# Destroy Me: Automatic Artifact Generation for Histopathology Images

arXiv: https://arxiv.org/abs/2608.27516 · HTML: https://mlsanity.com/paper/2608.27516/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Builds on (most cited first, 11 of 11)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation](https://mlsanity.com/paper/2404.09556/) (2024)
- [Artificial Intelligence for Digital and Computational Pathology](https://mlsanity.com/paper/2401.06148/) (2023)
- [Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks](https://mlsanity.com/paper/1901.11489/) (2019)
- [Computational Pathology: Challenges and Promises for Tissue Analysis](https://mlsanity.com/paper/1601.00027/) (2015)
- [Metrics that matter: Evaluating image quality metrics for medical image generation](https://mlsanity.com/paper/2505.07175/) (2025)
- [Equipping Computational Pathology Systems with Artifact Processing Pipelines: A Showcase for Computation and Performance Trade-offs](https://mlsanity.com/paper/2403.07743/) (2024)
- [PathDiff: Histopathology Image Synthesis with Unpaired Text and Mask Conditions](https://mlsanity.com/paper/2506.23440/) (2025)
- [Improving Quality Control of Whole Slide Images by Explicit Artifact Augmentation](https://mlsanity.com/paper/2406.11538/) (2024)
- [Semantic Segmentation Based Quality Control of Histopathology Whole Slide Images](https://mlsanity.com/paper/2410.03289/) (2024)

## Abstract (arXiv)

Deep learning's diagnostic utility in pathology is constrained by model vulnerability to real-world data imperfections. While current strategies favor "perfect data" by filtering low-quality regions, which can lead to the loss of valuable diagnostic context, we propose a paradigm shift: engineering models to thrive in imperfect environments using "Destroy Me", a hybrid framework for realistic artifact synthesis and robust data augmentation. Our approach combines Stable Diffusion, fine-tuned to preserve morphological continuity by realistically integrating artifacts with the underlying tissue architecture, with physics-based procedural modeling to synthesize six common artifact types: tissue folds, precipitates, blur, stitching errors, dust, and pen markers. Artifact fidelity is assessed using Kernel Inception Distance (KID) and color Wasserstein distance metrics. Validating this strategy on lung adenocarcinoma pattern classification with an nnU-Net, we confirm that models trained on "destroyed" patches consistently outperform baselines on independent real-world datasets. Specifically, we observed a 10.5% relative improvement in macro F1-score and a 15% relative increase in the Cohen's Kappa (kappa) coefficient. Crucially, our results demonstrate that selective, impact-weighted augmentation is vital for balancing practical robustness with the preservation of subtle diagnostic features.