Quantitative assessment of inflammatory infiltrates in kidney transplant biopsies using multiplex tyramide signal amplification and deep learning
Delayed graft function (DGF) is a strong risk factor for development of interstitial fibrosis and tubular atrophy (IFTA) in kidney transplants. Quantitative assessment of inflammatory infiltrates in kidney biopsies of DGF patients can reveal predictive markers for IFTA development. In this study, we...
Saved in:
Published in | Laboratory investigation Vol. 101; no. 8; p. 970 |
---|---|
Main Authors | , , , , , , , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
United States
01.08.2021
|
Online Access | Get full text |
Cover
Loading…
Abstract | Delayed graft function (DGF) is a strong risk factor for development of interstitial fibrosis and tubular atrophy (IFTA) in kidney transplants. Quantitative assessment of inflammatory infiltrates in kidney biopsies of DGF patients can reveal predictive markers for IFTA development. In this study, we combined multiplex tyramide signal amplification (mTSA) and convolutional neural networks (CNNs) to assess the inflammatory microenvironment in kidney biopsies of DGF patients (n = 22) taken at 6 weeks post-transplantation. Patients were stratified for IFTA development (<10% versus ≥10%) from 6 weeks to 6 months post-transplantation, based on histopathological assessment by three kidney pathologists. One mTSA panel was developed for visualization of capillaries, T- and B-lymphocytes and macrophages and a second mTSA panel for T-helper cell and macrophage subsets. The slides were multi spectrally imaged and custom-made python scripts enabled conversion to artificial brightfield whole-slide images (WSI). We used an existing CNN for the detection of lymphocytes with cytoplasmatic staining patterns in immunohistochemistry and developed two new CNNs for the detection of macrophages and nuclear-stained lymphocytes. F1-scores were 0.77 (nuclear-stained lymphocytes), 0.81 (cytoplasmatic-stained lymphocytes), and 0.82 (macrophages) on a test set of artificial brightfield WSI. The CNNs were used to detect inflammatory cells, after which we assessed the peritubular capillary extent, cell density, cell ratios, and cell distance in the two patient groups. In this cohort, distance of macrophages to other immune cells and peritubular capillary extent did not vary significantly at 6 weeks post-transplantation between patient groups. CD163
cell density was higher in patients with ≥10% IFTA development 6 months post-transplantation (p < 0.05). CD3
CD8
/CD3
CD8
ratios were higher in patients with <10% IFTA development (p < 0.05). We observed a high correlation between CD163
and CD4
GATA3
cell density (R = 0.74, p < 0.001). Our study demonstrates that CNNs can be used to leverage reliable, quantitative results from mTSA-stained, multi spectrally imaged slides of kidney transplant biopsies. This study describes a methodology to assess the microenvironment in sparse tissue samples. Deep learning, multiplex immunohistochemistry, and mathematical image processing techniques were incorporated to quantify lymphocytes, macrophages, and capillaries in kidney transplant biopsies of delayed graft function patients. The quantitative results were used to assess correlations with development of interstitial fibrosis and tubular atrophy. |
---|---|
