1
|
Glass M, Ji Z, Davis R, Pavlisko EN, DiBernardo L, Carney J, Fishbein G, Luthringer D, Miller D, Mitchell R, Larsen B, Butt Y, Bois M, Maleszewski J, Halushka M, Seidman M, Lin CY, Buja M, Stone J, Dov D, Carin L, Glass C. A machine learning algorithm improves the diagnostic accuracy of the histologic component of antibody mediated rejection (AMR-H) in cardiac transplant endomyocardial biopsies. Cardiovasc Pathol 2024; 72:107646. [PMID: 38677634 DOI: 10.1016/j.carpath.2024.107646] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/03/2023] [Revised: 04/15/2024] [Accepted: 04/16/2024] [Indexed: 04/29/2024] Open
Abstract
BACKGROUND Pathologic antibody mediated rejection (pAMR) remains a major driver of graft failure in cardiac transplant patients. The endomyocardial biopsy remains the primary diagnostic tool but presents with challenges, particularly in distinguishing the histologic component (pAMR-H) defined by 1) intravascular macrophage accumulation in capillaries and 2) activated endothelial cells that expand the cytoplasm to narrow or occlude the vascular lumen. Frequently, pAMR-H is difficult to distinguish from acute cellular rejection (ACR) and healing injury. With the advent of digital slide scanning and advances in machine deep learning, artificial intelligence technology is widely under investigation in the areas of oncologic pathology, but in its infancy in transplant pathology. For the first time, we determined if a machine learning algorithm could distinguish pAMR-H from normal myocardium, healing injury and ACR. MATERIALS AND METHODS A total of 4,212 annotations (1,053 regions of normal, 1,053 pAMR-H, 1,053 healing injury and 1,053 ACR) were completed from 300 hematoxylin and eosin slides scanned using a Leica Aperio GT450 digital whole slide scanner at 40X magnification. All regions of pAMR-H were annotated from patients confirmed with a previous diagnosis of pAMR2 (>50% positive C4d immunofluorescence and/or >10% CD68 positive intravascular macrophages). Annotations were imported into a Python 3.7 development environment using the OpenSlide™ package and a convolutional neural network approach utilizing transfer learning was performed. RESULTS The machine learning algorithm showed 98% overall validation accuracy and pAMR-H was correctly distinguished from specific categories with the following accuracies: normal myocardium (99.2%), healing injury (99.5%) and ACR (99.5%). CONCLUSION Our novel deep learning algorithm can reach acceptable, and possibly surpass, performance of current diagnostic standards of identifying pAMR-H. Such a tool may serve as an adjunct diagnostic aid for improving the pathologist's accuracy and reproducibility, especially in difficult cases with high inter-observer variability. This is one of the first studies that provides evidence that an artificial intelligence machine learning algorithm can be trained and validated to diagnose pAMR-H in cardiac transplant patients. Ongoing studies include multi-institutional verification testing to ensure generalizability.
Collapse
Affiliation(s)
- Matthew Glass
- Duke Division of Artificial Intelligence and Computational Pathology, Duke University Medical Center, Durham NC, USA; Department of Anesthesiology, Duke University Medical Center, Durham NC, USA
| | - Zhicheng Ji
- Department of Biostatistics and Bioinformatics, Duke School of Medicine, Durham NC, USA
| | - Richard Davis
- Department of Pathology, Duke University Medical Center, Durham NC, USA
| | - Elizabeth N Pavlisko
- Duke Division of Artificial Intelligence and Computational Pathology, Duke University Medical Center, Durham NC, USA; Department of Pathology, Duke University Medical Center, Durham NC, USA
| | - Louis DiBernardo
- Department of Pathology, Duke University Medical Center, Durham NC, USA
| | - John Carney
- Department of Pathology, Duke University Medical Center, Durham NC, USA
| | - Gregory Fishbein
- Department of Pathology, University of California at Los Angeles, Los Angeles CA, USA
| | - Daniel Luthringer
- Department of Pathology and Laboratory Medicine, Cedars-Sinai Medical Center, Los Angeles CA, USA
| | - Dylan Miller
- Department of Pathology, Intermountain Healthcare, Salt Lake City UT, USA
| | - Richard Mitchell
- Department of Pathology, Brigham and Women's Hospital, Boston MA, USA
| | - Brandon Larsen
