2024/05/15 by Yujie Xiang, Xiang, Yujie, Bojing Liu +3
Computer Science · Engineering · Medicine · #AI in cancer detection #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #I.4 #Image and Video Processing (eess.IV) #J.3 #Medical Imaging and Analysis #Radiomics and Machine Learning in Medical Imaging #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2405.09298
openalex publication_date 2024/05/15 · openalex created_date 2024/05/17 · openalex updated_date 2026/07/28
AI-based models for histopathology whole slide image (WSI) analysis are increasingly common, but unsharp or blurred areas within WSI can significantly reduce prediction performance. In this study, we investigated the effect of image blur on deep learning models and introduced a mixture of experts (MoE) strategy that combines predictions from multiple expert models trained on data with varying blur levels. Using H&E-stained WSIs from 2,093 breast cancer patients, we benchmarked performance on grade classification and IHC biomarker prediction with both CNN- (CNNCLAM and MoE-CNNCLAM) and Vision Transformer-based (UNICLAM and MoE-UNICLAM) models. Our results show that baseline models' performance consistently decreased with increasing blur, but expert models trained on blurred tiles and especially our proposed MoE approach substantially improved performance, and outperformed baseline models in a range of simulated scenarios. MoE-CNNCLAM outperformed the baseline CNNCLAM under moderate (AUC: 0.868 vs. 0.702) and mixed blur conditions (AUC: 0.890 vs. 0.875). MoE-UNICLAM outperformed the baseline UNICLAM model in both moderate (AUC: 0.950 vs. 0.928) and mixed blur conditions (AUC: 0.944 vs. 0.931). This MoE method has the potential to enhance the reliability of AI-based pathology models under variable image quality, supporting broader application in both research and clinical settings.