EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Exploiting Patch Sizes and Resolutions for Multi-Scale Deep Learning in Mammogram Image Classification

Gonzalo Iñaki Quintana iD, Zhijin Li, Laurence Vancamberg, Mathilde Mougeot, Agnès Desolneux, Serge Muller

Bioengineering · 27.04.2023 · 10 (5) · 534

DOI: 10.3390/bioengineering10050534 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 27.04.2023. Verfasst von Gonzalo Iñaki Quintana und 5 weiteren Autor:innen. Beteiligte Einrichtung: GE HealthCare, 283 Rue de la Minière, 78530 Buc, France. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: ANRT under CIFRE.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent progress in deep learning (DL) has revived the interest on DL-based computer aided detection or diagnosis (CAD) systems for breast cancer screening. Patch-based approaches are one of the main state-of-the-art techniques for 2D mammogram image classification, but they are intrinsically limited by the choice of patch size, as there is no unique patch size that is adapted to all lesion sizes. In addition, the impact of input image resolution on performance is not yet fully understood. In this work, we study the impact of patch size and image resolution on the classifier performance for 2D mammograms. To leverage the advantages of different patch sizes and resolutions, a multi patch-size classifier and a multi-resolution classifier are proposed. These new architectures perform multi-scale classification by combining different patch sizes and input image resolutions. The AUC is increased by 3% on the public CBIS-DDSM dataset and by 5% on an internal dataset. Compared with a baseline single patch size and single resolution classifier, our multi-scale classifier reaches an AUC of 0.809 and 0.722 in each dataset.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencebreast imagingcomputer aided detection or diagnosis (CAD)convolutional neural networks (CNNs)deep learningmulti-scale classification

Autor:innen und Institutionen

  • GE HealthCare, 283 Rue de la Minière, 78530 Buc, France.
  • ENS Paris-Saclay, Centre Borelli, 91190 Gif-sur-Yvette, France.

ORCID-Profile: Gonzalo Iñaki Quintana

Förderung

  • ANRT under CIFRE

Zitieren

APA

Quintana, G. I., Li, Z., Vancamberg, L., Mougeot, M., Desolneux, A., & Muller, S. (2023). Exploiting Patch Sizes and Resolutions for Multi-Scale Deep Learning in Mammogram Image Classification. Bioengineering, 10(5), 534. https://doi.org/10.3390/bioengineering10050534

Vancouver

Quintana GI, Li Z, Vancamberg L, Mougeot M, Desolneux A, Muller S. Exploiting Patch Sizes and Resolutions for Multi-Scale Deep Learning in Mammogram Image Classification. Bioengineering. 2023;10(5):534. doi:10.3390/bioengineering10050534

BibTeX
@article{Quintana2023,
  author = {Quintana, Gonzalo Iñaki and Li, Zhijin and Vancamberg, Laurence and Mougeot, Mathilde and Desolneux, Agnès and Muller, Serge},
  title = {Exploiting Patch Sizes and Resolutions for Multi-Scale Deep Learning in Mammogram Image Classification},
  journal = {Bioengineering},
  year = {2023},
  volume = {10},
  number = {5},
  pages = {534},
  doi = {10.3390/bioengineering10050534}
}
Kostenlos starten →