Deep Learning-Based Automatic Assessment of AgNOR-scores in Histopathology Images

TL;DR

This paper introduces a deep learning pipeline that automates the assessment of AgNOR-scores in histopathology images, achieving accuracy comparable to expert pathologists and potentially streamlining tumor prognosis evaluations.

Contribution

The study develops and validates a novel deep learning method for automatic AgNOR-score determination, providing a performance benchmark against human experts.

Findings

Mean squared error of 0.054 compared to pathologists.

Automated method performs comparably to human experts.

Potential to reduce manual labor in histopathological analysis.

Abstract

Nucleolar organizer regions (NORs) are parts of the DNA that are involved in RNA transcription. Due to the silver affinity of associated proteins, argyrophilic NORs (AgNORs) can be visualized using silver-based staining. The average number of AgNORs per nucleus has been shown to be a prognostic factor for predicting the outcome of many tumors. Since manual detection of AgNORs is laborious, automation is of high interest. We present a deep learning-based pipeline for automatically determining the AgNOR-score from histopathological sections. An additional annotation experiment was conducted with six pathologists to provide an independent performance evaluation of our approach. Across all raters and images, we found a mean squared error of 0.054 between the AgNOR- scores of the experts and those of the model, indicating that our approach offers performance comparable to humans.