EC Paediatrics

Research Article Volume 13 Issue 5 - 2025

Pretrained VGG16-Based Deep Learning for Precise Histopathological Classification of Lung and Colorectal Cancers, Enhancing Oncology Diagnostics with Improved Accuracy and Automated Image Analysis

Mathesh A1, Darius Alan A1, Shirly S1, Aadhithan DS1, Saravanan M2 and Dr Shailaja K3*

1Dept of Pharmacy Practice, C.L. Baid Metha College of Pharmacy, India
 2Associate Professor, Department of Pharmacy, Fatima College of Health Sciences, UAE
 3Professor, Department of Pharmacy Practice, C.L. Baid Metha College of Pharmacy, India

*Corresponding Author: Dr Shailaja K, Professor and HOD, Department of Pharmacy Practice, C. L. Baid Metha College of Pharmacy, Affiliated to The Tamil Nadu Dr. MGR. Medical University, Chennai, Tamil Nadu, India.
Received: April 07, 2025; Published: May 02, 2025




Introduction: Convolutional neural networks (CNN) and deep learning models have drastically changed the field of image classification. The Visual Geometry Group 16-layer network (VGG16) model, a popular CNN model, has been shown to have superior performance across different fields. This work investigates the effectiveness of a pretrained VGG16 model in histopathological image classification and its superiority in distinguishing visually indistinguishable types of cancer. Furthermore, we extend our analysis by integrating a self-attention mechanism into the VGG16 architecture to enhance the model’s capability to capture long-range dependencies and subtle contextual cues within tissue structures

Methods: We adopted a transfer learning strategy with the use of a pre-trained VGG16 model, augmented with self-attention to enhance feature extraction. Preprocessing was done on the dataset using normalization and data augmentation methods to improve generalization. The model was also fine-tuned on a histopathology dataset, and the performance metrics of accuracy, precision, recall, and F1-score were measured. Comparative analysis with baseline models was performed to measure improvements in classification performance.

Results: Pretrained VGG16 with self-attention showed the best classification results with a global accuracy of 98% and improvements are seen in precision, recall, F-1 score of individual classes. Integration of self-attention strengthened spatial feature learning and resulted in enhanced discrimination of histopathological subtypes. Compared to regular CNN architectures, our model depicted significantly reduced rates of misclassifications, especially in difficult cases.

Conclusion: This work verifies the superiority of the pretrained VGG16 model with self-attention for histopathological image classification and provides a reliable and efficient solution for cancer diagnosis. The results indicate that utilizing pretrained deep models can significantly improve performance with reduced computational complexity. Optimizing self-attention mechanisms, increasing dataset diversity, and incorporating explainability methods will be explored in future work to increase clinical relevance.

 Keywords: Convolutional Neural Networks; Visual Geometry Group; Artificial Intelligence; Machine Learning; Self Attention; Lung and Colorectal Cancer

