Fine-Tuning Models for Histopathological Classification of Colorectal Cancer

Background/Objectives: This study aims to design and evaluate transfer learning strategies that fine-tune multiple pre-trained convolutional neural network architectures based on their characteristics to improve the accuracy and generalizability of colorectal cancer histopathological image classification. Methods: The application of transfer learning with pre-trained models on specialized and multiple datasets is proposed, where the proposed models, CRCHistoDense, CRCHistoIncep, and CRCHistoXcep, are algorithmically fine-tuned at varying depths to improve the performance of colorectal cancer classification. These models were applied to datasets of 10,613 images from public and private repositories, external sources, and unseen data. To validate the models' decision-making and improve transparency, we integrated Grad-CAM to provide visual explanations that influence classification decisions. Results and Conclusions: On average across all datasets, CRCHistoDense, CRCHistoIncep, and CRCHistoXcep achieved test accuracies of 99.34%, 99.48%, and 99.45%, respectively, highlighting the effectiveness of fine-tuning in improving classification performance and generalization. Statistical methods, including paired t-tests, ANOVA, and the Kruskal-Wallis test, confirmed significant improvements in the proposed methods' performance, with p-values below 0.05. These findings demonstrate that fine-tuning based on the characteristics of CNN's architecture enhances colorectal cancer classification in histopathology, thereby improving the diagnostic potential of deep learning models.