PCMamba: Integrating partial convolution and state space models for lung cancer histopathological image classification

Abstract

Highlights • PCMamba integrates Partial Convolution with State Space Models for lung cancer classification.• Achieves 94.17% accuracy and 99.28% AUC on the LungHist700 dataset.• Dual-branch design captures both local textures and long-range tissue dependencies.• Reduces computational cost by 75% while maintaining state-of-the-art performance.