EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Combining Gabor-local and contextual-global deep features for cholesteatoma classification

Jianqing Chen, Guokai Zhang iD, Yanran Wang, Yuqing Sun

Science Progress · 2026-04 · 109 (2)

DOI: 10.1177/00368504261451406 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Progress, online erschienen am 12.05.2026. Verfasst von Jianqing Chen und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Otolaryngology, Head & Neck Surgery, Shanghai Ninth People's Hospital, Affiliated to Shanghai Jiaotong University School of Medicine, S…. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Shanghai Jiao Tong University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A key challenge in classifying cholesteatoma images lies in the effective extraction and integration of both local and global features. This paper addresses this challenge by introducing a Gabor-local and contextual-global network. This network enhances local feature extraction through the incorporation of Gabor filtering alongside a ResNet architecture, which captures richer local information at varying scales and orientations. Moreover, the attention mechanism generates an importance score map, enabling the network to dynamically focus on the most relevant regions within the input image by normalizing scores into a weight matrix and supporting Generalized-Mean (GeM) pooling, resulting in a more robust global descriptor. Finally, a novel dynamic feature fusion strategy combines local features, global features, and outputs from the last residual block based on their computed importance scores, further enhancing the model’s overall performance. Experimental results show the network’s superior performance, effectively leveraging both local and global information for enhanced classification outcomes.

Schlagwörter

Stichwörter der Autor:innen

cholesteatomadynamic feature fusionglobal featurelocal feature

Autor:innen und Institutionen

  • Department of Otolaryngology, Head & Neck Surgery, Shanghai Ninth People's Hospital, Affiliated to Shanghai Jiaotong University School of Medicine, Shanghai, China.
  • School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, China.
  • Department of Otolaryngology, Head and Neck Surgery, Zibo Central Hospital, Zibo, China.

ORCID-Profile: Guokai Zhang

Förderung

  • Shanghai Jiao Tong University

Zitieren

APA

Chen, J., Zhang, G., Wang, Y., & Sun, Y. (2026). Combining Gabor-local and contextual-global deep features for cholesteatoma classification. Science Progress, 109(2). https://doi.org/10.1177/00368504261451406

Vancouver

Chen J, Zhang G, Wang Y, Sun Y. Combining Gabor-local and contextual-global deep features for cholesteatoma classification. Science Progress. 2026;109(2). doi:10.1177/00368504261451406

BibTeX
@article{Chen2026,
  author = {Chen, Jianqing and Zhang, Guokai and Wang, Yanran and Sun, Yuqing},
  title = {Combining Gabor-local and contextual-global deep features for cholesteatoma classification},
  journal = {Science Progress},
  year = {2026},
  volume = {109},
  number = {2},
  doi = {10.1177/00368504261451406}
}
Kostenlos starten →