# Group Equivariant Diffusion for Anomaly Detection in Computational Cytology

arXiv: https://arxiv.org/abs/2607.25503 · HTML: https://mlsanity.com/paper/2607.25503/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 18 of 18)

- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Diffusion Models for Medical Anomaly Detection](https://mlsanity.com/paper/2203.04306/) (2022)
- [Denoising Diffusion Bridge Models](https://mlsanity.com/paper/2309.16948/) (2023)
- [Deep Learning for Medical Anomaly Detection -- A Survey](https://mlsanity.com/paper/2012.02364/) (2020)
- [Mask, Stitch, and Re-Sample: Enhancing Robustness and Generalizability in Anomaly Detection through Automatic Diffusion Models](https://mlsanity.com/paper/2305.19643/) (2023)
- [Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis](https://mlsanity.com/paper/2002.08725/) (2020)
- [Diffusion Models with Implicit Guidance for Medical Anomaly Detection](https://mlsanity.com/paper/2403.08464/) (2024)
- [Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning](https://mlsanity.com/paper/2210.09452/) (2022)
- [Deep Learning for Computational Cytology: A Survey](https://mlsanity.com/paper/2202.05126/) (2022)
- [Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2407.06635/) (2024)
- [MAD-AD: Masked Diffusion for Unsupervised Brain Anomaly Detection](https://mlsanity.com/paper/2502.16943/) (2025)
- [Binary Noise for Binary Tasks: Masked Bernoulli Diffusion for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2403.11667/) (2024)
- [DeepSet SimCLR: Self-supervised deep sets for improved pathology representation learning](https://mlsanity.com/paper/2402.15598/) (2024)
- [Structure Preserving Diffusion Models](https://mlsanity.com/paper/2402.19369/) (2024)
- [Denoising Diffusion Models for Anomaly Localization in Medical Images](https://mlsanity.com/paper/2410.23834/) (2024)

## Abstract (arXiv)

Computational cytology on whole-slide images is challenging because malignant cells are rare, heterogeneous, and annotated slides are scarce. Anomaly detection frameworks can be trained on normal slide-negative patches and then applied at test time to flag abnormal patches in held-out slides. Most unsupervised anomaly detection approaches including generative ones (GAN-based and diffusion-based), are tuned to organ-level imaging and require large curated datasets. In cytology the signal is cell-centric: rotating or flipping a single-cell patch does not change its diagnostic class, yet standard diffusion models treat transformed views as distinct inputs, leading to transformation-dependent reconstructions and unstable anomaly scores. We propose a D4-equivariant diffusion framework that enforces rotation and reflection symmetry both architecturally, via a D4-equivariant U-Net, and at inference, via equivariant noise coupling and (optionally) frame averaging. This alignment with biological invariance yields transformation-consistent pseudo-healthy reconstructions and more stable anomaly ranking under symmetry. On two publicly available cytology datasets of bone marrow and peripheral blood smears, our D4-equivariant diffusion models achieve higher AUC and retrieve more abnormal cells in the top K predictions than non-equivariant generative baselines, a deep one-class, and a multiple instance learning based method, while substantially reducing score variance across rotations and flips. Code is available at https://swchmida.github.io/D4diffCyto/.