Elucidating the exact contribution of microglia to central nervous system(CNS)pathology has historically been extremely challenging.These resident parenchymal myeloid cells are considered to have critical roles as fro...Elucidating the exact contribution of microglia to central nervous system(CNS)pathology has historically been extremely challenging.These resident parenchymal myeloid cells are considered to have critical roles as frontline responders during pathogen invasion and CNS perturbation.Thus,understanding the precise temporal kinetics of microglial function is central to the evolution of novel therapeutics for disease intervention and/or resolution(Spiteri et al.,2022a).The development of PLX5622,a colony-stimulating factor 1 receptor(CSF-1R)inhibitor typically formulated into a rodent chow for simple oral administration has facilitated exploration of microglial functions in disease(Spangenberg et al.,2019).展开更多
Imaging mass cytometry(IMC)is a high-dimensional imaging technology that allows the capture and quantification of up to fifty biomarkers at sub-cellular resolution.Each IMC dimension(‘channel’)corresponds to antibod...Imaging mass cytometry(IMC)is a high-dimensional imaging technology that allows the capture and quantification of up to fifty biomarkers at sub-cellular resolution.Each IMC dimension(‘channel’)corresponds to antibodies coupled to metaltagged antigens and captures the imaging representation of biomarkers for each cell.Conventional IMC analysis relies on manually segmenting the cells across all IMC channels,which is a time-consuming process and prone to human error.Recent advances in computerized IMC analysis,using deep learning techniques such as convolutional neural networks(CNNs),enable automated segmentation by quantifying cellular structures through a data-driven approach.However,existing CNNbased methods concatenate and integrate IMC image channels at an early stage in the learning process,which potentially limiting the model's ability to retain meaningful correlations among different channels for training.In addition,the cluttered nature and inhomogeneous textures of cellular structures may further complicate the training process,making it even more difficult for CNNs to accurately segment the cell boundaries.In this study,we propose a Stacked Channel Learning Network(SCLN),a two-phase CNN-based method for IMC cell segmentation.SCLN uses a channel embedding approach with two training phases:Phase I generates imaging masks for cellular structures using a pre-trained Res-U-Net model,while Phase II refines the segmentation by incorporating these masks as an additional channel alongside the existing biomarker channels.In addition,SCLN preserves the image representations derived independently from each channel,enabling more detailed channel-level feature analysis.The proposed method was evaluated on the widely used IMC breast cancer METABRIC dataset.The experimental results show that our SCLN achieved a Dice coefficient score of 91.45%,which outperformed the existing segmentation methods by~10%,especially for the challenging studies e.g.,cluttered cells and cells with inhomogeneous textures.Our codes can be found at https://github.com/kongn et-djd/SCLN.展开更多
基金supported by a grant from the Merridew Foundation and NH&MRC ProjectNo.1088242 (to NJCK)+1 种基金supported by the Australian Government Research Training Stipend ScholarshipThe University of Sydney Postgraduate Merit Award
文摘Elucidating the exact contribution of microglia to central nervous system(CNS)pathology has historically been extremely challenging.These resident parenchymal myeloid cells are considered to have critical roles as frontline responders during pathogen invasion and CNS perturbation.Thus,understanding the precise temporal kinetics of microglial function is central to the evolution of novel therapeutics for disease intervention and/or resolution(Spiteri et al.,2022a).The development of PLX5622,a colony-stimulating factor 1 receptor(CSF-1R)inhibitor typically formulated into a rodent chow for simple oral administration has facilitated exploration of microglial functions in disease(Spangenberg et al.,2019).
基金supported in part by Australia Research Council(ARC)grant(DE200103748)Tour de Cure Early Career Research Grant(RSP-120-FY2023).
文摘Imaging mass cytometry(IMC)is a high-dimensional imaging technology that allows the capture and quantification of up to fifty biomarkers at sub-cellular resolution.Each IMC dimension(‘channel’)corresponds to antibodies coupled to metaltagged antigens and captures the imaging representation of biomarkers for each cell.Conventional IMC analysis relies on manually segmenting the cells across all IMC channels,which is a time-consuming process and prone to human error.Recent advances in computerized IMC analysis,using deep learning techniques such as convolutional neural networks(CNNs),enable automated segmentation by quantifying cellular structures through a data-driven approach.However,existing CNNbased methods concatenate and integrate IMC image channels at an early stage in the learning process,which potentially limiting the model's ability to retain meaningful correlations among different channels for training.In addition,the cluttered nature and inhomogeneous textures of cellular structures may further complicate the training process,making it even more difficult for CNNs to accurately segment the cell boundaries.In this study,we propose a Stacked Channel Learning Network(SCLN),a two-phase CNN-based method for IMC cell segmentation.SCLN uses a channel embedding approach with two training phases:Phase I generates imaging masks for cellular structures using a pre-trained Res-U-Net model,while Phase II refines the segmentation by incorporating these masks as an additional channel alongside the existing biomarker channels.In addition,SCLN preserves the image representations derived independently from each channel,enabling more detailed channel-level feature analysis.The proposed method was evaluated on the widely used IMC breast cancer METABRIC dataset.The experimental results show that our SCLN achieved a Dice coefficient score of 91.45%,which outperformed the existing segmentation methods by~10%,especially for the challenging studies e.g.,cluttered cells and cells with inhomogeneous textures.Our codes can be found at https://github.com/kongn et-djd/SCLN.
