EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Attention-guided erasing for enhanced transfer learning in breast abnormality classification

Adarsh Bhandary Panambur iD, Sheethal Bhat, Hui Yu, Prathmesh Madhu, Siming Bayer, Andreas Maier

International Journal of Computer Assisted Radiology and Surgery · 2025

DOI: 10.1007/s11548-024-03317-6 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Computer Assisted Radiology and Surgery, 2025. Verfasst von Adarsh Bhandary Panambur und 5 weiteren Autor:innen. Beteiligte Einrichtung: Siemens Healthineers, Karl Heinz Kaske Str. 5, 91052, Erlangen, Bayern, Germany. adarsh.bhandary.panambur@fau.de. Hauptthemen laut MEDLINE: Breast Neoplasms, Mammography, Radiographic Image Interpretation, Computer-Assisted, Machine Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Friedrich-Alexander-Universität Erlangen-Nürnberg.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Breast cancer remains one of the most prevalent cancers globally, necessitating effective early screening and diagnosis. This study investigates the effectiveness and generalizability of our recently proposed data augmentation technique, attention-guided erasing (AGE), across various transfer learning classification tasks for breast abnormality classification in mammography.

Methods

AGE utilizes attention head visualizations from DINO self-supervised pretraining to weakly localize regions of interest (ROI) in images. These localizations are then used to stochastically erase non-essential background information from training images during transfer learning. Our research evaluates AGE across two image-level and three patch-level classification tasks. The image-level tasks involve breast density categorization in digital mammography (DM) and malignancy classification in contrast-enhanced mammography (CEM). Patch-level tasks include classifying calcifications and masses in scanned film mammography (SFM), as well as malignancy classification of ROIs in CEM.

Results

AGE significantly boosts classification performance with statistically significant improvements in mean F1-scores across four tasks compared to baselines. Specifically, for image-level classification of breast density in DM and malignancy in CEM, we achieve gains of 2% and 1.5%, respectively. Additionally, for patch-level classification of calcifications in SFM and CEM ROIs, gains of 0.4% and 0.6% are observed, respectively. However, marginal improvement is noted in the mass classification task, indicating the necessity for further optimization in tasks where critical features may be obscured by erasing techniques.

Conclusion

Our findings underscore the potential of AGE, a dataset- and task-specific augmentation strategy powered by self-supervised learning, to enhance the downstream classification performance of DL models, particularly involving ViTs, in medical imaging.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsMammographyRadiographic Image Interpretation, Computer-AssistedMachine LearningHumansFemaleBreastMiddle AgedContrast Media

Stichwörter der Autor:innen

Breast cancerData augmentationMammographySelf-supervised learningTransfer learning

Substanzen

Contrast Media

Autor:innen und Institutionen

  • Siemens Healthineers, Karl Heinz Kaske Str. 5, 91052, Erlangen, Bayern, Germany. adarsh.bhandary.panambur@fau.de.
  • Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nuremberg, Martensstr. 3, 91058, Erlangen, Bayern, Germany. adarsh.bhandary.panambur@fau.de.
  • Siemens Healthineers, Karl Heinz Kaske Str. 5, 91052, Erlangen, Bayern, Germany.
  • Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nuremberg, Martensstr. 3, 91058, Erlangen, Bayern, Germany.

ORCID-Profile: Adarsh Bhandary Panambur

Förderung

  • Friedrich-Alexander-Universität Erlangen-Nürnberg

Zitieren

APA

Panambur, A. B., Bhat, S., Yu, H., Madhu, P., Bayer, S., & Maier, A. (2025). Attention-guided erasing for enhanced transfer learning in breast abnormality classification. International Journal of Computer Assisted Radiology and Surgery. https://doi.org/10.1007/s11548-024-03317-6

Vancouver

Panambur AB, Bhat S, Yu H, Madhu P, Bayer S, Maier A. Attention-guided erasing for enhanced transfer learning in breast abnormality classification. International Journal of Computer Assisted Radiology and Surgery. 2025. doi:10.1007/s11548-024-03317-6

BibTeX
@article{Panambur2025,
  author = {Panambur, Adarsh Bhandary and Bhat, Sheethal and Yu, Hui and Madhu, Prathmesh and Bayer, Siming and Maier, Andreas},
  title = {Attention-guided erasing for enhanced transfer learning in breast abnormality classification},
  journal = {International Journal of Computer Assisted Radiology and Surgery},
  year = {2025},
  doi = {10.1007/s11548-024-03317-6}
}
Kostenlos starten →