Swin-GA-RF: genetic algorithm-based Swin Transformer and random forest for enhancing cervical cancer classification

被引:2
|
作者
Alohali, Manal Abdullah [1 ]
El-Rashidy, Nora [2 ]
Alaklabi, Saad [3 ]
Elmannai, Hela [4 ]
Alharbi, Saleh [3 ]
Saleh, Hager [5 ,6 ,7 ]
机构
[1] Princess Nourah Bint Abdulrahman Univ, Coll Comp & Informat Sci, Dept Informat Syst, Riyadh, Saudi Arabia
[2] Kafrelsheiksh Univ, Fac Artificial Intelligence, Machine Learning & Informat Retrieval Dept, Kafrelsheiksh, Egypt
[3] Shaqra Univ, Coll Sci & Humanities Dawadmi, Dept Comp Sci, Shaqra, Saudi Arabia
[4] Princess Nourah Bint Abdulrahman Univ, Coll Comp & Informat Sci, Dept Informat Technol, Riyadh, Saudi Arabia
[5] South Valley Univ, Fac Comp & Artificial Intelligence, Hurghada, Egypt
[6] Galway Univ, Data Sci Inst, Galway, Ireland
[7] Atlantic Technol Univ, Letterkenny, Ireland
来源
FRONTIERS IN ONCOLOGY | 2024年 / 14卷
关键词
image processing; image classification; image cancer classification; Swin Transformer; CNN models; genetic algorithm; random forest;
D O I
10.3389/fonc.2024.1392301
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Cervical cancer is a prevalent and concerning disease affecting women, with increasing incidence and mortality rates. Early detection plays a crucial role in improving outcomes. Recent advancements in computer vision, particularly the Swin transformer, have shown promising performance in image classification tasks, rivaling or surpassing traditional convolutional neural networks (CNNs). The Swin transformer adopts a hierarchical and efficient approach using shifted windows, enabling the capture of both local and global contextual information in images. In this paper, we propose a novel approach called Swin-GA-RF to enhance the classification performance of cervical cells in Pap smear images. Swin-GA-RF combines the strengths of the Swin transformer, genetic algorithm (GA) feature selection, and the replacement of the softmax layer with a random forest classifier. Our methodology involves extracting feature representations from the Swin transformer, utilizing GA to identify the optimal feature set, and employing random forest as the classification model. Additionally, data augmentation techniques are applied to augment the diversity and quantity of the SIPaKMeD1 cervical cancer image dataset. We compare the performance of the Swin-GA-RF Transformer with pre-trained CNN models using two classes and five classes of cervical cancer classification, employing both Adam and SGD optimizers. The experimental results demonstrate that Swin-GA-RF outperforms other Swin transformers and pre-trained CNN models. When utilizing the Adam optimizer, Swin-GA-RF achieves the highest performance in both binary and five-class classification tasks. Specifically, for binary classification, it achieves an accuracy, precision, recall, and F1-score of 99.012, 99.015, 99.012, and 99.011, respectively. In the five-class classification, it achieves an accuracy, precision, recall, and F1-score of 98.808, 98.812, 98.808, and 98.808, respectively. These results underscore the effectiveness of the Swin-GA-RF approach in cervical cancer classification, demonstrating its potential as a valuable tool for early diagnosis and screening programs.
引用
收藏
页数:18
相关论文
共 31 条
  • [21] Enhancing Skin Cancer Diagnosis Using Swin Transformer with Hybrid Shifted Window-Based Multi-head Self-attention and SwiGLU-Based MLP
    Pacal, Ishak
    Alaftekin, Melek
    Zengul, Ferhat Devrim
    JOURNAL OF IMAGING INFORMATICS IN MEDICINE, 2024, 37 (06): : 3174 - 3192
  • [22] Enhancing sports image data classification in federated learning through genetic algorithm-based optimization of base architecture
    Fu, De Sheng
    Huang, Jie
    Hazra, Dibyanarayan
    Dwivedi, Amit Kumar
    Gupta, Suneet Kumar
    Shivahare, Basu Dev
    Garg, Deepak
    PLOS ONE, 2024, 19 (07):
  • [23] Genetic algorithm-based feature selection with manifold learning for cancer classification using microarray data
    Wang, Zixuan
    Zhou, Yi
    Takagi, Tatsuya
    Song, Jiangning
    Tian, Yu-Shi
    Shibuya, Tetsuo
    BMC BIOINFORMATICS, 2023, 24 (01)
  • [24] Genetic algorithm-based feature selection with manifold learning for cancer classification using microarray data
    Zixuan Wang
    Yi Zhou
    Tatsuya Takagi
    Jiangning Song
    Yu-Shi Tian
    Tetsuo Shibuya
    BMC Bioinformatics, 24
  • [25] GA-VAE: Enhancing Local Feature Representation in VQ-VAE Through Genetic Algorithm-Based Token Optimization
    Jiang, Jinghui
    Kim, Dongjoon
    Kim, Bohyoung
    Shin, Yeong-Gil
    IEEE ACCESS, 2025, 13 : 34286 - 34295
  • [26] Liver Cancer Classification Using Random Forest and Extreme Gradient Boosting (XGBoost) with Genetic Algorithm as Feature Selection
    Desdhanty, Vabiyana Safira
    Rustam, Zuherman
    2021 INTERNATIONAL CONFERENCE ON DECISION AID SCIENCES AND APPLICATION (DASA), 2021,
  • [27] GA-ML: enhancing the prediction of water electrical conductivity through genetic algorithm-based end-to-end hyperparameter tuning
    Gul, Muhammed Furkan
    Bakir, Halit
    EARTH SCIENCE INFORMATICS, 2025, 18 (02)
  • [28] Genetic algorithm-based method for forest type classification using multi-temporal NDVI from Landsat TM imagery
    Tao, Hong
    Li, Manqi
    Wang, Ming
    Lu, Guonian
    ANNALS OF GIS, 2019, 25 (01) : 33 - 43
  • [29] Hybrid Filter and Genetic Algorithm-Based Feature Selection for Improving Cancer Classification in High-Dimensional Microarray Data
    Ali, Waleed
    Saeed, Faisal
    PROCESSES, 2023, 11 (02)
  • [30] Genetic Algorithm-Based Feature Selection and Optimization of Backpropagation Neural Network Parameters for Classification of Breast Cancer Using MicroRNA Profiles
    Adorada, Amazona
    Wibowo, Adi
    2019 3RD INTERNATIONAL CONFERENCE ON INFORMATICS AND COMPUTATIONAL SCIENCES (ICICOS 2019), 2019,