teknologi MARA.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

INTRODUCTION: Breast cancer, the most prevalent cancer among women globally, is classified into molecular subtypes (luminal, HER2-enriched, and triple-negative) to guide treatment and prognosis. Traditional subtyping methods, such as gene profiling and immunohistochemistry, are invasive and limited by intratumoural heterogeneity. MRI radiomics analysis offers a non-invasive alternative by extracting quantitative imaging features, yet its application in diverse, multi-ethnic populations remains underexplored. OBJECTIVE: This study aimed to identify predictive radiomic features from multiple MRI sequences to classify breast cancer subtypes, compare the performance of four MRI sequences, and determine the optimal machine learning (ML) model for this task. A total of 162 retrospective breast cancer MRI cases were semi-automatically segmented, and 256 radiomic features were extracted. A multimodal ML framework integrating random forest and recursive feature elimination was developed to identify the most predictive features based on the area under the receiver operating characteristic curve (AUROC). RESULTS: Key predictive features included age, tumour size, margin characteristics, and intensity patterns within the tumour. Among MRI sequences, inversion recovery and T1 post-contrast performed best for subtyping. In addition, texture-based ML models effectively emulated visual assessment, demonstrating the potential of radiomics in non-invasive breast cancer subtyping. With the top ten features, the AUROC values are 0.735, 0.630, and 0.747 for luminal, HER2-enriched, and triple-negative, respectively. CONCLUSION: These findings highlight the role of MRI-based texture features and advanced ML in enhancing breast cancer diagnosis, offering a non-invasive tool for personalised treatment planning while complementing existing clinical workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingBreast NeoplasmsHumansFemaleMachine LearningMiddle AgedRetrospective StudiesROC CurveAdultAgedEthnicityAlgorithmsArea Under CurveImage Processing, Computer-AssistedImage Interpretation, Computer-AssistedPrognosis

Stichwörter der Autor:innen

BreastBreast neoplasmLuminal, HER2-enriched, Triple-negative breast cancerMachine learningMagnetic resonance imaging

Autor:innen und Institutionen

  • Department of Radiology, Faculty of Medicine, Universiti Teknologi MARA, 47000, Sungai Buloh, Selangor, Malaysia. nazimah_mumin@uitm.edu.my.
  • Department of Biomedical Imaging, Faculty of Medicine, Universiti Malaya, 50603, Kuala Lumpur, Malaysia. nazimah_mumin@uitm.edu.my.
  • Hospital Tuanku Ampuan Najihah, Ministry of Health, 72000, Kuala Pilah, Negeri Sembilan, Malaysia.
  • Institute For Tropical Biology and Conservation, University Malaysia Sabah, 88400, Kota Kinabalu, Sabah, Malaysia.
  • Department of Biomedical Imaging, Faculty of Medicine, Universiti Malaya, 50603, Kuala Lumpur, Malaysia.
  • Department of Radiology, Faculty of Medicine, Universiti Teknologi MARA, 47000, Sungai Buloh, Selangor, Malaysia.

Förderung

  • Kementerian Sains, Teknologi dan Inovasi
  • Universiti Teknologi MARA

Zitieren

APA

Ab Mumin, N., Liew, C. H., Ong, S. Q., Wong, J. H. D., Ramli Hamid, M. T., Rahmat, K., & Ng, K. H. (2025). MRI-based texture analysis for breast cancer subtype classification in a multi-ethnic population. Magnetic Resonance Materials in Physics, Biology and Medicine. https://doi.org/10.1007/s10334-025-01285-9

Vancouver

Ab Mumin N, Liew CH, Ong SQ, Wong JHD, Ramli Hamid MT, Rahmat K, et al. MRI-based texture analysis for breast cancer subtype classification in a multi-ethnic population. Magnetic Resonance Materials in Physics, Biology and Medicine. 2025. doi:10.1007/s10334-025-01285-9

BibTeX
@article{AbMumin2025,
  author = {Ab Mumin, Nazimah and Liew, Chuin-Hen and Ong, Song-Quan and Wong, Jeannie Hsiu Ding and Ramli Hamid, Marlina Tanty and Rahmat, Kartini and Ng, Kwan Hoong},
  title = {MRI-based texture analysis for breast cancer subtype classification in a multi-ethnic population},
  journal = {Magnetic Resonance Materials in Physics, Biology and Medicine},
  year = {2025},
  doi = {10.1007/s10334-025-01285-9}
}
Kostenlos starten →