DiffKillR: Killing and Recreating Diffeomorphisms for Cell Annotation in Dense Microscopy Images

TL;DR

DiffKillR introduces a neural network framework that uses diffeomorphism-invariant features and image registration to efficiently propagate cell annotations in dense microscopy images, reducing manual labeling effort.

Contribution

It presents a novel approach combining archetype matching and image registration for cell annotation, with theoretical analysis and validation on multiple microscopy tasks.

Findings

Effective annotation propagation with minimal manual labels

Outperforms existing supervised, semi-supervised, and unsupervised methods

Applicable to various pixel-level annotation tasks

Abstract

The proliferation of digital microscopy images, driven by advances in automated whole slide scanning, presents significant opportunities for biomedical research and clinical diagnostics. However, accurately annotating densely packed information in these images remains a major challenge. To address this, we introduce DiffKillR, a novel framework that reframes cell annotation as the combination of archetype matching and image registration tasks. DiffKillR employs two complementary neural networks: one that learns a diffeomorphism-invariant feature space for robust cell matching and another that computes the precise warping field between cells for annotation mapping. Using a small set of annotated archetypes, DiffKillR efficiently propagates annotations across large microscopy images, reducing the need for extensive manual labeling. More importantly, it is suitable for any type of pixel-level annotation. We will discuss the theoretical properties of DiffKillR and validate it on three microscopy tasks, demonstrating its advantages over existing supervised, semi-supervised, and unsupervised methods. The code is available at https://github.com/KrishnaswamyLab/DiffKillR.