Deep Learning-Based Automatic Assessment of AgNOR-scores in Histopathology Images
This work addresses the need for automation in histopathology to improve efficiency and consistency in tumor prognosis assessment, representing an incremental advancement in applying deep learning to a specific medical imaging task.
The paper tackles the laborious task of manually detecting argyrophilic nucleolar organizer regions (AgNORs) in histopathology images by developing a deep learning-based pipeline for automatic AgNOR-score assessment, achieving a mean squared error of 0.054 compared to expert pathologists, indicating human-comparable performance.
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.