EMPAIA app interface: an open and vendor-neutral interface for AI applications in pathology

Daniel Romberg; Klaus Strohmenger; Christoph Jansen; Tobias Küster; Nick Weiss; Christian Geißler; Tomasz Sołtysiński; Michael Takla; Peter Hufnagl; Norman Zerbe

EMPAIA app interface: an open and vendor-neutral interface for AI applications in pathology

Daniel Romberg, Klaus Strohmenger, Christoph Jansen, Tobias Küster, Nick Weiss, Christian Geißler, Tomasz Sołtysiński, Michael Takla, Peter Hufnagl, Norman Zerbe

Institute of Mathematics and Image Computing

8 Citations (Scopus)

Abstract

Background and objective
Artificial intelligence (AI) apps hold great potential to make pathological diagnoses more accurate and time efficient. Widespread use of AI in pathology is hampered by interface incompatibilities between pathology software. We studied the existing interfaces in order to develop the EMPAIA App Interface, an open standard for the integration of pathology AI apps.

Methods
The EMPAIA App Interface relies on widely-used web communication protocols and containerization. It consists of three parts: A standardized format to describe the semantics of an app, a mechanism to deploy and execute apps in computing environments, and a web API through which apps can exchange data with a host application.

Results
Five commercial AI app manufacturers successfully adapted their products to the EMPAIA App Interface and helped improve it with their feedback. Open source tools facilitate the adoption of the interface by providing reusable data access and scheduling functionality and enabling automatic validation of app compliance.

Conclusions
Existing AI apps and pathology software can be adapted to the EMPAIA App Interface with little effort. It is a viable alternative to the proprietary interfaces of current software. If enough vendors join in, the EMPAIA App Interface can help to advance the use of AI in pathology.

Original language	English
Journal	Computer Methods and Programs in Biomedicine
Volume	215
Issue number	March 2022, 106596
Pages (from-to)	106596
Number of pages	1
ISSN	0169-2607
Publication status	Published - 2022

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Access to Document

https://www.sciencedirect.com/science/article/pii/S0169260721006702

Cite this

Romberg, D., Strohmenger, K., Jansen, C., Küster, T., Weiss, N., Geißler, C., Sołtysiński, T., Takla, M., Hufnagl, P., & Zerbe, N. (2022). EMPAIA app interface: an open and vendor-neutral interface for AI applications in pathology. Computer Methods and Programs in Biomedicine, 215(March 2022, 106596), 106596. https://www.sciencedirect.com/science/article/pii/S0169260721006702

@article{039bb05a53e442709c5a493d6eff7789,

title = "EMPAIA app interface: an open and vendor-neutral interface for AI applications in pathology",

abstract = "Background and objective Artificial intelligence (AI) apps hold great potential to make pathological diagnoses more accurate and time efficient. Widespread use of AI in pathology is hampered by interface incompatibilities between pathology software. We studied the existing interfaces in order to develop the EMPAIA App Interface, an open standard for the integration of pathology AI apps. Methods The EMPAIA App Interface relies on widely-used web communication protocols and containerization. It consists of three parts: A standardized format to describe the semantics of an app, a mechanism to deploy and execute apps in computing environments, and a web API through which apps can exchange data with a host application. Results Five commercial AI app manufacturers successfully adapted their products to the EMPAIA App Interface and helped improve it with their feedback. Open source tools facilitate the adoption of the interface by providing reusable data access and scheduling functionality and enabling automatic validation of app compliance. Conclusions Existing AI apps and pathology software can be adapted to the EMPAIA App Interface with little effort. It is a viable alternative to the proprietary interfaces of current software. If enough vendors join in, the EMPAIA App Interface can help to advance the use of AI in pathology.",

author = "Daniel Romberg and Klaus Strohmenger and Christoph Jansen and Tobias K{\"u}ster and Nick Weiss and Christian Gei{\ss}ler and Tomasz So{\l}tysi{\'n}ski and Michael Takla and Peter Hufnagl and Norman Zerbe",

year = "2022",

language = "English",

volume = "215",

pages = "106596",

journal = "Computer Methods and Programs in Biomedicine",

issn = "0169-2607",

publisher = "Elsevier Ireland Ltd",

number = "March 2022, 106596",

}

Romberg, D, Strohmenger, K, Jansen, C, Küster, T, Weiss, N, Geißler, C, Sołtysiński, T, Takla, M, Hufnagl, P & Zerbe, N 2022, 'EMPAIA app interface: an open and vendor-neutral interface for AI applications in pathology', Computer Methods and Programs in Biomedicine, vol. 215, no. March 2022, 106596, pp. 106596. <https://www.sciencedirect.com/science/article/pii/S0169260721006702>

TY - JOUR

T1 - EMPAIA app interface: an open and vendor-neutral interface for AI applications in pathology

AU - Romberg, Daniel

AU - Strohmenger, Klaus

AU - Jansen, Christoph

AU - Küster, Tobias

AU - Weiss, Nick

AU - Geißler, Christian

AU - Sołtysiński, Tomasz

AU - Takla, Michael

AU - Hufnagl, Peter

AU - Zerbe, Norman

PY - 2022

Y1 - 2022

N2 - Background and objective Artificial intelligence (AI) apps hold great potential to make pathological diagnoses more accurate and time efficient. Widespread use of AI in pathology is hampered by interface incompatibilities between pathology software. We studied the existing interfaces in order to develop the EMPAIA App Interface, an open standard for the integration of pathology AI apps. Methods The EMPAIA App Interface relies on widely-used web communication protocols and containerization. It consists of three parts: A standardized format to describe the semantics of an app, a mechanism to deploy and execute apps in computing environments, and a web API through which apps can exchange data with a host application. Results Five commercial AI app manufacturers successfully adapted their products to the EMPAIA App Interface and helped improve it with their feedback. Open source tools facilitate the adoption of the interface by providing reusable data access and scheduling functionality and enabling automatic validation of app compliance. Conclusions Existing AI apps and pathology software can be adapted to the EMPAIA App Interface with little effort. It is a viable alternative to the proprietary interfaces of current software. If enough vendors join in, the EMPAIA App Interface can help to advance the use of AI in pathology.

AB - Background and objective Artificial intelligence (AI) apps hold great potential to make pathological diagnoses more accurate and time efficient. Widespread use of AI in pathology is hampered by interface incompatibilities between pathology software. We studied the existing interfaces in order to develop the EMPAIA App Interface, an open standard for the integration of pathology AI apps. Methods The EMPAIA App Interface relies on widely-used web communication protocols and containerization. It consists of three parts: A standardized format to describe the semantics of an app, a mechanism to deploy and execute apps in computing environments, and a web API through which apps can exchange data with a host application. Results Five commercial AI app manufacturers successfully adapted their products to the EMPAIA App Interface and helped improve it with their feedback. Open source tools facilitate the adoption of the interface by providing reusable data access and scheduling functionality and enabling automatic validation of app compliance. Conclusions Existing AI apps and pathology software can be adapted to the EMPAIA App Interface with little effort. It is a viable alternative to the proprietary interfaces of current software. If enough vendors join in, the EMPAIA App Interface can help to advance the use of AI in pathology.

M3 - Journal articles

SN - 0169-2607

VL - 215

SP - 106596

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

IS - March 2022, 106596

ER -