Lung cancer pathological image classification using spatial-channel attention (SCA) mechanism

Authors: Siran Zhong ^{1, 2}, Qin Peng ³, Fan Zhang ⁴, Wen Lin ², Kanakarn Phanniphong ^5, *

Affiliations:

¹Chakrabongse Bhuvanarth International College for Interdisciplinary Studies, Rajamangala University of Technology Tawan-ok, Bangkok, Thailand
²Faculty of Data Science, Guangzhou Huashang College, Guangzhou, China
³Faculty of Data Science, City University of Macau, Macau, China
⁴Shenzhen Bao’an Chinese Medicine Hospital, Guangzhou University of Chinese Medicine, Shenzhen, China
⁵Faculty of Business Administration and Information Technology, Rajamangla University of Technology Tawan-ok, Bangkok, Thailand

Abstract

With the increasing use of deep learning in medical imaging, particularly in analyzing lung cancer pathology images, this technology shows great promise for building models for pathological grading and prognosis. This study highlights the growing importance of deep learning in this area, but also notes that accurately classifying lung cancer pathology images remains a difficult task, especially when high precision is needed for grading and prognosis. The aim of this research is to improve the classification of lung cancer pathology images by developing and optimizing a deep learning model. The study focuses on comparing different models, with special attention given to improving the performance of the SCA-ResNet model. The results show that SCA-ResNet performs better than the commonly used ResNet-50 model. It achieves higher scores in several evaluation measures, including precision, recall, specificity, F1 score, and the Kappa coefficient. ROC curve analysis also supports the superior performance of SCA-ResNet, showing better diagnostic accuracy across different cancer grades. These findings suggest that the SCA-ResNet model can offer more accurate and reliable classification of lung cancer pathology images, which may help doctors make better decisions about treatment and prognosis. Its use in clinical practice could lead to improved diagnostic accuracy and better outcomes for patients.

Keywords

Lung cancer, Deep learning, Pathology images, Image classification, Diagnostic accuracy

Download

📄 Full PDF

DOI

https://doi.org/10.21833/ijaas.2025.11.003

Citation (APA)

Zhong, S., Peng, Q., Zhang, F., Lin, W., & Phanniphong, K. (2025). Lung cancer pathological image classification using spatial-channel attention (SCA) mechanism. International Journal of Advanced and Applied Sciences, 12(11), 19–28. https://doi.org/10.21833/ijaas.2025.11.003