Precision lung cancer classification using convolutional neural networks with enhanced image pre-processing and model optimization.

Abstract

Among various types of cancers, lung cancer causes the highest mortality globally, necessitating prompt diagnosis for effective treatment. Traditionally, histopathological analysis of Hematoxylin and Eosin (H&E)-stained slides serves as the principal method for definitive diagnosis. However, manual interpretation is often hindered by staining variability. This research focuses on designing a Convolutional Neural Network (CNN) model tailored to classify various subtypes of lung carcinoma. It aims to overcome key diagnostic challenges, including variability in staining techniques. The publicly available LC25000 dataset comprising lung histopathological images was utilized. To mitigate staining variability and reduce noise, Reinhard color normalization and Gaussian filtering were applied during pre-processing. Particle Swarm Optimization (PSO) was employed for hyperparameter tuning, which helped in the development of a multi-scale CNN architecture tailored for robust classification. The optimized CNN model achieved a classification accuracy of 98.59% across three categories: two non-small cell lung malignant classes and one benign class. Comparative evaluations revealed that pre-processed images significantly improved classification consistency and accuracy, highlighting the benefits of color normalization techniques. The developed model exhibits strong diagnostic performance and improved resilience to staining variability. To support real-time clinical use, the model was successfully deployed as an Android-based mobile application. This application is publicly available and can be accessed at: https://github.com/jar3e1/AndroidApp.