EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dual scale light weight cross attention transformer for skin lesion classification

Dhirendra Prasad Yadav, Bhisham Sharma iD, Shivank Chauhan, Julian L Webber, Abolfazl Mehbodniya

PLOS ONE · 06.12.2024 · 19 (12) · e0312598

DOI: 10.1371/journal.pone.0312598 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 06.12.2024. Verfasst von Dhirendra Prasad Yadav und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering & Applications, G.L.A. University, Mathura, Uttar Pradesh, India. Hauptthemen laut MEDLINE: Neural Networks, Computer, Skin Neoplasms. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skin cancer is rapidly growing globally. In the past decade, an automated diagnosis system has been developed using image processing and machine learning. The machine learning methods require hand-crafted features, which may affect performance. Recently, a convolution neural network (CNN) was applied to dermoscopic images to diagnose skin cancer. The CNN improved its performance through its high-dimension feature extraction capability. However, these methods lack global co-relation of the spatial features. In this study, we design a dual-scale lightweight cross-attention vision transformer network (DSCATNet) that provides global attention to high-dimensional spatial features. In the DSCATNet, we extracted features from different patch sizes and performed cross-attention. The attention from different scales improved the spatial features by focusing on the different parts of the skin lesion. Furthermore, we applied a fusion strategy for the different scale spatial features. After that, enhanced features are fed to the lightweight transformer encoder for global attention. We validated the model superiority on the HAM 10000 and PAD datasets. Furthermore, the model’s performance is compared with CNN and ViT-based methods. Our DSCATNet achieved an average kappa and accuracy of 95.84% and 97.80% on the HAM 10000 dataset, respectively. Moreover,the model obtained 94.56% and 95.81% kappa and precision values on the PAD dataset.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerSkin NeoplasmsHumansMachine LearningDermoscopyImage Processing, Computer-AssistedAlgorithmsSkin

Autor:innen und Institutionen

  • Department of Computer Engineering & Applications, G.L.A. University, Mathura, Uttar Pradesh, India.
  • Centre for Research Impact & Outcome, Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura, Punjab, India.
  • Department of Electronics and Communication Engineering, Kuwait College of Science and Technology (KCST), Doha Area, Doha, Kuwait.

ORCID-Profile: Bhisham Sharma

Zitieren

APA

Yadav, D. P., Sharma, B., Chauhan, S., Webber, J. L., & Mehbodniya, A. (2024). Dual scale light weight cross attention transformer for skin lesion classification. PLOS ONE, 19(12), e0312598. https://doi.org/10.1371/journal.pone.0312598

Vancouver

Yadav DP, Sharma B, Chauhan S, Webber JL, Mehbodniya A. Dual scale light weight cross attention transformer for skin lesion classification. PLOS ONE. 2024;19(12):e0312598. doi:10.1371/journal.pone.0312598

BibTeX
@article{Yadav2024,
  author = {Yadav, Dhirendra Prasad and Sharma, Bhisham and Chauhan, Shivank and Webber, Julian L and Mehbodniya, Abolfazl},
  title = {Dual scale light weight cross attention transformer for skin lesion classification},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {12},
  pages = {e0312598},
  doi = {10.1371/journal.pone.0312598}
}
Kostenlos starten →