EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EffAtt-LungNet: An attention-guided EfficientNet framework for three-class lung histopathology classification

Muhammad Ahsan Jamil, Malik Daler Ali Awan, Fatima Bukhari, Malik Muhammad Saad Missen, Nadeem Iqbal Kajla iD

PLOS One · 2026

DOI: 10.1371/journal.pone.0359302 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Muhammad Ahsan Jamil und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Software Engineering, Faculty of Computing, The Islamia University of Bahawalpur, Bahawalpur, Pakistan. Hauptthemen laut MEDLINE: Lung Neoplasms, Lung, Deep Learning, Adenocarcinoma of Lung. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents EffAtt-LungNet, an attention-guided deep learning framework for three-class lung histopathology classification. The model combines an EfficientNetB3 backbone with the Convolutional Block Attention Module (CBAM) to refine features and improve discrimination among benign lung tissue, lung adenocarcinoma, and lung squamous cell carcinoma. Experiments used the publicly released LC25000 lung subset, which contains 15,000 images across three classes and was itself produced by augmenting a smaller collection of underlying histopathology images. We generated 10,500 additional fixed variants, creating a balanced working corpus of 25,500 images with training, validation, and test partitions of 15,300, 2,550, and 7,650 images. EffAtt-LungNet reached 99.86% accuracy, 99.86% precision, 99.86% recall, 99.86% F1 score, and 0.9997 AUC on the image-level test partition. Performance was stable across five random seeds (mean accuracy 99.86 ± 0.02 % ), and paired errors differed from those of the EfficientNetB3 backbone (McNemar’s test, χ 2 = 47.27 , p < 0.001). Because pre-augmentation source identifiers for the released LC25000 images were unavailable, independence at the earliest source-image level could not be confirmed. The results therefore represent internal tile-level benchmark performance and require validation on independent, non-augmented, multi-centre datasets before any translational or clinical claim can be made.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Lung NeoplasmsLungDeep LearningAdenocarcinoma of LungCarcinoma, Squamous CellHumansConvolutional Neural NetworksImage Processing, Computer-Assisted

Autor:innen und Institutionen

  • Department of Software Engineering, Faculty of Computing, The Islamia University of Bahawalpur, Bahawalpur, Pakistan.
  • Department of Computer Science, National University of Modern Languages (NUML), Islamabad, Pakistan.
  • School of Informatics and Creative Arts, Dundalk Institute of Technology, Dundalk, Ireland.

ORCID-Profile: Nadeem Iqbal Kajla

Zitieren

APA

Jamil, M. A., Awan, M. D. A., Bukhari, F., Missen, M. M. S., & Kajla, N. I. (2026). EffAtt-LungNet: An attention-guided EfficientNet framework for three-class lung histopathology classification. PLOS One. https://doi.org/10.1371/journal.pone.0359302

Vancouver

Jamil MA, Awan MDA, Bukhari F, Missen MMS, Kajla NI. EffAtt-LungNet: An attention-guided EfficientNet framework for three-class lung histopathology classification. PLOS One. 2026. doi:10.1371/journal.pone.0359302

BibTeX
@article{Jamil2026,
  author = {Jamil, Muhammad Ahsan and Awan, Malik Daler Ali and Bukhari, Fatima and Missen, Malik Muhammad Saad and Kajla, Nadeem Iqbal},
  title = {EffAtt-LungNet: An attention-guided EfficientNet framework for three-class lung histopathology classification},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0359302}
}
Kostenlos starten →