BrainSec: Automated Brain Tissue Segmentation Pipeline for Scalable Neuropathological Analysis

Abstract

As neurodegenerative disease pathological hallmarks have been reported in both grey matter (GM) and white matter (WM) with different density distributions, automating the segmentation process of GM/WM would be extremely advantageous for aiding 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 timeconsuming and subjective, preventing a scalable analysis on pathology images. This paper proposes an automated segmentation pipeline (BrainSec) combining a Convolutional Neural Network (CNN) module for segmenting GM/WM regions and a post-processing module to remove artifacts/residues of tissues. The final output generates 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 patch-based approach, BrainSec, to classify the GM/WM/background regions. We demonstrate BrainSec is robust and has reliable performance by testing it on over 180 WSIs that incorporate numerous unique cases as well as distinct neuroanatomic brain regions. We also apply gradient-weighted class activation mapping (Grad-CAM) to interpret the segmentation masks and provide relevant explanations and insights. In addition, we have integrated BrainSec with an existing Amyloid-β pathology classification model into a unified framework (without incurring significant computation complexity) to identify pathologies, visualize their distributions, and quantify each type of pathologies in segmented GM/WM regions, respectively.

Preanalytic variable effects on segmentation and quantification machine learning algorithms for amyloid-β analyses on digitized human brain slides

“…Recent studies utilizing ML/DL in pathology have been successful in displaying high prediction performance (7,8,9,23). However, due to the blackbox nature of trained DL models, rigorous testing is needed since there is no guarantee a model trained with a set of data may have the same performance when applied to data with different pre-analytic variables.…”

“…Both ResNet and VGG are commonly used CNN-based DL architectures. The pipeline used to generate both models' predictions were similar to the one described in (23). We patched each WSI in 256x256 segments and those patches were the input to both classification and segmentation models simultaneously as pictured in Figure 2.…”

“…By analyzing the saliency maps generated from each 256x256 patch, we can observe which areas of each patch contributed most to the final model output and how these areas may differ according to the pre-analytical variables. That is especially relevant for the WM/GM segmentation DL model, as there is no obvious single structure linked to the predictions such as an Amyloid-β plaque classification, as it relies on features such as texture of the tissue, as shown previously (23).…”