Histopathology Image Normalization via Latent Manifold Compaction
This addresses the challenge of cross-batch generalization for computational pathology, enabling more reliable deployment across clinical sites, though it appears incremental as it builds on existing normalization methods.
The paper tackled the problem of batch effects in histopathology images by introducing Latent Manifold Compaction (LMC), an unsupervised framework that learns batch-invariant embeddings, resulting in substantial reduction of batch-induced separations and outperforming state-of-the-art methods in cross-batch classification and detection tasks.
Batch effects arising from technical variations in histopathology staining protocols, scanners, and acquisition pipelines pose a persistent challenge for computational pathology, hindering cross-batch generalization and limiting reliable deployment of models across clinical sites. In this work, we introduce Latent Manifold Compaction (LMC), an unsupervised representation learning framework that performs image harmonization by learning batch-invariant embeddings from a single source dataset through explicit compaction of stain-induced latent manifolds. This allows LMC to generalize to target domain data unseen during training. Evaluated on three challenging public and in-house benchmarks, LMC substantially reduces batch-induced separations across multiple datasets and consistently outperforms state-of-the-art normalization methods in downstream cross-batch classification and detection tasks, enabling superior generalization.