Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 6 min ago
Peer-reviewedCC BY 4.0PLOS One

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

  • Muhammad Ahsan Jamil1
  • Malik Daler Ali Awan2
  • Fatima Bukhari3
  • Malik Muhammad Saad Missen
  • Nadeem Iqbal Kajla
  1. 1Department of Software Engineering, Faculty of Computing, The Islamia University of Bahawalpur, Bahawalpur, Pakistan
  2. 2Department of Computer Science, National University of Modern Languages (NUML), Islamabad, Pakistan
  3. 3School of Informatics and Creative Arts, Dundalk Institute of Technology, Dundalk, Ireland
Open at sourcePDFDOICite

Abstract

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, χ2=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.

Related

  1. EfficientNet-CICA: a sports image classification model based on causal intervention channel attention
    Junnan Yang, Shaocong Zhao
    Frontiers in PhysiologyPeer-reviewedCC BY 4.0Full textGeneral medicinePMCEurope PMC
  2. A dual-branch CNN-LSTM framework for exploratory classification of colorectal cancer histopathology and hepatocellular carcinoma clinical records
    Xiaoyan Guo, Jing Lai, Lili Wu +1
    Frontiers in oncologyPeer-reviewedCC BYFull textOncologyEurope PMCCrossref
  3. Traffic surveillance video-based a unified road accident detection, classification, and vehicle tracking framework using an optimized spatio-temporal attention mechanism
    Chokkakula Devi, Gowri S.
    PLOS OnePeer-reviewedCC BY 4.0Full textEpidemiology & public healthPLOS
  4. An EfficientNet hybrid deep learning detection framework of network intrusion with an optimized mixture-of-experts architecture
    Huadong Li, Xiongzhi Xiao, Jianfeng Feng +1
    Scientific ReportsPeer-reviewedCC BYFull textGeneral medicineDOAJ
  5. Comparative Evaluation of EfficientNet-B3, Vision Transformers, and RETFound for Seven-Category Retinopathy Fundus Image Classification.
    Majid Alutaibi, Meshari Alazmi
    Diagnostics (Basel, Switzerland)Peer-reviewedCC BYFull textMedical imaging & radiologyEurope PMC

Cite

BibTeXRIS
BibTeX
@article{jamil2026effattlungnet,
  title = {{EffAtt-LungNet: An attention-guided EfficientNet framework for three-class lung histopathology classification}},
  author = {Muhammad Ahsan Jamil and Malik Daler Ali Awan and Fatima Bukhari and Malik Muhammad Saad Missen and Nadeem Iqbal Kajla},
  journal = {PLOS One},
  year = {2026},
  month = oct,
  doi = {10.1371/journal.pone.0359302},
  url = {https://doi.org/10.1371/journal.pone.0359302},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - EffAtt-LungNet: An attention-guided EfficientNet framework for three-class lung histopathology classification
AU  - Muhammad Ahsan Jamil
AU  - Malik Daler Ali Awan
AU  - Fatima Bukhari
AU  - Malik Muhammad Saad Missen
AU  - Nadeem Iqbal Kajla
PY  - 2026
DA  - 2026/10/05
JO  - PLOS One
DO  - 10.1371/journal.pone.0359302
UR  - https://doi.org/10.1371/journal.pone.0359302
AB  - 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, χ2=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.
SN  - 1932-6203
ER  -