- Department of Pathology and Laboratory Medicine, Mayo Clinic, Phoenix AZ, USA
| | - Yasmeen Butt
- Department of Pathology and Laboratory Medicine, Mayo Clinic, Phoenix AZ, USA
| | - Melanie Bois
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester MN, USA
| | - Joseph Maleszewski
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester MN, USA
| | - Marc Halushka
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore MD, USA
| | - Michael Seidman
- Department of Pathology, University Health Network, Toronto ON, CA
| | - Chieh-Yu Lin
- Department of Pathology and Immunology, Washington University, St. Louis MO, USA
| | - Maximilian Buja
- Department of Pathology and Laboratory Medicine, The University of Texas Health Science Center at Houston, Houston TX, USA
| | - James Stone
- Department of Pathology, Massachusetts General Hospital, Boston MA, USA
| | - David Dov
- Duke Division of Artificial Intelligence and Computational Pathology, Duke University Medical Center, Durham NC, USA; Pratt School of Engineering, Department of Electrical and Computer Engineering, Duke University, Durham NC, USA
| | - Lawrence Carin
- Duke Division of Artificial Intelligence and Computational Pathology, Duke University Medical Center, Durham NC, USA; Pratt School of Engineering, Department of Electrical and Computer Engineering, Duke University, Durham NC, USA
| | - Carolyn Glass
- Duke Division of Artificial Intelligence and Computational Pathology, Duke University Medical Center, Durham NC, USA; Department of Pathology, Duke University Medical Center, Durham NC, USA.
| |
Collapse
|
2
|
Liu W, Kang ZY, Wang ZL, Li DH. Antibody-mediated rejection owing to donor-specific HLA-DQA1 antibodies after renal transplantation: A case report. Transpl Immunol 2022; 73:101607. [PMID: 35477043 DOI: 10.1016/j.trim.2022.101607] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2022] [Revised: 04/18/2022] [Accepted: 04/21/2022] [Indexed: 10/18/2022]
Abstract
BACKGROUND Donor-specific HLA antibodies are important risk factors in antibody-mediated rejection and graft loss after renal transplantation and are associated with higher rejection rates and lower graft survival. Most de novo donor specific antibodies (dnDSA) after renal transplantation are directed toward donor HLA-DQ antigens. An HLA-DQ antigen is a heterodimer consisting of an alpha and beta chain. Traditionally, HLA-DQA1 typing has not been part of pretransplant evaluation. Therefore, DQ alpha proteins are not usually considered in the interpretation of HLA-DQ antibody reactions. METHODS The renal transplant recipient had a 0% panel reactive antibody pretransplant. Two years after transplantation, he developed symptoms of abdominal distension and bilateral lower extremity edema. Histopathological findings on renal puncture biopsy showed a combination of T-cell-mediated acute rejection type IIA and antibody-mediated rejection with a trend toward chronicity in the transplanted kidney. DSAs were investigated by HLA-I (HLA-A/B) and HLA-II (HLA-DRB1/DQA1/DQB1) single antigen bead (SAB) assay. HLA typing was performed to explain the antibody reactivity patterns by PCR-SSO and Sequencing-based typing (SBT). HLAMatchmaker analysis was performed to identify eplets that explain antibody reactivity patterns. RESULTS HLA-II SAB analysis of the patient's serum at the time of rejection showed positive reactions with all DQB1*03:03-carrying beads with high mean fluorescence intensity (MFI). However, DQB1*03:03 was not a dnDSA antigen. High-resolution HLA typing revealed that HLA-DQA1*05:01 and DQA1*03:02 were mismatched donor antigens. HLA Matchmaker analysis demonstrated reactivity toward 130R and 116 V eplet on DQA1 and DQB1. CONCLUSIONS Antibodies specific to DQα chains after renal transplantation were highlighted.
Collapse
Affiliation(s)
- Wei Liu
- Department of Blood Transfusion, Tianjin First Central Hospital, School of Medicine, Nankai University, Tianjin, China
| | - Zhong-Yu Kang
- Department of Blood Transfusion, Tianjin First Central Hospital, School of Medicine, Nankai University, Tianjin, China
| | - Zheng-Lu Wang
- Department of Pathology, Tianjin First Central Hospital, School of Medicine, Nankai University, Tianjin, China
| | - Dai-Hong Li
- Department of Blood Transfusion, Tianjin First Central Hospital, School of Medicine, Nankai University, Tianjin, China.
