1
|
Eccher A, L'Imperio V, Pantanowitz L, Cazzaniga G, Del Carro F, Marletta S, Gambaro G, Barreca A, Becker JU, Gobbo S, Della Mea V, Alberici F, Pagni F, Dei Tos AP. Galileo-an Artificial Intelligence tool for evaluating pre-implantation kidney biopsies. J Nephrol 2024:10.1007/s40620-024-02094-4. [PMID: 39356416 DOI: 10.1007/s40620-024-02094-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2024] [Accepted: 08/25/2024] [Indexed: 10/03/2024]
Abstract
BACKGROUND Pre-transplant procurement biopsy interpretation is challenging, also because of the low number of renal pathology experts. Artificial intelligence (AI) can assist by aiding pathologists with kidney donor biopsy assessment. Herein we present the "Galileo" AI tool, designed specifically to assist the on-call pathologist with interpreting pre-implantation kidney biopsies. METHODS A multicenter cohort of whole slide images acquired from core-needle and wedge biopsies of the kidney was collected. A deep learning algorithm was trained to detect the main findings evaluated in the pre-implantation setting (normal glomeruli, globally sclerosed glomeruli, ischemic glomeruli, arterioles and arteries). The model obtained on the Aiforia Create platform was validated on an external dataset by three independent pathologists to evaluate the performance of the algorithm. RESULTS Galileo demonstrated a precision, sensitivity, F1 score and total area error of 81.96%, 94.39%, 87.74%, 2.81% and 74.05%, 71.03%, 72.5%, 2% in the training and validation sets, respectively. Galileo was significantly faster than pathologists, requiring 2 min overall in the validation phase (vs 25, 22 and 31 min by 3 separate human readers, p < 0.001). Galileo-assisted detection of renal structures and quantitative information was directly integrated in the final report. CONCLUSIONS The Galileo AI-assisted tool shows promise in speeding up pre-implantation kidney biopsy interpretation, as well as in reducing inter-observer variability. This tool may represent a starting point for further improvements based on hard endpoints such as graft survival.
Collapse
Affiliation(s)
- Albino Eccher
- Department of Medical and Surgical Sciences for Children and Adults, University of Modena and Reggio Emilia, University Hospital of Modena, Modena, Italy
| | - Vincenzo L'Imperio
- Department of Medicine and Surgery, Pathology, IRCCS Fondazione San Gerardo dei Tintori, University of Milano-Bicocca, Monza, Italy.
| | - Liron Pantanowitz
- Department of Pathology, University of Pittsburgh, Pittsburgh, PA, USA
| | - Giorgio Cazzaniga
- Department of Medicine and Surgery, Pathology, IRCCS Fondazione San Gerardo dei Tintori, University of Milano-Bicocca, Monza, Italy
| | - Fabio Del Carro
- Department of Medicine and Surgery, Pathology, IRCCS Fondazione San Gerardo dei Tintori, University of Milano-Bicocca, Monza, Italy
| | | | - Giovanni Gambaro
- Division of Nephrology, Department of Medicine, University of Verona, Verona, Italy
| | - Antonella Barreca
- Pathology Unit, Città della Salute e della Scienza di Torino University Hospital, Turin, Italy
| | - Jan Ulrich Becker
- Institute of Pathology, University Hospital of Cologne, Cologne, Germany
| | - Stefano Gobbo
- Department of Translational Medicine, University of Ferrara, Ferrara, Italy
| | - Vincenzo Della Mea
- Department of Mathematics, Computer Science and Physics, University of Udine, Udine, Italy
| | - Federico Alberici
- Division of Nephrology and Dialysis, Department of Medical and Surgical Specialties, Radiological Sciences, and Public Health, University of Brescia and ASST-Spedali Civili of Brescia, Brescia, Italy
| | - Fabio Pagni
- Department of Medicine and Surgery, Pathology, IRCCS Fondazione San Gerardo dei Tintori, University of Milano-Bicocca, Monza, Italy
| | - Angelo Paolo Dei Tos
- Surgical Pathology and Cytopathology Unit, Department of Medicine-DIMED, University of Padua School of Medicine, Padua, Italy
| |
Collapse
|
2
|
Zaza G, Cucchiari D, Becker JU, de Vries APJ, Eccher A, Florquin S, Kers J, Rabant M, Rossini M, Pengel L, Marson L, Furian L. European Society for Organ Transplantation (ESOT)-TLJ 3.0 Consensus on Histopathological Analysis of Pre-Implantation Donor Kidney Biopsy: Redefining the Role in the Process of Graft Assessment. Transpl Int 2023; 36:11410. [PMID: 37470063 PMCID: PMC10353313 DOI: 10.3389/ti.2023.11410] [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: 03/28/2023] [Accepted: 05/31/2023] [Indexed: 07/21/2023]
