Deep learning ensemble approach with explainable AI for lung and colon cancer classification using advanced hyperparameter tuning

Sep 21, 2026

Upload by Oliver

Lung and colon cancers drive substantial global cancer mortality and can be distinguished through histopathological characteristics visible in medical imaging. Accurate classification is essential for reliable diagnosis and effective treatment, yet existing imaging workflows often face overfitting and limited generalizability. This work proposes a deep learning ensemble combining Xception and MobileNet and uses advanced hyperparameter tuning to strengthen feature extraction, robustness, and generalization. Training on histopathology images and validating on a balanced test set yields 99.44% accuracy with perfect precision and recall for targeted tissue classes. Interpretability is added via Grad-CAM to support clinical decision transparency.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Abstract

Introduction

Vanitha et al. BMC Medical Informatics and Decision Making [https://doi.org/10.1186/s12911-024-02628-7](https://doi.org/10.1186/s12911-024-02628-7) (2024) 24:222 BMC Medical Informatics and Decision Making RESEARCH Open Access Deep learning ensemble approach with explainable AI for lung and colon cancer classification using advanced hyperparameter tuning K. Vanitha 1, Mahesh T. R2, S. Sathea Sree3 and Suresh Guluwadi4* Abstract Lung and colon cancers are leading contributors to cancer-related fatalities globally, distinguished by unique histopathological traits discernible through medical imaging. Effective classification of these cancers is critical for accurate diagnosis and treatment. This study addresses critical challenges in the diagnostic imaging of lung and colon cancers, which are among the leading causes of cancer-related deaths worldwide. Recognizing the limitations of existing diagnostic methods, which often suffer from overfitting and poor generalizability, our research introduces a novel deep learning framework that synergistically combines the Xception and MobileNet architectures. This innovative ensemble model aims to enhance feature extraction, improve model robustness, and reduce overfitting. Our methodology involves training the hybrid model on a comprehensive dataset of histopathological images, followed by validation against a balanced test set. The results demonstrate an impressive classification accuracy of 99 .44%, with perfect precision and recall in identifying certain cancerous and non-cancerous tissues, marking a significant improvement over traditional approach. The practical implications of these findings are profound. By integrating Gradient-weighted Class Activation Mapping (Grad-CAM), the model offers enhanced interpretability, allowing clinicians to visualize the diagnostic reasoning process. This transparency is vital for clinical acceptance and enables more personalized, accurate treatment planning. Our study not only pushes the boundaries of medical imaging technology but also sets the stage for future research aimed at expanding these techniques to other types of cancer diagnostics. Keywords Enhanced deep learning, Histopathology, Lung cancer diagnosis, Colon cancer detection, Ensemble learning models, Xception and MobileNet integration, Gradient-weighted Class Activation Mapping (Grad-CAM), Medical image analysis, Automated cancer classification, Clinical AI applications *Correspondence: Suresh Guluwadi [suresh.guluwadi@astu.edu.et](suresh.guluwadi@astu.edu.et) Full list of author information is available at the end of the article © The Author(s) 2024. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creativecommons.org/licenses/by-nc-nd/4.0/](http://creativecommons.org/licenses/by-nc-nd/4.0/.)[.](http://creativecommons.org/licenses/by-nc-nd/4.0/.) Vanitha etal. BMC Medical Informatics and Decision Making (2024) 24:222 Page 2 of 18 Introduction Lung and colon cancers represent two of the most significant challenges in the field of onco

FAQs

What problem does the study address for lung and colon cancer classification?

It targets the need for more accurate and generalizable diagnostic imaging methods, since many existing approaches can overfit and generalize poorly.

What model design is proposed in this research?

It introduces an ensemble framework that synergistically combines the Xception and MobileNet architectures.

How does the study improve interpretability for clinical use?

It integrates Gradient-weighted Class Activation Mapping (Grad-CAM) so clinicians can visualize the diagnostic reasoning process behind predictions.

Sep 21, 2026

Upload by Oliver