Machine learning quantification of Amyloid-β deposits in the temporal lobe of 131 brain bank cases

Aug 4, 2026

Upload by Hazel

Accurate, scalable quantification of amyloid-β (Aβ) pathology is essential for deeper disease phenotyping and progress in Alzheimer disease (AD) research. This multidisciplinary study addresses neuropathology limitations by using a machine learning pipeline to generate granular Aβ deposit quantification and map distribution across the temporal lobe. Using 131 whole-slide images from consecutive autopsied cases, the workflow validates quantification in white and gray matter, defines Aβ deposit-type distributions, and links Aβ deposits with dementia status and mixed pathology.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Introduction

Amyloid-β pathology and AD relevance

Traditional neuropathology workflows and imaging advances

Whole-slide imaging and ML quantification

UC Davis UC Davis Previously Published Works Title Machine learning quantification of Amyloid-β deposits in the temporal lobe of 131 brain bank cases Permalink [https://escholarship.org/uc/item/3ch4n9tv](https://escholarship.org/uc/item/3ch4n9tv) Journal Acta Neuropathologica Communications, 12(1) ISSN 2051-5960 Authors Scalco, Rebeca Oliveira, Luca C Lai, Zhengfeng et al. Publication Date 2024 DOI 10.1186/s40478-024-01827-7 Copyright Information This work is made available under the terms of a Creative Commons AttributionNonCommercial-ShareAlike License, available at [https://creativecommons.org/licenses/by-nc-sa/4.0/](https://creativecommons.org/licenses/by-nc-sa/4.0/) Peer reviewed [eScholarship.org](eScholarship.org) Powered by the California Digital Library University of California RESEARCH Open Access Machine learning quantification of Amyloid-β deposits in temporal lobe of 131 brain bank cases Rebeca Scalco 1,5^, Luca C. Oliveira 1,4^, Zhengfeng Lai 1,4, Danielle J. Harvey 1,2, Lana Abujamil 1, Charles DeCarli3, Lee-Way Jin 1, Chen-Nee Chuah4 and Brittany N. Dugger 1* Abstract Accurate and scalable quantification of amyloid-β (Aβ) pathology is crucial for deeper disease phenotyping and furthering research in Alzheimer Disease (AD) . This multidisciplinary study addresses the current limitations on neuropathology by leveraging a machine learning (ML) pipeline to perform a granular quantification of Aβ deposits and assess their distribution in the temporal lobe. Utilizing 131 whole-slide-images from consecutive autopsied cases at the University of California Davis Alzheimer Disease Research Center, our objectives were threefold: (1) Validate an automatic workflow for Aβ deposit quantification in white matter (WM) and gray matter (GM); (2) define the distributions of different Aβ deposit types in GM and WM, and (3) investigate correlates of Aβ deposits with dementia status and the presence of mixed pathology. Our methodology highlights the robustness and efficacy of the ML pipeline, demonstrating proficiency akin to experts’ evaluations. We provide comprehensive insights into the quantification and distribution of Aβ deposits in the temporal GM and WM revealing a progressive increase in tandem with the severity of established diagnostic criteria (NIA-AA) . We also present correlations of Aβ load with clinical diagnosis as well as presence/absence of mixed pathology. This study introduces a reproducible workflow, showcasing the practical use of ML approaches in the field of neuropathology, and use of the output data for correlative analyses. Acknowledging limitations, such as potential biases in the ML model and current ML classifications, we propose avenues for future research to refine and expand the methodology. We hope to contribute to the broader landscape of neuropathology advancements, ML applications, and precision medicine, paving the way for deep phenotyping of AD brain cases and establishing a foundation for further advancements inneuropathological research. Keywords Machine learning, Quantitative analysis, Neuropathology, Whole-slide imaging, Clinicopathological correlation Rebeca Scalco and Luca C. Oliveira share first authorship. *Correspondence: Brittany N. Dugger [bndugger@ucdavis.edu](bndugger@ucdavis.edu) 1Department of Pathology and Laboratory Medicine, University of California Davis, 4645 2nd Ave. 3400a research building III, Sacramento, CA 95817, USA 2Department of Public Health Sciences, University of California Davis, School of Medicine, Sacramento, CA, USA 3Department of Neurology, University of California Davis, School of Medicine, Sacramento, CA, USA 4Department of Electrical and Computer Engineering, University of California Davis, Davis, CA, USA 5Present address: Institute of Animal Pathology, Vetsuisse Faculty, University of Bern, Länggassstrasse 122, 3012 Bern, Switzerland Page 2 of 16 Introduction Postmortem histopathol

FAQs

What is the main goal of this study?

To build and validate a machine learning workflow that quantifies amyloid-β deposits and characterizes their distribution in the temporal lobe.

How many cases and what data type are used?

The study analyzes 131 whole-slide images from consecutive autopsied brain bank cases.

Which biological compartments and deposit types are analyzed?

Quantification covers both white matter and gray matter, and deposit-type distributions are defined within those regions.

Aug 4, 2026

Upload by Hazel