Abstract
The ESOT TLJ 3.0. consensus conference brought together leading experts in transplantation to develop evidence-based guidance on the standardization and clinical utility of pre-implantation kidney biopsy in the assessment of grafts from Expanded Criteria Donors (ECD). Seven themes were selected and underwent in-depth analysis after formulation of PICO (patient/population, intervention, comparison, outcomes) questions. After literature search, the statements for each key question were produced, rated according the GRADE approach [Quality of evidence: High (A), Moderate (B), Low (C); Strength of Recommendation: Strong (1), Weak (2)]. The statements were subsequently presented in-person at the Prague kick-off meeting, discussed and voted. After two rounds of discussion and voting, all 7 statements reached an overall agreement of 100% on the following issues: needle core/wedge/punch technique representatively [B,1], frozen/paraffin embedded section reliability [B,2], experienced/non-experienced on-call renal pathologist reproducibility/accuracy of the histological report [A,1], glomerulosclerosis/other parameters reproducibility [C,2], digital pathology/light microscopy in the measurement of histological variables [A,1], special stainings/Haematoxylin and Eosin alone comparison [A,1], glomerulosclerosis reliability versus other histological parameters to predict the graft survival, graft function, primary non-function [B,1]. This methodology has allowed to reach a full consensus among European experts on important technical topics regarding pre-implantation biopsy in the ECD graft assessment.
Collapse
Affiliation(s)
- Gianluigi Zaza
- Nephrology, Dialysis and Transplantation Unit, Department of Medical and Surgical Sciences, University/Hospital of Foggia, Foggia, Italy
| | - David Cucchiari
- Department of Nephrology and Kidney Transplantation, Hospital Clínic, Barcelona, Spain
| | - Jan Ulrich Becker
- Institut für Pathologie und Molekularpathologie, University Hospital of Cologne, Cologne, Germany
| | - Aiko P. J. de Vries
- Division of Nephrology, Department of Medicine, Transplant Center, Leiden University Medical Center, Leiden, Netherlands
| | - Albino Eccher
- Department of Pathology and Diagnostics, University and Hospital Trust of Verona, Verona, Italy
| | - Sandrine Florquin
- Department of Pathology, Amsterdam UMC, University of Amsterdam, Amsterdam, Netherlands
| | - Jesper Kers
- Department of Pathology, Amsterdam UMC, University of Amsterdam, Amsterdam, Netherlands
| | - Marion Rabant
- Department of Pathology, Necker-Enfants Malades University Hospital, Paris, France
| | - Michele Rossini
- Nephrology, Dialysis and Transplantation Unit, University/Hospital of Bari, Bari, Italy
| | - Liset Pengel
- Centre for Evidence in Transplantation, Oxford, United Kindom
| | - Lorna Marson
- Department of Surgery, University of Edinburgh, Edinburgh, United Kingdom
| | - Lucrezia Furian
- Kidney and Pancreas Transplantation Unit, University of Padova, Padova, Italy
| |
Collapse
|
3
|
Li X, Davis RC, Xu Y, Wang Z, Souma N, Sotolongo G, Bell J, Ellis M, Howell D, Shen X, Lafata KJ, Barisoni L. Deep learning segmentation of glomeruli on kidney donor frozen sections. J Med Imaging (Bellingham) 2021; 8:067501. [PMID: 34950750 PMCID: PMC8685284 DOI: 10.1117/1.jmi.8.6.067501] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2021] [Accepted: 11/08/2021] [Indexed: 10/15/2023] Open
Abstract
Purpose: Recent advances in computational image analysis offer the opportunity to develop automatic quantification of histologic parameters as aid tools for practicing pathologists. We aim to develop deep learning (DL) models to quantify nonsclerotic and sclerotic glomeruli on frozen sections from donor kidney biopsies. Approach: A total of 258 whole slide images (WSI) from cadaveric donor kidney biopsies performed at our institution ( n = 123 ) and at external institutions ( n = 135 ) were used in this study. WSIs from our institution were divided at the patient level into training and validation datasets (ratio: 0.8:0.2), and external WSIs were used as an independent testing dataset. Nonsclerotic ( n = 22767 ) and sclerotic ( n = 1366 ) glomeruli were manually annotated by study pathologists on all WSIs. A