ADNP-15: An Open-Source Histopathological Dataset for Neuritic Plaque Segmentation in Human Brain Whole Slide Images with Frequency Domain Image Enhancement for Stain Normalization

TL;DR

The paper addresses the challenge of neuritic plaque segmentation in Alzheimer's disease by introducing ADNP-15, an open-source whole-slide image dataset from 15 brains with 4000 expert-annotated plaques. It standardizes evaluation across four stain normalization methods and five deep learning models, and introduces a lightweight frequency-domain enhancement applied to the green channel using a Fourier transform, a low-pass filter, and a Laplacian-based kernel to improve segmentation under staining variability. The study demonstrates that the enhancement consistently improves segmentation metrics, with DynUNet and certain normalization methods (notably Reinhard and Vahadane) achieving the best performance, and highlights the importance of combining normalization and enhancement for robust WSI segmentation. This work provides a valuable benchmark and open resources to accelerate research in Alzheimer's pathology and computational histopathology.

Abstract

Alzheimer's Disease (AD) is a neurodegenerative disorder characterized by amyloid-beta plaques and tau neurofibrillary tangles, which serve as key histopathological features. The identification and segmentation of these lesions are crucial for understanding AD progression but remain challenging due to the lack of large-scale annotated datasets and the impact of staining variations on automated image analysis. Deep learning has emerged as a powerful tool for pathology image segmentation; however, model performance is significantly influenced by variations in staining characteristics, necessitating effective stain normalization and enhancement techniques. In this study, we address these challenges by introducing an open-source dataset (ADNP-15) of neuritic plaques (i.e., amyloid deposits combined with a crown of dystrophic tau-positive neurites) in human brain whole slide images. We establish a comprehensive benchmark by evaluating five widely adopted deep learning models across four stain normalization techniques, providing deeper insights into their influence on neuritic plaque segmentation. Additionally, we propose a novel image enhancement method that improves segmentation accuracy, particularly in complex tissue structures, by enhancing structural details and mitigating staining inconsistencies. Our experimental results demonstrate that this enhancement strategy significantly boosts model generalization and segmentation accuracy. All datasets and code are open-source, ensuring transparency and reproducibility while enabling further advancements in the field.

Figures (8)

• Figure 1: The architecture of the proposed method.
• Figure 2: The enhanced images after the frequency domain enhancement operation.
• Figure 3: Examples of different stain normalization techniques applied to pathological patch images and their corresponding annotated masks.
• Figure 4: Comparison of annotated masks (neuritic plaque) and segmentation results for images processed using four different normalization methods (including images after enhancement), obtained from five deep learning models.
• Figure 5: Comparison of Dice score for Best Color Normalization Methods Before and After Data Enhancement.