Objective:This article describes a new method(VS-FPM)for analysis of unstained tissues based on the application of supervised machine learning to generate brightfield hematoxylin and eosin(H&E)images from phase im...Objective:This article describes a new method(VS-FPM)for analysis of unstained tissues based on the application of supervised machine learning to generate brightfield hematoxylin and eosin(H&E)images from phase images recovered using Fourier ptychographic microscopy(FPM).Impact Statement:VS-FPM has several advantages for label-free digital pathology.Capture of complex image information simplifies model training and allows post-capture refocusing.FPM images combine high resolution with a large field of view,and the hardware is low-cost and compatible with many existing brightfield microscope systems.Introduction:By generating realistic histologically stained images from label-free image data,virtual staining(VS)methods have the potential to streamline clinical workflows,improve image consistency,and enable new ways of visualizing and analyzing histological tissues.Methods:We trained a conditional generative adversarial network to translate high-resolution FPM images of unstained tissues to brightfield H&E images and assessed the method using diagnosis of colonic polyps as a test case.Results:We found no statistically significant difference between the spatial resolution of FPM images captured at 4×magnification and images from a pathology slide scanner at 20×magnification.Visual assessment and image similarity metrics showed that VS-FPM images of unstained tissues closely resemble images of chemically H&Estained tissues.However,the spatial resolution of virtual H&E images was approximately 20%lower than equivalent images of chemically stained tissues.Using VS-FPM,board-certified pathologists were able to accurately distinguish normal from dysplastic tissues and derive correct pathological diagnoses.Conclusion:VS-FPM is a reliable,accessible VS method that also overcomes many other limitations inherent to histopathology microscopy.展开更多
Background:Family studies support a genetic predisposition to inflammatory bowel diseases(IBD),but known genetic variants only partially explain the disease heritability.Families withmultiple affected individuals pote...Background:Family studies support a genetic predisposition to inflammatory bowel diseases(IBD),but known genetic variants only partially explain the disease heritability.Families withmultiple affected individuals potentially harbour rare and highimpact causal variants.Long regions of homozygosity due to recent inbreedingmay increase the risk of individuals bearing homozygous loss-of-function variants.This study aimed to identify rare and homozygous genetic variants contributing to IBD.Methods:Four families with known consanguinity and multiple cases of IBD were recruited.In a family-specific analysis,we utilised homozygosity mapping complemented by whole-exome sequencing.Results:We detected a single region of homozygosity shared by Crohn’s disease cases from a family of Druze ancestry,spanning 2.6Mb containing the NOD2 gene.Whole-exome sequencing did not identify any potentially damaging variants within the region,suggesting that non-coding variation may be involved.In addition,affected individuals in the families harboured several rare and potentially damaging homozygous variants in genes with a role in autophagy and innate immunity including LRRK1,WHAMM,DENND3,and C5.Conclusion:This study examined the potential contribution of rare,high-impact homozygous variants in consanguineous families with IBD.While the analysis was not designed to achieve statistical significance,our findings highlight genes or loci that warrant further research.Non-coding variants affecting NOD2 may be of importance in Druze patients with Crohn’s disease.展开更多
基金funded by a proof-of-concept award from Wellcome/EPSRC Centre for Interventional and Surgical Science(award 203145Z/16/Z)the NIHR UCLH Biomedical Research Centre(award 187809).A.P.L.was funded by The Pathological Society of Great Britain and Ireland.
文摘Objective:This article describes a new method(VS-FPM)for analysis of unstained tissues based on the application of supervised machine learning to generate brightfield hematoxylin and eosin(H&E)images from phase images recovered using Fourier ptychographic microscopy(FPM).Impact Statement:VS-FPM has several advantages for label-free digital pathology.Capture of complex image information simplifies model training and allows post-capture refocusing.FPM images combine high resolution with a large field of view,and the hardware is low-cost and compatible with many existing brightfield microscope systems.Introduction:By generating realistic histologically stained images from label-free image data,virtual staining(VS)methods have the potential to streamline clinical workflows,improve image consistency,and enable new ways of visualizing and analyzing histological tissues.Methods:We trained a conditional generative adversarial network to translate high-resolution FPM images of unstained tissues to brightfield H&E images and assessed the method using diagnosis of colonic polyps as a test case.Results:We found no statistically significant difference between the spatial resolution of FPM images captured at 4×magnification and images from a pathology slide scanner at 20×magnification.Visual assessment and image similarity metrics showed that VS-FPM images of unstained tissues closely resemble images of chemically H&Estained tissues.However,the spatial resolution of virtual H&E images was approximately 20%lower than equivalent images of chemically stained tissues.Using VS-FPM,board-certified pathologists were able to accurately distinguish normal from dysplastic tissues and derive correct pathological diagnoses.Conclusion:VS-FPM is a reliable,accessible VS method that also overcomes many other limitations inherent to histopathology microscopy.
基金supported by the Charles Wolfson Charitable Trust and the Medical Research Council.
文摘Background:Family studies support a genetic predisposition to inflammatory bowel diseases(IBD),but known genetic variants only partially explain the disease heritability.Families withmultiple affected individuals potentially harbour rare and highimpact causal variants.Long regions of homozygosity due to recent inbreedingmay increase the risk of individuals bearing homozygous loss-of-function variants.This study aimed to identify rare and homozygous genetic variants contributing to IBD.Methods:Four families with known consanguinity and multiple cases of IBD were recruited.In a family-specific analysis,we utilised homozygosity mapping complemented by whole-exome sequencing.Results:We detected a single region of homozygosity shared by Crohn’s disease cases from a family of Druze ancestry,spanning 2.6Mb containing the NOD2 gene.Whole-exome sequencing did not identify any potentially damaging variants within the region,suggesting that non-coding variation may be involved.In addition,affected individuals in the families harboured several rare and potentially damaging homozygous variants in genes with a role in autophagy and innate immunity including LRRK1,WHAMM,DENND3,and C5.Conclusion:This study examined the potential contribution of rare,high-impact homozygous variants in consanguineous families with IBD.While the analysis was not designed to achieve statistical significance,our findings highlight genes or loci that warrant further research.Non-coding variants affecting NOD2 may be of importance in Druze patients with Crohn’s disease.