nine-layer convolutional neural network based on the common U-Net architecture was developed and tested for the segmentation of nonsclerotic and sclerotic glomeruli. DL-derived, manual segmentation, and reported glomerular count (standard of care) were compared. Results: The average Dice similarity coefficient testing was 0.90 and 0.83. And the F 1 , recall, and precision scores were 0.93, 0.96, and 0.90, and 0.87, 0.93, and 0.81, for nonsclerotic and sclerotic glomeruli, respectively. DL-derived and manual segmentation-derived glomerular counts were comparable, but statistically different from reported glomerular count. Conclusions: DL segmentation is a feasible and robust approach for automatic quantification of glomeruli. We represent the first step toward new protocols for the evaluation of donor kidney biopsies.
Collapse
Affiliation(s)
- Xiang Li
- Duke University, Department of Electrical and Computer Engineering, Durham, North Carolina, United States
| | - Richard C. Davis
- Duke University, Department of Pathology, Division of AI and Computational Pathology, Durham, North Carolina, United States
| | - Yuemei Xu
- Duke University, Department of Pathology, Division of AI and Computational Pathology, Durham, North Carolina, United States
- Nanjing Drum Tower Hospital, Department of Pathology, Nanjing, China
| | - Zehan Wang
- Duke University, Department of Biomedical Engineering, Durham, North Carolina, United States
| | - Nao Souma
- Duke University, Department of Medicine, Division of Nephrology, Durham, North Carolina, United States
| | - Gina Sotolongo
- Duke University, Department of Pathology, Division of AI and Computational Pathology, Durham, North Carolina, United States
| | - Jonathan Bell
- Duke University, Department of Pathology, Division of AI and Computational Pathology, Durham, North Carolina, United States
| | - Matthew Ellis
- Duke University, Department of Medicine, Division of Nephrology, Durham, North Carolina, United States
- Duke University, Department of Surgery, Durham, North Carolina, United States
| | - David Howell
- Duke University, Department of Pathology, Division of AI and Computational Pathology, Durham, North Carolina, United States
| | - Xiling Shen
- Duke University, Department of Biomedical Engineering, Durham, North Carolina, United States
| | - Kyle J. Lafata
- Duke University, Department of Electrical and Computer Engineering, Durham, North Carolina, United States
- Duke University, Department of Radiation Oncology, Durham, North Carolina, United States
- Duke University, Department of Radiology, Durham, North Carolina, United States
| | - Laura Barisoni
- Duke University, Department of Pathology, Division of AI and Computational Pathology, Durham, North Carolina, United States
- Duke University, Department of Medicine, Division of Nephrology, Durham, North Carolina, United States
| |
Collapse
|
4
|
Liu L, Cheng K, Huang J. Effect of Long Cold Ischemia Time of Kidneys from Aged Donors on Prognosis of Kidney Transplantation. Ann Transplant 2021; 26:e928735. [PMID: 34663778 PMCID: PMC8540027 DOI: 10.12659/aot.928735] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022] Open
Abstract
With the increasing incidence of end-stage renal disease (ESRD), patients' life span and life quality are significantly reduced. Kidney transplantation has gradually become the ideal method for treating ESRD, and the shortage of organ sources has become the main problem. In recent years, China has successfully realized the transformation of organ sources. Voluntary donation after the death of citizens has increased year by year, and the number of kidney transplantations has increased, which alleviates the organ shortage to a certain extent, but compared with the past, the increasing proportion of aged donors has also become an inevitable global problem. At the same time, due to the sudden and widespread distribution of voluntary donation, most donor kidneys have the problem of longer cold ischemic time (CIT). The probability of adverse events, such as delayed renal function recovery after transplantation, was also significantly increased. At present, there is little research on the effect of donor's aging and long CIT on the prognosis of renal transplantation. This paper reviews the literature in recent years and explore this problem from 2 aspects: the elderly donor and the long CIT.
