EUVIMEDEUVIMED entdecken
Crossref

An Evolutionary Attention-Based Network for Medical Image Classification

Hengde Zhu, Jian Wang, Shui-Hua Wang, Rajeev Raman, Juan M Górriz, Yu-Dong Zhang

International Journal of Neural Systems · 2023-03 · 33 (03)

DOI: 10.1142/s0129065723500107 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Neural Systems, online erschienen am 19.01.2023. Verfasst von Hengde Zhu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, UK. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: British Heart Foundation Accelerator Award, UK, Royal Society International Exchanges Cost Share Award, UK, Hope Foundation for Cancer Research, UK.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning has become a primary choice in medical image analysis due to its powerful representation capability. However, most existing deep learning models designed for medical image classification can only perform well on a specific disease. The performance drops dramatically when it comes to other diseases. Generalizability remains a challenging problem. In this paper, we propose an evolutionary attention-based network (EDCA-Net), which is an effective and robust network for medical image classification tasks. To extract task-related features from a given medical dataset, we first propose the densely connected attentional network (DCA-Net) where feature maps are automatically channel-wise weighted, and the dense connectivity pattern is introduced to improve the efficiency of information flow. To improve the model capability and generalizability, we introduce two types of evolution: intra- and inter-evolution. The intra-evolution optimizes the weights of DCA-Net, while the inter-evolution allows two instances of DCA-Net to exchange training experience during training. The evolutionary DCA-Net is referred to as EDCA-Net. The EDCA-Net is evaluated on four publicly accessible medical datasets of different diseases. Experiments showed that the EDCA-Net outperforms the state-of-the-art methods on three datasets and achieves comparable performance on the last dataset, demonstrating good generalizability for medical image classification.

Schlagwörter

Stichwörter der Autor:innen

Evolutionary networksattention mechanismdeep learningmedical image analysis

Autor:innen und Institutionen

  • School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, UK.
  • Department of Signal Theory, Networking and Communications, University of Granada, Granada 52005, Spain.

Förderung

  • British Heart Foundation Accelerator Award, UK
  • Royal Society International Exchanges Cost Share Award, UK
  • Hope Foundation for Cancer Research, UK
  • Medical Research Council Confidence in Concept Award, UK
  • Sino-UK Industrial Fund, UK
  • Global Challenges Research Fund (GCRF), UK
  • LIAS Pioneering Partnerships award, UK
  • Data Science Enhancement Fund, UK

Zitieren

APA

Zhu, H., Wang, J., Wang, S. H., Raman, R., Górriz, J. M., & Zhang, Y. D. (2023). An Evolutionary Attention-Based Network for Medical Image Classification. International Journal of Neural Systems, 33(03). https://doi.org/10.1142/s0129065723500107

Vancouver

Zhu H, Wang J, Wang SH, Raman R, Górriz JM, Zhang YD. An Evolutionary Attention-Based Network for Medical Image Classification. International Journal of Neural Systems. 2023;33(03). doi:10.1142/s0129065723500107

BibTeX
@article{Zhu2023,
  author = {Zhu, Hengde and Wang, Jian and Wang, Shui-Hua and Raman, Rajeev and Górriz, Juan M and Zhang, Yu-Dong},
  title = {An Evolutionary Attention-Based Network for Medical Image Classification},
  journal = {International Journal of Neural Systems},
  year = {2023},
  volume = {33},
  number = {03},
  doi = {10.1142/s0129065723500107}
}
Kostenlos starten →