![[2602.04819] XtraLight-MedMamba for Classification of Neoplastic Tubular Adenomas](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.04819] XtraLight-MedMamba for Classification of Neoplastic Tubular Adenomas
Summary
The article presents XtraLight-MedMamba, a deep learning framework designed for the classification of neoplastic tubular adenomas, achieving high accuracy in identifying precancerous polyps.
Why It Matters
This research is significant as it addresses the limitations of subjective histopathologic assessments in colonoscopy screenings, potentially improving colorectal cancer risk stratification through advanced digital pathology techniques.
Key Takeaways
- XtraLight-MedMamba utilizes a state-space-based deep learning architecture for enhanced classification of neoplastic tubular adenomas.
- The framework achieved an accuracy of 97.18% and an F1-score of 0.9767, outperforming existing models.
- The model integrates innovative components like the SCAB module for multiscale feature extraction and FNOClassifier for parameter reduction.
Computer Science > Computer Vision and Pattern Recognition arXiv:2602.04819 (cs) [Submitted on 4 Feb 2026 (v1), last revised 23 Feb 2026 (this version, v2)] Title:XtraLight-MedMamba for Classification of Neoplastic Tubular Adenomas Authors:Aqsa Sultana, Rayan Afsar, Ahmed Rahu, Surendra P. Singh, Brian Shula, Brandon Combs, Derrick Forchetti, Vijayan K. Asari View a PDF of the paper titled XtraLight-MedMamba for Classification of Neoplastic Tubular Adenomas, by Aqsa Sultana and 7 other authors View PDF HTML (experimental) Abstract:Accurate risk stratification of precancerous polyps during routine colonoscopy screenings is essential for lowering the risk of developing colorectal cancer (CRC). However, assessment of low-grade dysplasia remains limited by subjective histopathologic interpretation. Advancements in digital pathology and deep learning provide new opportunities to identify subtle and 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 for classifying neoplastic tubular adenomas from whole-slide images (WSIs). The architecture is a blend of ConvNext based shallow feature extractor with parallel vision mamba to efficiently model both long- and short-range dependencies and image generalization. An integration of Spatial and Channel Attention Bridge (SCAB) module enhances multiscale feature extraction, whi...
