Banff Digital Pathology Working Group: Image Bank, Artificial Intelligence Algorithm, and Challenge Trial Developments

Alton B Farris¹, Mariam P Alexander², Ulysses G J Balis³, Laura Barisoni⁴, Peter Boor^{5

6}, Roman D Bülow⁵, Lynn D Cornell², Anthony J Demetris⁷, Evan Farkash³, Meyke Hermsen⁸, Julien Hogan^{1

9}, Renate Kain¹⁰, Jesper Kers^{11

12}, Jun Kong^{13

14}, Richard M Levenson¹⁵, Alexandre Loupy¹⁶, Maarten Naesens¹⁷, Pinaki Sarder¹⁸, John E Tomaszewski¹⁹, Jeroen van der Laak^{8

20}, Dominique van Midden⁸, Yukako Yagi²¹, Kim Solez²²

Affiliations

¹ Department of Pathology and Laboratory Medicine, Emory University, Atlanta, GE, United States.
² Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, United States.
³ Department of Pathology, University of Michigan, Ann Arbor, MI, United States.
⁴ Department of Pathology and Medicine, Duke University, Durham, NC, United States.
⁵ Institute of Pathology, Rheinisch-Westfälische Technische Hochschule (RWTH) Aachen University Clinic, Aachen, Germany.
⁶ Department of Nephrology and Immunology, RWTH Aachen University Clinic, Aachen, Germany.
⁷ Department of Pathology, University of Pittsburgh, Pittsburgh, PA, United States.
⁸ Department of Pathology, Radboud University Medical Center, Nijmegen, Netherlands.
⁹ Nephrology Service, Robert Debré Hospital, University of Paris, Paris, France.
¹⁰ Department of Pathology, Medical University of Vienna, Vienna, Austria.
¹¹ Department of Pathology, Amsterdam University Medical Centers, Amsterdam, Netherlands.
¹² Department of Pathology, Leiden University Medical Center, Leiden, Netherlands.
¹³ Georgia State University, Atlanta, GA, United States.
¹⁴ Emory University, Atlanta, GA, United States.
¹⁵ Department of Pathology, University of California Davis Health System, Sacramento, CA, United States.
¹⁶ Institut National de la Santé et de la Recherche Médicale, UMR 970, Paris Translational Research Centre for Organ Transplantation, and Kidney Transplant Department, Hôpital Necker, Assistance Publique-Hôpitaux de Paris, University of Paris, Paris, France.
¹⁷ Department of Microbiology, Immunology and Transplantation, KU Leuven, Leuven, Belgium.
¹⁸ Division of Nephrology, Hypertension, and Renal Transplantation, Department of Medicine, Intelligent Critical Care Center, College of Medicine, University of Florida at Gainesville, Gainesville, FL, United States.
¹⁹ Department of Pathology, The State University of New York at Buffalo, Buffalo, NY, United States.
²⁰ Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden.
²¹ Memorial Sloan Kettering Cancer Center, New York, NY, United States.
²² Department of Pathology, University of Alberta, Edmonton, AB, Canada.

PMID: 37908675
PMCID: PMC10614670
DOI: 10.3389/ti.2023.11783

Banff Digital Pathology Working Group: Image Bank, Artificial Intelligence Algorithm, and Challenge Trial Developments

Alton B Farris et al. Transpl Int. 2023.

. 2023 Oct 16:36:11783.

doi: 10.3389/ti.2023.11783. eCollection 2023.

Authors

Affiliations

¹ Department of Pathology and Laboratory Medicine, Emory University, Atlanta, GE, United States.
² Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, MN, United States.
³ Department of Pathology, University of Michigan, Ann Arbor, MI, United States.
⁴ Department of Pathology and Medicine, Duke University, Durham, NC, United States.
⁵ Institute of Pathology, Rheinisch-Westfälische Technische Hochschule (RWTH) Aachen University Clinic, Aachen, Germany.
⁶ Department of Nephrology and Immunology, RWTH Aachen University Clinic, Aachen, Germany.
⁷ Department of Pathology, University of Pittsburgh, Pittsburgh, PA, United States.
⁸ Department of Pathology, Radboud University Medical Center, Nijmegen, Netherlands.
⁹ Nephrology Service, Robert Debré Hospital, University of Paris, Paris, France.
¹⁰ Department of Pathology, Medical University of Vienna, Vienna, Austria.
¹¹ Department of Pathology, Amsterdam University Medical Centers, Amsterdam, Netherlands.
¹² Department of Pathology, Leiden University Medical Center, Leiden, Netherlands.
¹³ Georgia State University, Atlanta, GA, United States.
¹⁴ Emory University, Atlanta, GA, United States.
¹⁵ Department of Pathology, University of California Davis Health System, Sacramento, CA, United States.
¹⁶ Institut National de la Santé et de la Recherche Médicale, UMR 970, Paris Translational Research Centre for Organ Transplantation, and Kidney Transplant Department, Hôpital Necker, Assistance Publique-Hôpitaux de Paris, University of Paris, Paris, France.
¹⁷ Department of Microbiology, Immunology and Transplantation, KU Leuven, Leuven, Belgium.
¹⁸ Division of Nephrology, Hypertension, and Renal Transplantation, Department of Medicine, Intelligent Critical Care Center, College of Medicine, University of Florida at Gainesville, Gainesville, FL, United States.
¹⁹ Department of Pathology, The State University of New York at Buffalo, Buffalo, NY, United States.
²⁰ Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden.
²¹ Memorial Sloan Kettering Cancer Center, New York, NY, United States.
²² Department of Pathology, University of Alberta, Edmonton, AB, Canada.

