A novel framework for lung cancer classification using lightweight convolutional neural networks and ridge extreme learning machine model with SHapley Additive exPlanations (SHAP)

被引:14
|
作者
Nahiduzzaman, Md. [1 ]
Abdulrazak, Lway Faisal [2 ]
Ayari, Mohamed Arselene [3 ,6 ]
Khandakar, Amith [4 ]
Islam, S. M. Riazul [5 ]
机构
[1] Rajshahi Univ Engn & Technol, Dept Elect & Comp Engn, Rajshahi 6204, Bangladesh
[2] Cihan Univ Sulaimaniya, Comp Sci Dept, Sulaimaniya 64001, Kurdistan Reg, Iraq
[3] Qatar Univ, Dept Civil & Architectural Engn, Doha, Qatar
[4] Qatar Univ, Dept Elect Engn, Doha, Qatar
[5] Univ Aberdeen, Dept Comp Sci, Aberdeen AB24 3FX, Scotland
[6] Qatar Univ, Technol Innovat & Engn Educ Unit TIEE, Doha, Qatar
关键词
Adenocarcinoma; Convolutional Neural Networks (CNN); Extreme Learning Machines (ELM); Contrast-limited adaptive histogram equalization (CLAHE); Large Cell Carcinoma; Lung Cancer; Squamous Cell Carcinoma; Shapley Additive Explanations (SHAP); ALGORITHM;
D O I
10.1016/j.eswa.2024.123392
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents a novel approach that merges a lightweight parallel depth-wise separable convolutional neural network (LPDCNN) with a ridge regression extreme learning machine (Ridge-ELM) for precise classification of three lung cancer types alongside normal lung tissue (adenocarcinoma, large cell carcinoma, normal, and squamous cell carcinoma) using CT images. The proposed methodology combines contrast-limited adaptive histogram equalization (CLAHE) and Gaussian blur to enhance image quality, reduce noise, and improve visual clarity. The LPDCNN extracts discriminant features while minimizing computational complexity (0.53 million parameters and 9 layers). The Ridge-ELM model was developed to enhance classification performance, replacing the traditional pseudoinverse in the ELM approach. Through comprehensive evaluation against state-of-the-art models, the framework achieves remarkable average recall and accuracy values of 98.25 +/- 1.031 % and 98.40 +/- 0.822 %, respectively, through rigorous five-fold cross-validation for four-class classifications. In binary classifications, outstanding results are obtained with recall and accuracy values of 99.70 +/- 0.671 % and 99.70 +/- 0.447 %%, respectively. Notably, the framework exhibits exceptional efficiency, with a testing time of only 0.003 s. Additionally, integrating the SHAP (Shapley Additive Explanations) in the proposed framework enhances Explain-ability, providing insights into decision-making and boosting confidence in real-world lung cancer diagnoses.
引用
收藏
页数:17
相关论文
共 50 条
  • [31] An interpretable framework for modeling global solar radiation using tree-based ensemble machine learning and Shapley additive explanations methods
    Song, Zhe
    Cao, Sunliang
    Yang, Hongxing
    APPLIED ENERGY, 2024, 364
  • [32] Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection
    Kim, Jihun
    Kim, Jonghong
    Jang, Gil-Jin
    Lee, Minho
    NEURAL NETWORKS, 2017, 87 : 109 - 121
  • [33] Breast Cancer Classification Using Concatenated Triple Convolutional Neural Networks Model
    Alshayeji, Mohammad H.
    Al-Buloushi, Jassim
    BIG DATA AND COGNITIVE COMPUTING, 2023, 7 (03)
  • [34] Key factors affecting groundwater nitrate levels in the Yinchuan Region, Northwest China: Research using the eXtreme Gradient Boosting (XGBoost) model with the SHapley Additive exPlanations (SHAP) method
    Alam, S. M. Khorshed
    Li, Peiyue
    Rahman, Mahbubur
    Fida, Misbah
    Elumalai, Vetrimurugan
    ENVIRONMENTAL POLLUTION, 2025, 364
  • [35] Machine learning enabled classification of lung cancer cell lines co-cultured with fibroblasts with lightweight convolutional neural network for initial diagnosis
    Germain, Adam
    Sabol, Alex
    Chavali, Anjani
    Fitzwilliams, Giles
    Cooper, Alexa
    Khuon, Sandra
    Green, Bailey
    Kong, Calvin
    Minna, John
    Kim, Young-Tae
    JOURNAL OF BIOMEDICAL SCIENCE, 2024, 31 (01)
  • [36] A Novel Wearable Electrocardiogram Classification System Using Convolutional Neural Networks and Active Learning
    Xia, Yufa
    Xie, Yaoqin
    IEEE ACCESS, 2019, 7 : 7989 - 8001
  • [37] Interpretable prediction of cardiopulmonary complications after non-small cell lung cancer surgery based on machine learning and SHapley additive exPlanations
    Zhai, Yihai
    Lin, Xue
    Wei, Qiaolin
    Pu, Yuanjin
    Pang, Yonghui
    HELIYON, 2023, 9 (07)
  • [38] Creating machine learning models that interpretably link systemic inflammatory index, sex steroid hormones, and dietary antioxidants to identify gout using the SHAP (SHapley Additive exPlanations) method
    Cao, Shunshun
    Hu, Yangyang
    FRONTIERS IN IMMUNOLOGY, 2024, 15
  • [39] Breast cancer masses classification using deep convolutional neural networks and transfer learning
    Shayma’a A. Hassan
    Mohammed S. Sayed
    Mahmoud I Abdalla
    Mohsen A. Rashwan
    Multimedia Tools and Applications, 2020, 79 : 30735 - 30768
  • [40] Breast cancer masses classification using deep convolutional neural networks and transfer learning
    Hassan, Shayma'a A.
    Sayed, Mohammed S.
    Abdalla, Mahmoud, I
    Rashwan, Mohsen A.
    MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (41-42) : 30735 - 30768