A hybrid framework for enhanced segmentation and classification of colorectal cancer histopathology

TL;DR

This paper introduces a hybrid deep learning model that improves the accuracy and efficiency of diagnosing colorectal cancer from histopathology images.

Contribution

A novel hybrid framework combining Swin Transformer, EfficientNet, and ResUNet-A for enhanced CRC histopathology analysis.

Findings

The hybrid model achieved 93% accuracy, 92% precision, 93% recall, and 93% F1-score in CRC histopathology analysis.

The model outperformed individual architectures in both segmentation and classification tasks.

Expert annotations closely matched the model's outputs, confirming its reliability.

Abstract

Colorectal cancer (CRC) remains one of the leading causes of cancer-related deaths globally. Early detection and precise diagnosis are crucial in improving patient outcomes. Traditional histological evaluation through manual inspection of stained tissue slides is time-consuming, prone to observer variability, and susceptible to inconsistent diagnoses.

To address these challenges, we propose a hybrid deep learning system combining Swin Transformer, EfficientNet, and ResUNet-A. This model integrates self-attention, compound scaling, and residual learning to enhance feature extraction, global context modeling, and spatial categorization. The model was trained and evaluated using a histopathological dataset that included serrated adenoma, polyps, adenocarcinoma, high-grade and low-grade intraepithelial neoplasia, and normal tissues.

Our hybrid model achieved impressive results, with 93% accuracy, 92% precision, 93% recall, and 93% F1-score. It outperformed individual architectures in both segmentation and classification tasks. Expert annotations and segmentation masks closely matched, demonstrating the model’s reliability.

The proposed hybrid design proves to be a robust tool for the automated analysis of histopathological features in CRC, showing significant promise for improving diagnostic accuracy and efficiency in clinical settings.

Figures