EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Deep learning framework for breast cancer subtypes detection and diagnosis

João Pedro Pereira Fontes, Evandro Neves Fonseca, António Carlos Ferreira Pinto, Luís Gonzaga Mendes Magalhães, Teresa Gonçalves, Maria João Martins, Vitor Rigueira, Pedro Miguel da Costa Santos Ferreira, Luis Filipe Rafael Branco, Filipe Seixo, Miguel Angel Guevara Lopez

Biomedical Signal Processing and Control · 2027-02 · 130 · 111532

DOI: 10.1016/j.bspc.2026.111532 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Signal Processing and Control, 2027-02. Verfasst von João Pedro Pereira Fontes und 10 weiteren Autor:innen. Die Arbeit nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Foundation for Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Molecular subtyping of breast cancer serves as a cornerstone for personalised diagnosis and therapeutic monitoring; nevertheless, the deployment of advanced deep learning models is often hindered by the lack of accurate tumour segmentations in extensive datasets and the intrinsic class imbalance among molecular subtypes, particularly the under-representation of the HER2-enriched subtype in public archives. This study introduces a comprehensive and practical pipeline for characterising breast cancer phenotypes, effectively addressing these challenges. We have collected publicly accessible images belonging to breast cancer from different datasets using magnetic resonance imaging, encompassing categorised molecular subtypes, with or without manual tumour segmentations. Using a 3D Convolutional Neural Network (3D CNN) model trained exclusively on the Duke Breast Cancer MRI dataset, which contains bounding box annotations and molecular subtypes, we developed a robust classifier. To extend our analysis to data without annotations, we applied a Faster R-CNN model, pre-trained on the same Duke dataset, to generate lesion detections in the remaining multicentric datasets. From these, we strategically selected a balanced subset of 200 cases (50 for each phenotype: Luminal A, Luminal B, HER2-enriched and Triple-Negative), based on the highest detection confidence, thus solving the class imbalance problem and ensuring equitable representation of all subtypes for rigorous testing of our classifier. The final validation was performed on an independent clinical dataset from a public hospital in Setúbal, Portugal, where the model demonstrated strong discriminative performance with AUC-ROC values ranging from 0.8786 to 0.9825 across the four molecular subtypes, providing promising evidence of cross-institutional generalisation under a pronounced subtype prior shift between the North American training distribution and the Portuguese evaluation cohort. This work, complemented by a data anonymisation system and close collaboration with clinical specialists, establishes a scalable and effective methodology for precision radiogenomics that simultaneously overcomes the challenges of data imbalance and the absence of detailed annotations. Further multi-site prospective validation on larger and ethnically diverse cohorts is required before clinical deployment.

Förderung

  • Foundation for Science and Technology

Zitieren

APA

Fontes, J. P. P., Fonseca, E. N., Pinto, A. C. F., Magalhães, L. G. M., Gonçalves, T., Martins, M. J., Rigueira, V., Ferreira, P. M. D. C. S., Branco, L. F. R., Seixo, F., & Lopez, M. A. G. (2027). Deep learning framework for breast cancer subtypes detection and diagnosis. Biomedical Signal Processing and Control, 130, 111532. https://doi.org/10.1016/j.bspc.2026.111532

Vancouver

Fontes JPP, Fonseca EN, Pinto ACF, Magalhães LGM, Gonçalves T, Martins MJ, et al. Deep learning framework for breast cancer subtypes detection and diagnosis. Biomedical Signal Processing and Control. 2027;130:111532. doi:10.1016/j.bspc.2026.111532

BibTeX
@article{Fontes2027,
  author = {Fontes, João Pedro Pereira and Fonseca, Evandro Neves and Pinto, António Carlos Ferreira and Magalhães, Luís Gonzaga Mendes and Gonçalves, Teresa and Martins, Maria João and Rigueira, Vitor and Ferreira, Pedro Miguel da Costa Santos and Branco, Luis Filipe Rafael and Seixo, Filipe and Lopez, Miguel Angel Guevara},
  title = {Deep learning framework for breast cancer subtypes detection and diagnosis},
  journal = {Biomedical Signal Processing and Control},
  year = {2027},
  volume = {130},
  pages = {111532},
  doi = {10.1016/j.bspc.2026.111532}
}
Kostenlos starten →