One-Shot Neural Architecture Search with Network Similarity Directed Initialization for Pathological Image Classification
This work addresses computational inefficiencies in pathological image classification for medical applications, though it appears incremental by adapting existing NAS methods to a specific domain.
The paper tackled the mismatch between computer vision models and pathological image analysis by proposing a Network Similarity Directed Initialization strategy and integrating domain adaptation into one-shot neural architecture search, resulting in improved classification performance and feature localization on the BRACS dataset.
Deep learning-based pathological image analysis presents unique challenges due to the practical constraints of network design. Most existing methods apply computer vision models directly to medical tasks, neglecting the distinct characteristics of pathological images. This mismatch often leads to computational inefficiencies, particularly in edge-computing scenarios. To address this, we propose a novel Network Similarity Directed Initialization (NSDI) strategy to improve the stability of neural architecture search (NAS). Furthermore, we introduce domain adaptation into one-shot NAS to better handle variations in staining and semantic scale across pathology datasets. Experiments on the BRACS dataset demonstrate that our method outperforms existing approaches, delivering both superior classification performance and clinically relevant feature localization.