# Nuclear Segmentation and Classification: On Color & Compression Generalization

arXiv: https://arxiv.org/abs/2301.03418 · HTML: https://mlsanity.com/paper/2301.03418/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 9 Jan 2023.

## Builds on (most cited first, 14 of 14)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [Lizard: A Large-Scale Dataset for Colonic Nuclear Instance Segmentation and Classification](https://mlsanity.com/paper/2108.11195/) (2021)
- [CoNIC: Colon Nuclei Identification and Counting Challenge 2022](https://mlsanity.com/paper/2111.14485/) (2021)
- [Learning domain-agnostic visual representation for computational pathology using medically-irrelevant style transfer augmentation](https://mlsanity.com/paper/2102.01678/) (2021)
- [Panoptic segmentation with highly imbalanced semantic labels](https://mlsanity.com/paper/2203.11692/) (2022)
- [ConvNeXt-backbone HoVerNet for nuclei segmentation and classification](https://mlsanity.com/paper/2202.13560/) (2022)
- [ciscNet -- A Single-Branch Cell Instance Segmentation and Classification Network](https://mlsanity.com/paper/2202.13960/) (2022)
- [Color Space-based HoVer-Net for Nuclei Instance Segmentation and Classification](https://mlsanity.com/paper/2203.01940/) (2022)

## Built on by (most cited first, 4 of 4)

- [CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting](https://mlsanity.com/paper/2303.06274/) (2023)
- [StainFuser: Controlling Diffusion for Faster Neural Style Transfer in Multi-Gigapixel Histology Images](https://mlsanity.com/paper/2403.09302/) (2024)
- [Benchmarking Domain Generalization Algorithms in Computational Pathology](https://mlsanity.com/paper/2409.17063/) (2024)
- [A protocol for evaluating robustness to H&E staining variation in computational pathology models](https://mlsanity.com/paper/2603.12886/) (2026)

## Abstract (arXiv)

Since the introduction of digital and computational pathology as a field, one of the major problems in the clinical application of algorithms has been the struggle to generalize well to examples outside the distribution of the training data. Existing work to address this in both pathology and natural images has focused almost exclusively on classification tasks. We explore and evaluate the robustness of the 7 best performing nuclear segmentation and classification models from the largest computational pathology challenge for this problem to date, the CoNIC challenge. We demonstrate that existing state-of-the-art (SoTA) models are robust towards compression artifacts but suffer substantial performance reduction when subjected to shifts in the color domain. We find that using stain normalization to address the domain shift problem can be detrimental to the model performance. On the other hand, neural style transfer is more consistent in improving test performance when presented with large color variations in the wild.