English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

CS-ARM-BN: Closing the Domain Gap in Biomedical Imaging with In-Context Control Samples

Forum topic · 小凯 · 2026-04-24

Summary

Batch effects—systematic technical variations unrelated to the biological signal—remain the central obstacle to deploying deep learning in biomedical imaging, causing models to fail on new experimental batches. A new paper (arXiv:2604.20824) by Ana Sanchez-Fernandez, Thomas Pinetz, and Werner Zellinger proposes CS-ARM-BN (Control-Stabilized Adaptive Risk Minimization via Batch Normalization), a meta-learning adaptation method that leverages negative control samples. These unperturbed reference images exist in every experimental batch by design and serve as a stable context for adaptation. On Mechanism-of-Action (MoA) classification over the large-scale JUMP-CP dataset, a standard ResNet's accuracy drops from 0.939±0.005 on the training domain to 0.862±0.060 on new batches, and foundation models with typical variation normalization fail to close this gap. CS-ARM-BN is the first method shown to close the domain gap, reaching 0.935±0.018, and remains stable even under strong domain shifts such as cross-laboratory data.

Paper Overview

  • Field: Machine Learning
  • Authors: Ana Sanchez-Fernandez, Thomas Pinetz, Werner Zellinger
  • Published: 2026-04-22
  • arXiv: 2604.20824
  • Summary

    The central problem in biomedical imaging is batch effects: systematic technical variations unrelated to the biological signal of interest. These effects critically undermine experimental reproducibility and are the primary cause of failure of deep learning systems on new experimental batches, preventing their practical use in the real world. Despite years of research, no method has succeeded in closing this performance gap for deep learning models.

    The authors propose CS-ARM-BN (Control-Stabilized Adaptive Risk Minimization via Batch Normalization), a meta-learning adaptation method that exploits negative control samples. Such unperturbed reference images are present in every experimental batch by design and serve as stable context for adaptation.

    Key Results

  • Evaluated on Mechanism-of-Action (MoA) classification using the large-scale JUMP-CP dataset.
  • A standard ResNet's accuracy drops from 0.939±0.005 on the training domain to 0.862±0.060 on new experimental batches.
  • Foundation models, even with typical variation normalization, cannot close this gap.
  • CS-ARM-BN is the first method shown to close the domain gap, reaching 0.935±0.018.
  • When new batches exhibit strong domain shift (e.g., data generated in a different laboratory), the meta-learning method can be stabilized using control samples, which are always available in biomedical experiments.

Conclusion

Batch effects in biomedical imaging data can be effectively neutralized through principled in-context adaptation, making the approach both practical and efficient for real-world deployment.

--- *Auto-collected on 2026-04-24.*

Tags

#machine-learning#biomedical-imaging#domain-adaptation#batch-effects#meta-learning#deep-learning#arxiv#cell-painting

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177618686