| |
Collapse
|
3
|
Non-HLA Antibodies in Hand Transplant Recipients Are Connected to Multiple Acute Rejection Episodes and Endothelial Activation. J Clin Med 2022; 11:jcm11030833. [PMID: 35160284 PMCID: PMC8837026 DOI: 10.3390/jcm11030833] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/15/2022] [Revised: 02/01/2022] [Accepted: 02/02/2022] [Indexed: 02/01/2023] Open
Abstract
The role of anti-HLA antibodies in transplant rejection is well-known but the injury associated with non-HLA antibodies is now widely discussed. The aim of our study was to investigate a role of non-HLA antibodies in hand allografts rejection. The study was performed on six patients after hand transplantation. The control group consisted of: 12 kidney transplant recipients and 12 healthy volunteers. The following non-HLA antibodies were tested: antibody against angiotensin II type 1 receptor (AT1R-Ab), antibody against endothelin-1 type-A-receptor (ETAR-Ab), antibody against protease-activated receptor 1 (PAR-1-Ab) and anti-VEGF-A antibody (VEGF-A-Ab). Chosen proinflammatory cytokines (Il-1, IL-6, IFNγ) were used to evaluate the post-transplant humoral response. Laboratory markers of endothelial activation (VEGF, sICAM, vWF) were used to assess potential vasculopathy. The patient with the highest number of acute rejections had both positive non-HLA antibodies: AT1R-Ab and ETAR-Ab. The same patient had the highest VEGF-A-Ab and very high PAR1-Ab. All patients after hand transplantation had high levels of laboratory markers of endothelial activation. The existence of non-HLA antibodies together with multiple acute rejections observed in patient after hand transplantation should stimulate to look for potential role of non-HLA antibodies in humoral injury in vascular composite allotransplantation.
Collapse
|
4
|
Xu Q, McAlister VC, House AA, Molinari M, Leckie S, Zeevi A. Autoantibodies to LG3 are associated with poor long-term survival after liver retransplantation. Clin Transplant 2021; 35:e14318. [PMID: 33871888 DOI: 10.1111/ctr.14318] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2021] [Revised: 03/12/2021] [Accepted: 04/02/2021] [Indexed: 12/21/2022]
Abstract
Autoantibodies are detrimental to the survival of organ transplantation. We demonstrated that Angiotensin II Type I Receptor agonistic autoantibodies (AT1R-AA) were associated with poor outcomes after liver retransplantation. To examine the effect of other autoantibodies, we studied a retrospective cohort of 93 patients who received a second liver transplant. Pre-retransplant sera were tested with Luminex-based solid-phase assays. Among 33 tested autoantibodies, 15 were significantly higher in 48 patients who lost their regrafts than 45 patients whose regrafts were still functioning. Specifically, patients with autoantibodies to the C-terminal laminin-like globular domain of Perlecan (LG3) experienced significantly worse regraft survival (p = .002) than those with negative LG3 autoantibodies (LG3-A). In multivariate analysis, LG3-A (HR = 2.35 [1.11-4.98], p = .027) and AT1R-AA (HR = 2.09 [1.07-4.10], p = .032) remained significant predictors of regraft loss after adjusting for recipient age and sex. There were synergistic deleterious effects on regraft survival in patients who were double-positive for LG3-A and donor-specific antibody (DSA) (HR = 5.26 [2.15-12.88], p = .001), or LG3-A and AT1R-AA (HR = 3.23 [1.37-7.66], p = .008). All six double-positive patients lost their liver regrafts. In conclusion, LG3-A is associated with inferior long-term outcomes of a second liver transplant. Screening anti-HLA antibodies and autoantibodies such as LG3-A/AT1R-AA identifies patients with a higher risk for liver transplantation.
Collapse
Affiliation(s)
- Qingyong Xu
- Department of Pathology, University of Pittsburgh, Pittsburgh, PA, USA
| | - Vivian C McAlister
- Department of Surgery, University of Western Ontario, London, ON, Canada
| | - Andrew A House
- Department of Medicine, University of Western Ontario, London, ON, Canada
| | - Michele Molinari
- Department of Surgery, University of Pittsburgh, Pittsburgh, PA, USA
| | - Steve Leckie
- Department of Pathology and Lab Medicine, London Health Science Center, London, ON, Canada
| | - Adriana Zeevi
- Department of Pathology, University of Pittsburgh, Pittsburgh, PA, USA
| |
Collapse
|