AbstractList | Delayed graft function (DGF) is a strong risk factor for development of interstitial fibrosis and tubular atrophy (IFTA) in kidney transplants. Quantitative assessment of inflammatory infiltrates in kidney biopsies of DGF patients can reveal predictive markers for IFTA development. In this study, we combined multiplex tyramide signal amplification (mTSA) and convolutional neural networks (CNNs) to assess the inflammatory microenvironment in kidney biopsies of DGF patients (n = 22) taken at 6 weeks post-transplantation. Patients were stratified for IFTA development (<10% versus ≥10%) from 6 weeks to 6 months post-transplantation, based on histopathological assessment by three kidney pathologists. One mTSA panel was developed for visualization of capillaries, T- and B-lymphocytes and macrophages and a second mTSA panel for T-helper cell and macrophage subsets. The slides were multi spectrally imaged and custom-made python scripts enabled conversion to artificial brightfield whole-slide images (WSI). We used an existing CNN for the detection of lymphocytes with cytoplasmatic staining patterns in immunohistochemistry and developed two new CNNs for the detection of macrophages and nuclear-stained lymphocytes. F1-scores were 0.77 (nuclear-stained lymphocytes), 0.81 (cytoplasmatic-stained lymphocytes), and 0.82 (macrophages) on a test set of artificial brightfield WSI. The CNNs were used to detect inflammatory cells, after which we assessed the peritubular capillary extent, cell density, cell ratios, and cell distance in the two patient groups. In this cohort, distance of macrophages to other immune cells and peritubular capillary extent did not vary significantly at 6 weeks post-transplantation between patient groups. CD163
cell density was higher in patients with ≥10% IFTA development 6 months post-transplantation (p < 0.05). CD3
CD8
/CD3
CD8
ratios were higher in patients with <10% IFTA development (p < 0.05). We observed a high correlation between CD163
and CD4
GATA3
cell density (R = 0.74, p < 0.001). Our study demonstrates that CNNs can be used to leverage reliable, quantitative results from mTSA-stained, multi spectrally imaged slides of kidney transplant biopsies. This study describes a methodology to assess the microenvironment in sparse tissue samples. Deep learning, multiplex immunohistochemistry, and mathematical image processing techniques were incorporated to quantify lymphocytes, macrophages, and capillaries in kidney transplant biopsies of delayed graft function patients. The quantitative results were used to assess correlations with development of interstitial fibrosis and tubular atrophy. |
Author | Hermsen, Meyke Volk, Valery Schaadt, Nadine S Steenbergen, Eric J Kers, Jesper Gwinner, Wilfried Hilbrands, Luuk B van der Laak, Jeroen A W M Swiderska-Chadaj, Zaneta Smeets, Bart Linmans, Jasper Feuerhake, Friedrich Geijs, Daan J Bräsen, Jan Hinrich Schmitz, Jessica |