PMID: 37908675
PMCID: PMC10614670
DOI: 10.3389/ti.2023.11783

Abstract

The Banff Digital Pathology Working Group (DPWG) was established with the goal to establish a digital pathology repository; develop, validate, and share models for image analysis; and foster collaborations using regular videoconferencing. During the calls, a variety of artificial intelligence (AI)-based support systems for transplantation pathology were presented. Potential collaborations in a competition/trial on AI applied to kidney transplant specimens, including the DIAGGRAFT challenge (staining of biopsies at multiple institutions, pathologists' visual assessment, and development and validation of new and pre-existing Banff scoring algorithms), were also discussed. To determine the next steps, a survey was conducted, primarily focusing on the feasibility of establishing a digital pathology repository and identifying potential hosts. Sixteen of the 35 respondents (46%) had access to a server hosting a digital pathology repository, with 2 respondents that could serve as a potential host at no cost to the DPWG. The 16 digital pathology repositories collected specimens from various organs, with the largest constituent being kidney (n = 12,870 specimens). A DPWG pilot digital pathology repository was established, and there are plans for a competition/trial with the DIAGGRAFT project. Utilizing existing resources and previously established models, the Banff DPWG is establishing new resources for the Banff community.

Keywords: Banff; artificial intelligence; digital pathology; image analysis; machine learning.

Copyright © 2023 Farris, Alexander, Balis, Barisoni, Boor, Bülow, Cornell, Demetris, Farkash, Hermsen, Hogan, Kain, Kers, Kong, Levenson, Loupy, Naesens, Sarder, Tomaszewski, van der Laak, van Midden, Yagi and Solez.

PubMed Disclaimer

Conflict of interest statement

JvL has been a member of the advisory boards of Philips, Netherlands and ContextVision, Sweden, and received research funding from Philips, Netherlands, ContextVision, Sweden, and Sectra, Sweden in the last 5 years. He is chief scientific officer (CSO) and shareholder of Aiosyn BV, Netherlands. JeK is a consultant for Aiosyn BV and Novartis AG Switzerland and received speaker fees from Chiesi Pharmaceuticals, Netherlands. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

**FIGURE 1**
The Banff Digital Pathology Working Group (DPWG) main aims are shown. The primary aims of the Banff DPWG include 1) image bank/collection establishment, to possibly include other data in digital pathology repositories (digital pathology repositories); 2) algorithm sharing platform initialization; and 3) competition/trial organization. Multiple solutions for each of these aims may be possible. After competition/trial conduction among the Banff community and other collaborators, the algorithm performance will be characterized in a process that will affect the future performance and sharing of algorithms; and thus, the competition(s)/trial(s) will provide “feedback” to algorithm sharing. Ultimately, effective, precision patient care could be provided with Banff algorithm scores. (The “Banff Conference” and “Aim 3” image were produced by Kim Solez using DALL-E 2.).

**FIGURE 2**
Digital Pathology Laboratory: a publicly available web platform for multi-dimensional pathology image analytics example image manipulations are shown, including the following: **(A)** A representative WSI visualized from DPLab at multiple image resolutions; **(B)** Cell detection result in a user-annotated rectangle region; **(C)** Liver fibrosis quantification with a region annotated by a free-hand annotation tool; **(D)** Detailed 3D liver tissue sub-volume visualization after serial WSI registration and collagen quantifications.

**FIGURE 3**
The DIAGGRAFT Challenge Work Plan is shown. Abbreviations: FFPE, formalin-fixed paraffin-embedded; PAS, periodic acid Schiff; WSI, Whole Slide Images; IHC, immunohistochemistry.

See this image and copyright information in PMC

References

1. Farris AB, Moghe I, Wu S, Hogan J, Cornell LD, Alexander MP, et al. Banff Digital Pathology Working Group: Going Digital in Transplant Pathology. Am J Transpl (2020) 20:2392–9. 10.1111/ajt.15850 - DOI - PMC - PubMed
1. Abels E, Pantanowitz L, Aeffner F, Zarella MD, van der Laak J, Bui MM, et al. Computational Pathology Definitions, Best Practices, and Recommendations for Regulatory Guidance: A White Paper From the Digital Pathology Association. J Pathol (2019) 249:286–94. 10.1002/path.5331 - DOI - PMC - PubMed
1. Louis DN, Feldman M, Carter AB, Dighe AS, Pfeifer JD, Bry L, et al. Computational Pathology: A Path Ahead. Arch Pathol Lab Med (2015) 140:41–50. 10.5858/arpa.2015-0093-SA - DOI - PMC - PubMed
1. Fuchs TJ, Buhmann JM. Computational Pathology: Challenges and Promises for Tissue Analysis. Comput Med Imaging Graph (2011) 35:515–30. 10.1016/j.compmedimag.2011.02.006 - DOI - PubMed
1. Barisoni L, Lafata KJ, Hewitt SM, Madabhushi A, Balis UGJ. Digital Pathology and Computational Image Analysis in Nephropathology. Nat Rev Nephrol (2020) 16:669–85. 10.1038/s41581-020-0321-6 - DOI - PMC - PubMed

MeSH terms

Actions
Actions
Actions
Actions
Actions

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Banff Digital Pathology Working Group: Image Bank, Artificial Intelligence Algorithm, and Challenge Trial Developments

Affiliations

Banff Digital Pathology Working Group: Image Bank, Artificial Intelligence Algorithm, and Challenge Trial Developments

Authors

Affiliations

Abstract

Conflict of interest statement

Figures

References

MeSH terms

Grants and funding

LinkOut - more resources

Full Text Sources

Medical