Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a D4-equivariant diffusion framework for anomaly detection in computational cytology, addressing the challenges posed by the rarity and heterogeneity of malignant cells in whole-slide images. By enforcing rotation and reflection symmetry through a D4-equivariant U-Net and equivariant noise coupling, the method achieves transformation-consistent reconstructions and stable anomaly rankings. The proposed approach outperforms existing generative baselines and other methods in terms of AUC and retrieval of abnormal cells, while significantly reducing score variance across transformations.
Achieving transformation-consistent anomaly detection in cytology could revolutionize how we identify malignant cells in rare and heterogeneous datasets.
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/.