Automated Segmentation of Amyloid-βStained Whole Slide Images of Brain Tissue

Abstract

Neurodegenerative disease pathologies have been reported in both grey matter (GM) and white matter (WM) with different density distributions, an automated separation task of GM/WM would be extremely advantageous for aid in neuropathologic deep phenotyping. Standard segmentation methods typically involve manual annotations, where a trained researcher traces the delineation of GM/WM in ultra-high-resolution Whole Slide Images (WSIs). This method can be time-consuming and subjective, preventing the analysis of large amounts of WSIs in a scalable way. In this paper, we propose an automated segmentation pipeline combining a Convolutional Neural Network (CNN) module for segmenting GM/WM regions and a post-processing module to remove artifacts/residues of tissues as well as generate XML annotations that can be visualized via Aperio ImageScope. First, we investigate two baseline models for medical image segmentation: FCN, and U-Net. Then we propose a new patch-based approach, ResNet-Patch, to classify the GM/WM/background regions. In addition, we integrate a Neural Conditional Random Field (NCRF) module, ResNet-NCRF, to model and incorporate the spatial correlations among neighboring patches. Although their mechanisms are greatly different, both U-Net and ResNet-Patch/ResNet-NCRF achieve Intersection over Union (IoU) of more than 90% in GM and more than 80% in WM, while ResNet-Patch achieves 1% superior to U-Net with lower variance among various WSIs. ResNet-NCRF further improves the IoU by 3% for WM compared to ResNet-Patch before post-processing. We also apply gradient-weighted class activation mapping (Grad-CAM) to interpret the segmentation masks and provide clinical explanations and insights.

Advances in Deep Neuropathological Phenotyping of Alzheimer Disease: Past, Present, and Future

“…A specific class of CNN models named U-NET, is particularly effective at analyzing WSI in segments (i.e. image segmentation) ( 180 ), which can prove to be helpful in determining the regional differences of AD pathology deposition ( 181 ). U-NET is loosely defined as a fully functioning CNN, and it was first described in 2017 ( 182 ).…”

“…It has also been compared with expert pathologist opinion in detecting and quantifying immune cells in certain cancers, and has shown a moderately high agreement score with the pathologist evaluation ( 184 ). In terms of AD, the model has been used to aid in gray matter and white matter segmentation ( 181 ); and Wurts et al ( 185 ) have recently hypothesized that a pretrained U-NET model may be successful at identifying and segmenting tau pathologies in AD.…”