A lightweight CNN for colon cancer tissue classification and visualization

Colon cancer (CC) image classification plays a key role in the diagnostic process in clinical contexts, especially as computational medical solutions become the trend for future radiology and pathology practices. This study presents a novel lightweight Convolutional Neural Network (CNN) model designed with effective data cleaning strategy for the classification and visualization of histopathology images of various colon cancer tissues.

Addressing the critical need for efficient diagnostic tools in colon cancer detection, the proposed model leverages a non-pretrained architecture optimized for performance in resource-constrained environments. Utilizing the NCT-CRC-HE-100K and CRC-VAL-HE-7K datasets, this model employs a parametric Gaussian distribution-based data cleaning approach to enhance data quality by removing outliers.

With a total of 4,414,217 parameters and a total size of 16.9 megabytes, the model achieves a test accuracy of 0.990 ± 0.003 with 95% level of confidence, which demonstrates high precision, recall, specificity, and F1 scores across various tissue classes.

Comparative analysis with benchmark studies underscores the model's effectiveness, while discussions on underfitting and overfitting provide insights into potential fine-tuning strategies. This research presents a robust, lightweight solution for colon cancer histopathology image classification, offering a foundation for future advancements in colon cancer diagnostics with result visualization.