CellPilot: A unified approach to automatic and interactive segmentation in histopathology

TL;DR

CellPilot is a comprehensive framework that combines automatic and interactive segmentation for histopathology images, improving accuracy and efficiency in cell and gland segmentation tasks across diverse datasets.

Contribution

It introduces a unified model capable of automatic and guided interactive segmentation, trained on extensive diverse datasets, and provides open-source tools for the community.

Findings

Outperforms existing interactive segmentation tools on multiple datasets

Enables reliable automatic segmentation across diverse tissue types

Provides open-source model and GUI for large-scale annotation

Abstract

Histopathology, the microscopic study of diseased tissue, is increasingly digitized, enabling improved visualization and streamlined workflows. An important task in histopathology is the segmentation of cells and glands, essential for determining shape and frequencies that can serve as indicators of disease. Deep learning tools are widely used in histopathology. However, variability in tissue appearance and cell morphology presents challenges for achieving reliable segmentation, often requiring manual correction to improve accuracy. This work introduces CellPilot, a framework that bridges the gap between automatic and interactive segmentation by providing initial automatic segmentation as well as guided interactive refinement. Our model was trained on over 675,000 masks of nine diverse cell and gland segmentation datasets, spanning 16 organs. CellPilot demonstrates superior performance compared to other interactive tools on three held-out histopathological datasets while enabling automatic segmentation. We make the model and a graphical user interface designed to assist practitioners in creating large-scale annotated datasets available as open-source, fostering the development of more robust and generalized diagnostic models.