Collapse
Affiliation(s)
- Lian Liu
- Center for Organ Transplantation, 3rd Xiangya Hospital, Central South University, Changsha, Hunan, China (mainland).,Research Center of National Health Ministry on Transplantation Medicine Engineering and Technology, 3rd Xiangya Hospital, Central South University, Changsha, Hunan, China (mainland).,Department of Anatomy and Neurobiology, School of Basic Medical Science, Central South University, Changsha, Hunan, China (mainland)
| | - Ke Cheng
- Center for Organ Transplantation, 3rd Xiangya Hospital, Central South University, Changsha, Hunan, China (mainland).,Research Center of National Health Ministry on Transplantation Medicine Engineering and Technology, 3rd Xiangya Hospital, Central South University, Changsha, Hunan, China (mainland)
| | - Jufang Huang
- Department of Anatomy and Neurobiology, School of Basic Medical Science, Central South University, Changsha, Hunan, China (mainland)
| |
Collapse
|
5
|
Teixeira AC, de Sandes-Freitas TV, Fagundes de Deus E Silva ML, Gomes Prado RM, de Matos Esmeraldo R. Procurement Biopsies Can Predict Unfavorable Outcomes in Kidneys With Low MAPI Score Values. Transplant Proc 2020; 53:602-606. [PMID: 33077181 DOI: 10.1016/j.transproceed.2020.09.010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/18/2020] [Revised: 08/31/2020] [Accepted: 09/20/2020] [Indexed: 11/27/2022]
Abstract
BACKGROUND There are few reports about the usefulness of Maryland Aggregate Pathology Index (MAPI) score in procurement biopsies. This study aimed to evaluate the association between histopathological analysis according to MAPI and unfavorable outcomes in the first year after kidney transplantation (KT). METHODS This retrospective study included deceased-donor KT patients whose grafts were biopsied before transplantation and had low MAPI scores (<8) in frozen sections (FSs). Paraffin sections (PSs) were analyzed after KT. MAPI parameters were global glomerulosclerosis in more than 15% (2 patients), periglomerular fibrosis (4 patients), wall-lumen ratio of arteries >0.5 (2 patients), arteriolar hyalinosis (4 patients), and interstitial scar (3 patients). Multivariable models were used to analyze risk factors for delayed graft function (DGF), prolonged DGF, inferior renal function, and graft loss (P < .05). RESULTS One hundred fifty-nine KTs were included. Donors (n = 120) were predominantly men (70%) and young adults (37.68 ± 12.50 years old) who suffered a traumatic death (55.8%). Recipients were predominantly men (62.26%) and adults (45.70 ± 15.80 years old) with kidney disease of unknown etiology (39.6%). Low rates of agreement between FS and PS were observed for all MAPI criteria, with kappa values ranging from 0.28 to 0.51. Using FS, no histologic parameter was independently associated with outcomes. After adjustment, glomerulosclerosis was an independent risk factor for prolonged DGF (odds ratio = 6.18: 95% confidence interval, 1.27-30.18) and wall-lumen ratio >0.5 for inferior renal function at 1 year (odds ratio = 4.08; 95% confidence interval, 1.21-13.76). CONCLUSION Procurement biopsies can be useful to predict inferior outcomes even in kidneys with low MAPI scores.
Collapse
Affiliation(s)
- André Costa Teixeira
- Department of Clinical Medicine, Faculty of Medicine of Federal University of Ceará, Fortaleza (CE), Brazil.
| | - Tainá Veras de Sandes-Freitas
- Department of Clinical Medicine, Faculty of Medicine of Federal University of Ceará, Fortaleza (CE), Brazil; Division of Transplantation, General Hospital of Fortaleza, Fortaleza (CE), Brazil
| | | | | | | |
Collapse
|