Author_xml | – sequence: 1 givenname: Meyke surname: Hermsen fullname: Hermsen, Meyke organization: Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands – sequence: 2 givenname: Valery surname: Volk fullname: Volk, Valery organization: Institute for Pathology, Hannover Medical School, Hannover, Germany – sequence: 3 givenname: Jan Hinrich surname: Bräsen fullname: Bräsen, Jan Hinrich organization: Institute for Pathology, Hannover Medical School, Hannover, Germany – sequence: 4 givenname: Daan J surname: Geijs fullname: Geijs, Daan J organization: Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands – sequence: 5 givenname: Wilfried surname: Gwinner fullname: Gwinner, Wilfried organization: Department of Nephrology, Hannover Medical School, Hannover, Germany – sequence: 6 givenname: Jesper surname: Kers fullname: Kers, Jesper organization: Department of Pathology, Amsterdam University Medical Centers, Amsterdam, The Netherlands; Department of Pathology, Leiden University Medical Center, Leiden, The Netherlands; Center for Analytical Sciences Amsterdam (CASA), Van 't Hoff Institute for Molecular Sciences (HIMS), University of Amsterdam, Amsterdam, The Netherlands – sequence: 7 givenname: Jasper surname: Linmans fullname: Linmans, Jasper organization: Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands – sequence: 8 givenname: Nadine S surname: Schaadt fullname: Schaadt, Nadine S organization: Institute of Diagnostic and Interventional Neuroradiology, Hannover Medical School, Hannover, Germany – sequence: 9 givenname: Jessica surname: Schmitz fullname: Schmitz, Jessica organization: Institute for Pathology, Hannover Medical School, Hannover, Germany – sequence: 10 givenname: Eric J surname: Steenbergen fullname: Steenbergen, Eric J organization: Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands – sequence: 11 givenname: Zaneta surname: Swiderska-Chadaj fullname: Swiderska-Chadaj, Zaneta organization: Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands; Faculty of Electrical Engineering, Warsaw University of Technology, Warsaw, Poland – sequence: 12 givenname: Bart surname: Smeets fullname: Smeets, Bart organization: Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands – sequence: 13 givenname: Luuk B surname: Hilbrands fullname: Hilbrands, Luuk B organization: Department of Nephrology, Radboud University Medical Center, Nijmegen, The Netherlands – sequence: 14 givenname: Friedrich surname: Feuerhake fullname: Feuerhake, Friedrich organization: Institute for Pathology, Hannover Medical School, Hannover, Germany; Institute for Neuropathology, University Clinic Freiburg, Freiburg, Germany – sequence: 15 givenname: Jeroen A W M surname: van der Laak fullname: van der Laak, Jeroen A W M email: jeroen.vanderlaak@radboudumc.nl organization: Department of Pathology, Radboud University Medical Center, Nijmegen, The Netherlands; Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden. Electronic address: jeroen.vanderlaak@radboudumc.nl |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/36775372$$D View this record in MEDLINE/PubMed |
BookMark | eNqFT0tOAzEMjRBV_1dAvkCllHQ6B6hAbJHYVy7xVIbEieIMYo7BjQkSrFn5Pft95JW5lSR0Y5b7ztmddbZfmJXqm7X7w-HYzc3CHfu-c_390nw9jyiVK1b-IEBVUo0kFdIALEPAGLGmMv0QDrVgJW0Y3tkLTdAWojm0CLhwysrtOirLFeIYKudAn1CngpE9gfJVMADGHHjg11aZBFA8eKIMgbBIc27MbMCgtP2da3P3-PByetrl8RLJn3PhiGU6__3g_hV8A2HYWMg |
ContentType | Journal Article |
Copyright | Copyright © 2021 The Authors. Published by Elsevier Inc. All rights reserved. |
Copyright_xml | – notice: Copyright © 2021 The Authors. Published by Elsevier Inc. All rights reserved. |
DBID | NPM |
DatabaseName | PubMed |
DatabaseTitle | PubMed |
DatabaseTitleList | PubMed |
Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine |
EISSN | 1530-0307 |
