Weakly annotated bioimages get domain knowledge: seven model families improve at once
Automated feature extraction from weakly annotated bioimaging data performs inconsistently across datasets because models depend on the images alone. A model-agnostic knowledge augmentation method lets machine learning models exploit domain knowledge beyond automated feature extraction, improving classification across seven architectures; combined with masked autoencoder self-supervised learning it raises precision by 2.9% over the next-best method on three in-house microscopy datasets and by 6.8% on average across three public cytomorphology benchmarks.