MamMIL: Multiple Instance Learning for Whole Slide Images with State Space Models

arXiv:2403.05160v1 Announce Type: new
Abstract: Recently, pathological diagnosis, the gold standard for cancer diagnosis, has achieved superior performance by combining the Transformer with the multiple instance learning (MIL) framework using whole slide images (WSIs). However, the giga-pixel nature of WSIs poses a great challenge for the quadratic-complexity self-attention mechanism in Transformer to be applied in MIL. Existing studies usually use linear attention to improve computing efficiency but inevitably bring performance bottlenecks. To tackle this challenge, we propose a MamMIL framework …

abstract arxiv attention cancer cancer diagnosis challenge complexity cs.cv diagnosis framework however images instance mil multiple nature performance pixel self-attention space standard state transformer type