    1. Thandra KC., et al. “Epidemiology of lung cancer”. Contemporary Oncology/Współczesna Onkologia1 (2021): 45-52.
    2. Rawla Prashanth., et al. “Epidemiology of colorectal cancer: incidence, mortality, survival, and risk factors”. Gastroenterology Review/Przegląd Gastroenterologiczny2 (2019): 89-103.
    3. Nath Arvind., et al. “A clinicoepidemiological profile of lung cancers in India-Results from the National Cancer Registry Programme”. Indian Journal of Medical Research2 (2022): 264-272.
    4. Sung Hyuna., et al. “Colorectal cancer incidence trends in younger versus older adults: an analysis of population-based cancer registry data”. The Lancet Oncology1 (2025): 51-63.
    5. Horgan Denis., et al. “Aligning cancer research priorities in Europe with recommendations for conquering cancer: a comprehensive analysis”. Healthcare2 (2024): 259.
    6. Bajwa Junaid., et al. “Artificial intelligence in healthcare: transforming the practice of medicine”. Future Healthcare Journal2 (2021): e188-e194.
    7. Mangal Shubham., et al. “Convolution neural networks for diagnosing colon and lung cancer histopathological images”. arXiv preprint arXiv:2009.03878 (2020).
    8. Garg S and S Garg. "Prediction of lung and colon cancer through analysis of histopathological images by utilizing Pre-trained CNN models with visualization of class activation and saliency maps”. Proceedings of the 2020 3rd Artificial Intelligence and Cloud Computing Conference (2020): 38-45.
    9. Ji Jingyi., et al. “Automated lung and colon cancer classification using histopathological images”. Biomedical Engineering and Computational Biology 15 (2024): 11795972241271569.
    10. Ali M and R Ali. "Multi-input dual-stream capsule network for improved lung and colon cancer classification”. Diagnostics 8 (2021): 1485.
    11. Masud Md., et al. “A machine learning approach to diagnosing lung and colon cancer using a deep learning-based classification framework”. Sensors 3 (2021): 748.
    12. Hage Chehade Ahmad., et al. “Lung and colon cancer classification using medical imaging: A feature engineering approach”. Physical and Engineering Sciences in Medicine3 (2022): 729-746.
    13. Talukder Md Abir., et al. “Machine learning-based lung and colon cancer detection using deep feature extraction and ensemble learning”. Expert Systems with Applications 205 (2022): 117695.
    14. Mehmood Shahbaz., et al. “Malignancy detection in lung and colon histopathology images using transfer learning with class selective image processing”. IEEE Access 10 (2022): 25657-25668.
    15. Singh Omveer and KK Singh. "An approach to classify lung and colon cancer of histopathology images using deep feature extraction and an ensemble method”. International Journal of Information Technology8 (2023): 4149-4160.
    16. Bhattacharya Anurag., et al. “Deep feature selection using adaptive β-Hill Climbing aided whale optimization algorithm for lung and colon cancer detection”. Biomedical Signal Processing and Control 83 (2023): 104692.
    17. Al-Jabbar Mohammed., et al. “Histopathological analysis for detecting lung and colon cancer malignancies using hybrid systems with fused features”. Bioengineering3 (2023): 383.
    18. Xu Hui., et al. “Vision transformers for computational histopathology”. IEEE Reviews in Biomedical Engineering 17 (2024): 63-79.
    19. Katar Ozlem., et al. “A novel hybrid model for automatic non-small cell lung cancer classification using histopathological images”. Diagnostics 22 (2024): 2497.
    20. Sengodan N. "CBAM-EfficientNetV2 for histopathology image classification using transfer learning and dual attention mechanisms”. arXiv preprint arXiv:2410.22392 (2024).
    21. Zheng Yan., et al. “Application of transfer learning and ensemble learning in image-level classification for breast histopathology”. Intelligent Medicine2 (2023): 115-128.
    22. Balasubramanian AA., et al. “Ensemble deep learning-based image classification for breast cancer subtype and invasiveness diagnosis from whole slide image histopathology”. Cancers12 (2024): 2222.
    23. Li Zhe., et al. “Vision transformer-based weakly supervised histopathological image analysis of primary brain tumors”. iScience1 (2022): 105872.
    24. Atabansi Chuka C., et al. “A survey of Transformer applications for histopathological image analysis: New developments and future directions”. Biomedical Engineering Online1 (2023): 96.
    25. Gao Xiaoyan., et al. “A comparative analysis of combination of CNN-based models with ensemble learning on imbalanced data”. JOIV: International Journal on Informatics Visualization1 (2024): 456-464.
    26. Park Se-Yeon., et al. “Vision transformers for low-quality histopathological images: a case study on squamous cell carcinoma margin classification”. Diagnostics3 (2025): 260.
    27. Hayat Mohammad., et al. “Hybrid deep learning EfficientNetV2 and vision transformer (EffNetV2-ViT) model for breast cancer histopathological image classification”. IEEE Access 12 (2024): 184119-184131.
    28. Kumaran SY., et al. “Explainable lung cancer classification with ensemble transfer learning of VGG16, ResNet50, and InceptionV3 using Grad-CAM”. BMC Medical Imaging1 (2024): 176.
    29. Zhang Ying., et al. “Deep-learning model of ResNet combined with CBAM for malignant-benign pulmonary nodules classification on computed tomography images”. Medicina6 (2023): 1088.
    30. Abimouloud Mohammed L., et al. “Advancing breast cancer diagnosis: token vision transformers for faster and accurate classification of histopathology images”. Visual Computing for Industry, Biomedicine, and Art1 (2025): 1.
    31. Çetin-Kaya Yeliz. "Equilibrium optimization-based ensemble CNN framework for breast cancer multiclass classification using histopathological image”. Diagnostics19 (2024): 2253.
    32. Springenberg Matthias., et al. “From modern CNNs to vision transformers: assessing the performance, robustness, and classification strategies of deep learning models in histopathology”. Medical Image Analysis 87 (2023): 102809.
    33. Borkowski Andrew A., et al. “Lung and colon cancer histopathological image dataset (LC25000)”. arXiv:1912.12142 (2019).

Dr Shailaja K., et al. "Pretrained VGG16-Based Deep Learning for Precise Histopathological Classification of Lung and Colorectal Cancers, Enhancing Oncology Diagnostics with Improved Accuracy and Automated Image Analysis". EC Paediatrics 13.5 (2025): 01-10.

ECronicon Journal

Our Services

Quick Links

Information

Creative Commons LicenseOpen Access by ECronicon is licensed under a Creative Commons Attribution 4.0 International License
Based on a work at www.ecronicon.net