Systematic review of 23 studies with network meta-analysis of deep learning on pretreatment imaging in HNSCC: pooled AUC 0.78 for lymph node and 0.84 for tumour invasion classification; lower in multicentre or externally validated than single-centre studies (0.84 vs 0.92).
Meta-analysisn = 23 studies
Ketschau et al. Deep Learning for Pretreatment Imaging-Based Tumor and Nodal Classification in Head and Neck Squamous Cell Carcinoma: A Systematic Review and Network Meta-Analysis