Slideflow: deep learning for digital histopathology with real-time whole-slide visualization

TLDR

Deep learning has become a powerful tool for analyzing histopathological images, yet most approaches are domain‑specific, tied to particular software, and few open‑source solutions exist for interactive deployment. The authors created Slideflow, a flexible deep‑learning library for digital pathology that supports many methods and offers a fast whole‑slide interface for model deployment. Slideflow provides a framework‑agnostic pipeline with efficient stain normalization, augmentation, weakly‑supervised classification, uncertainty quantification, feature generation, space analysis, explainability, and a GUI that visualizes predictions and heatmaps in real time on diverse hardware, including ARM devices. The optimized processing enables extraction of 40× tiles from a whole‑slide image in just 2.5 s.

Abstract

Abstract Deep learning methods have emerged as powerful tools for analyzing histopathological images, but current methods are often specialized for specific domains and software environments, and few open-source options exist for deploying models in an interactive interface. Experimenting with different deep learning approaches typically requires switching software libraries and reprocessing data, reducing the feasibility and practicality of experimenting with new architectures. We developed a flexible deep learning library for histopathology called Slideflow, a package which supports a broad array of deep learning methods for digital pathology and includes a fast whole-slide interface for deploying trained models. Slideflow includes unique tools for whole-slide image data processing, efficient stain normalization and augmentation, weakly-supervised whole-slide classification, uncertainty quantification, feature generation, feature space analysis, and explainability. Whole-slide image processing is highly optimized, enabling whole-slide tile extraction at 40x magnification in 2.5 s per slide. The framework-agnostic data processing pipeline enables rapid experimentation with new methods built with either Tensorflow or PyTorch, and the graphical user interface supports real-time visualization of slides, predictions, heatmaps, and feature space characteristics on a variety of hardware devices, including ARM-based devices such as the Raspberry Pi.