EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Mixed‐decomposed convolutional network: A lightweight yet efficient convolutional neural network for ocular disease recognition

Xiaoqing Zhang, Xiao Wu, Zunjie Xiao, Lingxi Hu, Zhongxi Qiu, Qingyang Sun, Risa Higashita, Jiang Liu

CAAI Transactions on Intelligence Technology · 2024-04 · 9 (2) · 319-332

DOI: 10.1049/cit2.12246 ↗

Kurz gefasst

Fachartikel in der Zeitschrift CAAI Transactions on Intelligence Technology, online erschienen am 04.06.2023. Verfasst von Xiaoqing Zhang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Eye health has become a global health concern and attracted broad attention. Over the years, researchers have proposed many state‐of‐the‐art convolutional neural networks (CNNs) to assist ophthalmologists in diagnosing ocular diseases efficiently and precisely. However, most existing methods were dedicated to constructing sophisticated CNNs, inevitably ignoring the trade‐off between performance and model complexity. To alleviate this paradox, this paper proposes a lightweight yet efficient network architecture, mixed‐decomposed convolutional network (MDNet), to recognise ocular diseases. In MDNet, we introduce a novel mixed‐decomposed depthwise convolution method, which takes advantage of depthwise convolution and depthwise dilated convolution operations to capture low‐resolution and high‐resolution patterns by using fewer computations and fewer parameters. We conduct extensive experiments on the clinical anterior segment optical coherence tomography (AS‐OCT), LAG, University of California San Diego, and CIFAR‐100 datasets. The results show our MDNet achieves a better trade‐off between the performance and model complexity than efficient CNNs including MobileNets and MixNets. Specifically, our MDNet outperforms MobileNets by 2.5% of accuracy by using 22% fewer parameters and 30% fewer computations on the AS‐OCT dataset.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhang, X., Wu, X., Xiao, Z., Hu, L., Qiu, Z., Sun, Q., Higashita, R., & Liu, J. (2024). Mixed‐decomposed convolutional network: A lightweight yet efficient convolutional neural network for ocular disease recognition. CAAI Transactions on Intelligence Technology, 9(2), 319-332. https://doi.org/10.1049/cit2.12246

Vancouver

Zhang X, Wu X, Xiao Z, Hu L, Qiu Z, Sun Q, et al. Mixed‐decomposed convolutional network: A lightweight yet efficient convolutional neural network for ocular disease recognition. CAAI Transactions on Intelligence Technology. 2024;9(2):319-332. doi:10.1049/cit2.12246

BibTeX
@article{Zhang2024,
  author = {Zhang, Xiaoqing and Wu, Xiao and Xiao, Zunjie and Hu, Lingxi and Qiu, Zhongxi and Sun, Qingyang and Higashita, Risa and Liu, Jiang},
  title = {Mixed‐decomposed convolutional network: A lightweight yet efficient convolutional neural network for ocular disease recognition},
  journal = {CAAI Transactions on Intelligence Technology},
  year = {2024},
  volume = {9},
  number = {2},
  pages = {319--332},
  doi = {10.1049/cit2.12246}
}
Kostenlos starten →