Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Histopathology Image Normalization via Latent Manifold Compaction

Xiaolong Zhang, Jianwei Zhang, Selim Sevim, Emek Demir, Ece Eksi, Xubo Song

TL;DR

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.

Abstract

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.

Histopathology Image Normalization via Latent Manifold Compaction

TL;DR

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.

Abstract

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.
Paper Structure (18 sections, 3 equations, 3 figures, 2 tables)

This paper contains 18 sections, 3 equations, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Method
  3. Stain-Induced Manifold Generation
  4. Manifold Compaction in Latent Space
  5. Experiments
  6. Experimental Settings
  7. ViT Backbone and Training.
  8. Baselines.
  9. Tumor Metastasis Classification
  10. Dataset and Setup.
  11. Results.
  12. Prostate Multi-class Gleason Grading
  13. Dataset and Setup.
  14. Results.
  15. Mitotic Figure Detection
  16. ...and 3 more sections

Figures (3)

  • Figure 1: (a) Manifold generated by varying H and E intensities of each image induces a local 2D manifold in latent space. All points on the manifold are compacted to a single point $Z^n$, which is a stain-invariant representation that reduces batch effects while preserving biological structure. (b) LMC applies H&E stain-space augmentations, encodes paired views with a Vision Transformer (ViT) backbone, and enforces batch-invariant representations using a contrastive loss.
  • Figure 2: Camelyon16 visualization and quantification of batch separation results. (a-d) Qualitative UMAPs. (e) Quantitative batch separations measured by CFD and W2. $\bigcirc$-Normal, $\triangle$-Tumor.
  • Figure 3: Camelyon16 RAD-trained Model Cross-batch Test (on UNI): ROC and AUC. Our model (solid black line) achieves the best AUC among all compared methods.