ExternalDocumentID | 36775372 |
Genre | Journal Article |
GroupedDBID | --- -Q- -~X .55 .GJ 0R~ 0SF 1KJ 29L 2WC 36B 39C 3V. 4.4 53G 5GY 5RE 70F 7X7 88E 8AO 8C1 8FI 8FJ 8R4 8R5 8WZ A6W AALRI AANZL AAWBL AAXUO AAZLF ABAWZ ABCQX ABJNI ABLJU ABUWG ACGFO ACGFS ACIWK ACKTT ACPRK ACRQY ACZOJ ADBBV ADHDB ADVLN AEJRE AENEX AEXYK AFFNX AFJKZ AFKRA AFOSN AFRAH AFSHS AGAYW AGEZK AGHAI AHMBA AHSBF AILAN AITUG AJRNO AKRWK ALFFA ALIPV ALMA_UNASSIGNED_HOLDINGS AMRAJ AMYLF ASPBG AVWKF AXYYD AZFZN BAWUL BBNVY BENPR BHPHI BKKNO BPHCQ BVXVI CAG CCPQU COF CS3 DIK DNIVK DU5 E3Z EBS EE. EIOEI EJD EMB F5P FDB FDQFY FEDTE FERAY FIZPM FSGXE FYUFA GX1 HCIFZ HMCUK HVGLF HZ~ IH2 IWAJR JSO KQ8 M1P M7P MVM NAO NPM NQJWS O9- OK1 P2P P6G PQQKQ PROAC PSQYO Q2X RNS RNT RNTTT ROL S10 SNX SNYQT SOHCF SRMVM SV3 SWTZT TAOOD TBHMF TDRGL TR2 TSG TWZ UKHRP X7M Y6R YFH YKV YOC YQI YQT ZGI ZXP |
ID | FETCH-pubmed_primary_367753723 |
IngestDate | Sat Sep 28 08:12:06 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 8 |
Language | English |
License | Copyright © 2021 The Authors. Published by Elsevier Inc. All rights reserved. |
LinkModel | OpenURL |
MergedId | FETCHMERGED-pubmed_primary_367753723 |
PMID | 36775372 |
ParticipantIDs | pubmed_primary_36775372 |
PublicationCentury | 2000 |
PublicationDate | 2021-Aug |
PublicationDateYYYYMMDD | 2021-08-01 |
PublicationDate_xml | – month: 08 year: 2021 text: 2021-Aug |
PublicationDecade | 2020 |
PublicationPlace | United States |
PublicationPlace_xml | – name: United States |
PublicationTitle | Laboratory investigation |
PublicationTitleAlternate | Lab Invest |
PublicationYear | 2021 |
SSID | ssj0014465 |
Score | 4.393669 |
Snippet | Delayed graft function (DGF) is a strong risk factor for development of interstitial fibrosis and tubular atrophy (IFTA) in kidney transplants. Quantitative... |
SourceID | pubmed |
SourceType | Index Database |
StartPage | 970 |
Title | Quantitative assessment of inflammatory infiltrates in kidney transplant biopsies using multiplex tyramide signal amplification and deep learning |
URI | https://www.ncbi.nlm.nih.gov/pubmed/36775372 |
Volume | 101 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8JAEN4AJoSL8f0mc_BGauiDR49i0IaIUYOEG2np1lSgJVgS8V_4j53d7baFSKJemrIt2zTf19mdnZlvCbl0TXOkNRxPMauapxgeYtG0bVPRmzZ-WXUXJymsGrn7ULdejM6gNsjlFtnqksi5Gn3-WFfyH1SxDXFlVbJ_QDbpFBvwHPHFIyKMx19h_LSwA14kxtJ_7ERjU8hAeIj1VMTQ8Yc_4TK0PPt17LsBmoKI65pPsIuK44ezd_SZKwu-dCCzDD8q0XJuT32XVlieB5MVYAnoXrzOxwMPLqUzuffEa3aqey_oJZ6fiHmkUX8Lx4R4-adLl-OEYP1wwi10H4euNEe5JUL6RvyPDpolyw_QiCfL2XfUfxM-gc1KsrLLGZqaJNPhaCRNcFVhpmfFRse3CDI2MxbXFPuOZNCeTTncer2BrpjYF2hNUlteypO8rtYKZKvVfnh8ToJPTEOuRIryrjWHg088ejtkO_YY4FrAv0tyNNgjxW6cE7FPvrIsgJQFEHqQZQFkWIDnIFgAKQtAsgA4CyBhAUgWgGABrLAAkAXAWACSBQekfNvu3ViKeKHhTCiaDOWr6oekEIQBPSbAVJls1a3WTd01HNp0XE2nmqpiG_rwDeeEHG3o5HTjlTNSSiE_J4VovqAXOKeLnHKMwTfVNGFB |
link.rule.ids | 315,786,790 |
linkProvider | ProQuest |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Quantitative+assessment+of+inflammatory+infiltrates+in+kidney+transplant+biopsies+using+multiplex+tyramide+signal+amplification+and+deep+learning&rft.jtitle=Laboratory+investigation&rft.au=Hermsen%2C+Meyke&rft.au=Volk%2C+Valery&rft.au=Br%C3%A4sen%2C+Jan+Hinrich&rft.au=Geijs%2C+Daan+J&rft.date=2021-08-01&rft.eissn=1530-0307&rft.volume=101&rft.issue=8&rft.spage=970&rft_id=info%3Apmid%2F36775372&rft.externalDocID=36775372 |