mlsanityData to 13 Oct 2026

Assessing and Enhancing Robustness of Deep Learning Models with Corruption Emulation in Digital Pathology

arXiv 2310.20427 ↗First posted 31 Oct 2023eess.IV cs.CV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Deep learning in digital pathology brings intelligence and automation as substantial enhancements to pathological analysis, the gold standard of clinical diagnosis. However, multiple steps from tissue preparation to slide imaging introduce various image corruptions, making it difficult for deep neural network (DNN) models to achieve stable diagnostic results for clinical use. In order to assess and further enhance the robustness of the models, we analyze the physical causes of the full-stack corruptions throughout the pathological life-cycle and propose an Omni-Corruption Emulation (OmniCE) method to reproduce 21 types of corruptions quantified with 5-level severity. We then construct three OmniCE-corrupted benchmark datasets at both patch level and slide level and assess the robustness of popular DNNs in classification and segmentation tasks. Further, we explore to use the OmniCE-corrupted datasets as augmentation data for training and experiments to verify that the generalization ability of the models has been significantly enhanced.

Key facts. Cited by 6 papers in the map (data through 13 Oct 2026). Builds on 17 of its 30 references that are in the map. First posted on arXiv 31 Oct 2023.

Builds on

17 of 30 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,656
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
  4. 2016Densely Connected Convolutional Networkscited by 6,707
  5. 2017Squeeze-and-Excitation Networkscited by 4,772
  6. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,371
  7. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 899
  8. 2018Rotation Equivariant CNNs for Digital Pathologycited by 420
  9. 2021Gradient Matching for Domain Generalizationcited by 258
  10. 2017Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Networkcited by 208
  11. 2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
  12. 2021Extending the WILDS Benchmark for Unsupervised Adaptationcited by 86
5 more
  1. 2016DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentationcited by 84
  2. 2018Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networkscited by 57
  3. 2022Benchmarking the Robustness of Deep Neural Networks to Common Corruptions in Digital Pathologycited by 26
  4. 2021Focus on the Common Good: Group Distributional Robustness Followscited by 25
  5. 2022Robust Medical Image Classification from Noisy Labeled Data with Global and Local Representation Guided Co-trainingcited by 21

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 3; 2025: 1.

6 papers.

  1. 2024MedMNIST-C: Comprehensive benchmark and improved classifier robustness by simulating realistic image corruptionscited by 17
  2. 2024Benchmarking PathCLIP for Pathology Image Analysiscited by 6
  3. 2024PathInsight: Instruction Tuning of Multimodal Datasets and Models for Intelligence Assisted Diagnosis in Histopathologycited by 6
  4. 2023Improving Vision-and-Language Reasoning via Spatial Relations Modelingcited by 5
  5. 2025Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attentioncited by 5
  6. 2023SCAAT: Improving Neural Network Interpretability via Saliency Constrained Adaptive Adversarial Trainingcited by 2