EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient deep learning model for classifying lung cancer images using normalized stain agnostic feature method and FastAI-2

Pranshu Saxena iD, Sanjay Kumar Singh, Mamoon Rashid, Sultan S Alshamrani iD, Mrim M Alnfiai iD

PeerJ Computer Science · 27.05.2025 · 11 · e2903

DOI: 10.7717/peerj-cs.2903 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 27.05.2025. Verfasst von Pranshu Saxena und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science Engineering and Technology, Bennett University, Greater Noida, India. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Taif University, Saudi Arabia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Lung cancer has the highest global fatality rate, with diagnosis primarily relying on histological tissue sample analysis. Accurate classification is critical for treatment planning and patient outcomes.

Methods

This study develops a computer-assisted diagnosis system for non-small cell lung cancer histology classification, utilizing the FastAI-2 framework with a modified ResNet-34 architecture. The methodology includes stain normalization using LAB colour space for colour consistency, followed by deep learning-based classification. The proposed model is trained on the LC25000 dataset and compared with VGG11 and SqueezeNet1_1, demonstrating modified ResNet-34’s optimal balance between depth and performance. FastAI-2 enhances computational efficiency, enabling rapid convergence with minimal training time.

Results

The proposed system achieved 99.78% accuracy, confirming the effectiveness of automated lung cancer histopathology classification. This study highlights the potential of artificial intelligence (AI)-driven diagnostic tools to assist pathologists by improving accuracy, reducing workload, and enhancing decision-making in clinical settings.

Schlagwörter

Stichwörter der Autor:innen

ClassificationDeep learningDiagnosisHistopathological imagesLung cancer

Autor:innen und Institutionen

  • School of Computer Science Engineering and Technology, Bennett University, Greater Noida, India.
  • University School of Automation and Robotics, Guru Gobind Singh Indraprastha University, Delhi, India.
  • School of Information Communication and Technology, Bahrain Polytechnic, Isa Town, Bahrain.
  • Department of Information Technology, College of Computers and Information Technology, Taif University, Taif, Saudi Arabia.

ORCID-Profile: Pranshu Saxena, Sultan S Alshamrani, Mrim M Alnfiai

Förderung

  • Taif University, Saudi Arabia

Zitieren

APA

Saxena, P., Singh, S. K., Rashid, M., Alshamrani, S. S., & Alnfiai, M. M. (2025). Efficient deep learning model for classifying lung cancer images using normalized stain agnostic feature method and FastAI-2. PeerJ Computer Science, 11, e2903. https://doi.org/10.7717/peerj-cs.2903

Vancouver

Saxena P, Singh SK, Rashid M, Alshamrani SS, Alnfiai MM. Efficient deep learning model for classifying lung cancer images using normalized stain agnostic feature method and FastAI-2. PeerJ Computer Science. 2025;11:e2903. doi:10.7717/peerj-cs.2903

BibTeX
@article{Saxena2025,
  author = {Saxena, Pranshu and Singh, Sanjay Kumar and Rashid, Mamoon and Alshamrani, Sultan S and Alnfiai, Mrim M},
  title = {Efficient deep learning model for classifying lung cancer images using normalized stain agnostic feature method and FastAI-2},
  journal = {PeerJ Computer Science},
  year = {2025},
  volume = {11},
  pages = {e2903},
  doi = {10.7717/peerj-cs.2903}
}
Kostenlos starten →