{"doi":"10.1101/2020.11.13.381871","title":"Automated Segmentation of Amyloid- <i>β</i> Stained Whole Slide Images of Brain Tissue","abstract":"Abstract Neurodegenerative disease pathologies have been reported in both grey matter (GM) and white matter (WM) with different density distributions, an automated separation 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 time-consuming and subjective, preventing the analysis of large amounts of WSIs at scale. This paper proposes 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 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 relevant explanations and insights.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2020,"id":125602,"datarank":0.19516157337344592,"base_score":1.0986122886681096,"endowment":1.0986122886681096,"self_citation_contribution":0.16479184330021646,"citation_network_contribution":0.03036973007322947,"self_endowment_contribution":0.16479184330021646,"citer_contribution":0.03036973007322947,"corpus_percentile":null,"corpus_rank":null,"citation_count":2,"citer_count":2,"citers_with_citation_signal":2,"citers_with_endowment":2,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9469,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2020-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":573041,"name":"Runlin Guo","orcid":null,"position":1,"is_corresponding":false},{"id":573042,"name":"Wenda Xu","orcid":null,"position":2,"is_corresponding":false},{"id":573043,"name":"Zin Hu","orcid":null,"position":3,"is_corresponding":false},{"id":573044,"name":"Kelsey Mifflin","orcid":null,"position":4,"is_corresponding":false},{"id":277082,"name":"Charles DeCarli","orcid":"0000-0003-1914-2693","position":5,"is_corresponding":false},{"id":96,"name":"Brittany N. Dugger","orcid":"0000-0003-2141-8855","position":6,"is_corresponding":false},{"id":573045,"name":"Sen-ching Cheung","orcid":null,"position":7,"is_corresponding":false},{"id":573046,"name":"Chen-Nee Chuah","orcid":null,"position":8,"is_corresponding":false},{"id":435625,"name":"Zhengfeng Lai","orcid":"0000-0002-2984-7913","position":0,"is_corresponding":true}],"reference_count":55,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-18T23:15:19.482428Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}