EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multiscale Feature Fusion for Skin Lesion Classification

Gang Wang iD, Pu Yan iD, Qingwei Tang, Lijuan Yang, Jie Chen

BioMed Research International · 2023

DOI: 10.1155/2023/5146543 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BioMed Research International, 2023. Verfasst von Gang Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei 230000, China. Hauptthemen laut MEDLINE: Skin Diseases, Skin Neoplasms. Die Arbeit wurde bisher 42-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Anhui Province, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skin cancer has a high mortality rate, and early detection can greatly reduce patient mortality. Convolutional neural network (CNN) has been widely applied in the field of computer‐aided diagnosis. To improve the ability of convolutional neural networks to accurately classify skin lesions, we propose a multiscale feature fusion model for skin lesion classification. We use a two‐stream network, which are a densely connected network (DenseNet‐121) and improved visual geometry group network (VGG‐16). In the feature fusion module, we construct multireceptive fields to obtain multiscale pathological information and use generalized mean pooling (GeM pooling) to reduce the spatial dimensionality of lesion features. Finally, we built and tested a system with the developed skin lesion classification model. The experiments were performed on the dataset ISIC2018, which can achieve a good classification performance with a test accuracy of 91.24% and macroaverages of 95%.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Skin DiseasesSkin NeoplasmsHumansSkinDiagnosis, Computer-AssistedNeural Networks, Computer

Autor:innen und Institutionen

  • College of Electronic and Information Engineering, Anhui Jianzhu University, Hefei 230000, China.
  • Anhui International Joint Research Center for Ancient Architecture Intellisencing and Multi-Dimensional Modeling, Anhui Jianzhu University, Hefei 230000, China.
  • Anhui Provincial Key Laboratory of Intelligent Building and Building Energy Conservation, Anhui Jianzhu University, Hefei 230000, China.

ORCID-Profile: Gang Wang, Pu Yan

Förderung

  • Natural Science Foundation of Anhui Province
  • National Natural Science Foundation of China

Zitieren

APA

Wang, G., Yan, P., Tang, Q., Yang, L., & Chen, J. (2023). Multiscale Feature Fusion for Skin Lesion Classification. BioMed Research International. https://doi.org/10.1155/2023/5146543

Vancouver

Wang G, Yan P, Tang Q, Yang L, Chen J. Multiscale Feature Fusion for Skin Lesion Classification. BioMed Research International. 2023. doi:10.1155/2023/5146543

BibTeX
@article{Wang2023,
  author = {Wang, Gang and Yan, Pu and Tang, Qingwei and Yang, Lijuan and Chen, Jie},
  title = {Multiscale Feature Fusion for Skin Lesion Classification},
  journal = {BioMed Research International},
  year = {2023},
  doi = {10.1155/2023/5146543}
}
Kostenlos starten →