XtraLight-MedMamba for Classification of Neoplastic Tubular Adenomas

TL;DR

This paper introduces XtraLight-MedMamba, a lightweight deep learning model that accurately classifies neoplastic tubular adenomas from whole-slide images, aiding early CRC risk assessment with high efficiency.

Contribution

The work presents a novel ultra-lightweight deep learning framework combining state-space modeling, attention mechanisms, and parameter reduction techniques for pathology image classification.

Findings

Achieved 97.18% accuracy and 0.9767 F1-score on adenoma classification.

Outperformed transformer-based and conventional models in accuracy and efficiency.

Model uses only about 32,000 parameters, suitable for resource-limited settings.

Abstract

Accurate risk stratification of precancerous polyps during routine colonoscopy screening is a key strategy to reduce the incidence of colorectal cancer (CRC). However, assessment of low-grade dysplasia remains limited by subjective histopathologic interpretation. Advances in computational pathology and deep learning offer new opportunities to identify subtle, fine morphologic patterns associated with malignant progression that may be imperceptible to the human eye. In this work, we propose XtraLight-MedMamba, an ultra-lightweight state-space-based deep learning framework to classify neoplastic tubular adenomas from whole-slide images (WSIs). The architecture is a blend of a ConvNeXt-based shallow feature extractor with parallel vision mamba blocks to efficiently model local texture cues within global contextual structure. An integration of the Spatial and Channel Attention Bridge (SCAB) module enhances multiscale feature extraction, while the Fixed Non-Negative Orthogonal Classifier (FNOClassifier) enables substantial parameter reduction and improved generalization. The model was evaluated on a curated dataset acquired from patients with low-grade tubular adenomas, stratified into case and control cohorts based on subsequent CRC development. XtraLight-MedMamba achieved an accuracy of 97.18\% and an F1-score of 0.9767 using approximately 32,000 parameters, outperforming transformer-based and conventional Mamba architectures, which have significantly higher model complexity and computational burden, making it suitable for resource-constrained areas.