# A Closer Look at Domain Shift for Deep Learning in Histopathology

arXiv: https://arxiv.org/abs/1909.11575 · HTML: https://mlsanity.com/paper/1909.11575/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2019.

## Built on by (most cited first, 25 of 25)

- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [An Empirical Framework for Domain Generalization in Clinical Settings](https://mlsanity.com/paper/2103.11163/) (2021)
- [Learning to Predict RNA Sequence Expressions from Whole Slide Images with Applications for Search and Classification](https://mlsanity.com/paper/2203.13997/) (2022)
- [Contour Proposal Networks for Biomedical Instance Segmentation](https://mlsanity.com/paper/2104.03393/) (2021)
- [Improving Self-supervised Learning with Hardness-aware Dynamic Curriculum Learning: An Application to Digital Pathology](https://mlsanity.com/paper/2108.07183/) (2021)
- [Domain generalization in deep learning-based mass detection in mammography: A large-scale multi-center study](https://mlsanity.com/paper/2201.11620/) (2022)
- [A Systematic Review of Generalization Research in Medical Image Classification](https://mlsanity.com/paper/2403.12167/) (2024)
- [Domain-Adaptive Neural Posterior Estimation for Strong Gravitational Lens Analysis](https://mlsanity.com/paper/2410.16347/) (2024)
- [Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation](https://mlsanity.com/paper/2105.07715/) (2021)
- [A Pathology Deep Learning System Capable of Triage of Melanoma Specimens Utilizing Dermatopathologist Consensus as Ground Truth](https://mlsanity.com/paper/2109.07554/) (2021)
- [Test Time Transform Prediction for Open Set Histopathological Image Recognition](https://mlsanity.com/paper/2206.10033/) (2022)
- [Primary Tumor and Inter-Organ Augmentations for Supervised Lymph Node Colon Adenocarcinoma Metastasis Detection](https://mlsanity.com/paper/2109.09518/) (2021)
- [Active Learning Based Domain Adaptation for Tissue Segmentation of Histopathological Images](https://mlsanity.com/paper/2303.05225/) (2023)
- [Geometric Data Augmentations to Mitigate Distribution Shifts in Pollen Classification from Microscopic Images](https://mlsanity.com/paper/2311.11029/) (2023)
- [Beyond Real Data: Synthetic Data through the Lens of Regularization](https://mlsanity.com/paper/2510.08095/) (2025)
- [Evaluating Generic Auto-ML Tools for Computational Pathology](https://mlsanity.com/paper/2112.03622/) (2021)
- [Conditional Deep Convolutional Neural Networks for Improving the Automated Screening of Histopathological Images](https://mlsanity.com/paper/2105.14338/) (2021)
- [Cascade RCNN for MIDOG Challenge](https://mlsanity.com/paper/2109.01085/) (2021)
- [A benchmark with decomposed distribution shifts for 360 monocular depth estimation](https://mlsanity.com/paper/2112.00432/) (2021)
- [Source-free Domain Adaptation Requires Penalized Diversity](https://mlsanity.com/paper/2304.02798/) (2023)
- [Adenocarcinoma Segmentation Using Pre-trained Swin-UNet with Parallel Cross-Attention for Multi-Domain Imaging](https://mlsanity.com/paper/2409.15501/) (2024)
- [State-of-the-Art Periorbital Distance Prediction and Disease Classification Using Periorbital Features](https://mlsanity.com/paper/2409.18769/) (2024)
- [UWarp: A Whole Slide Image Registration Pipeline to Characterize Scanner-Induced Local Domain Shift](https://mlsanity.com/paper/2503.20653/) (2025)
- [Uncertainty-Guided Selective Adaptation Enables Cross-Platform Predictive Fluorescence Microscopy](https://mlsanity.com/paper/2511.12006/) (2025)
- [Magnification-Invariant Image Classification via Domain Generalization and Stable Sparse Embedding Signatures](https://mlsanity.com/paper/2604.25817/) (2026)

## Abstract (arXiv)

Domain shift is a significant problem in histopathology. There can be large differences in data characteristics of whole-slide images between medical centers and scanners, making generalization of deep learning to unseen data difficult. To gain a better understanding of the problem, we present a study on convolutional neural networks trained for tumor classification of H&E stained whole-slide images. We analyze how augmentation and normalization strategies affect performance and learned representations, and what features a trained model respond to. Most centrally, we present a novel measure for evaluating the distance between domains in the context of the learned representation of a particular model. This measure can reveal how sensitive a model is to domain variations, and can be used to detect new data that a model will have problems generalizing to. The results show how learning is heavily influenced by the preparation of training data, and that the latent representation used to do classification is sensitive to changes in data distribution, especially when training without augmentation or normalization.