IsletSwipe, a mobile platform for expert opinion exchange on islet graft images

0571406 - FGÚ 2024 RIV US eng J - Journal Article
Habart, D. - Koza, A. - Leontovyč, I. - Kosinová, L. - Berková, Z. - Kříž, J. - Zacharovová, K. - Brinkhof, B. - Cornelissen, D. J. - Magrane, N. - Bittenglová, K. - Čapek, Martin - Valečka, J. - Habartová, Alena - Saudek, F.
IsletSwipe, a mobile platform for expert opinion exchange on islet graft images.
Islets. Roč. 15, č. 1 (2023), č. článku 2189873. ISSN 1938-2014. E-ISSN 1938-2022
R&D Projects: GA MZd(CZ) NU22-01-00141; GA MŠMT(CZ) LX22NPO5104; GA MŠMT(CZ) LM2018129; GA MŠMT(CZ) EF18_046/0016045
Institutional support: RVO:67985823 ; RVO:61388963
Keywords : consensus building * deep learning * expert opinion exchange * ground truth * human islets * image annotation * islet counting * mobile application * islet graft quality control * islet isolation * islet transplantation * user experience
OECD category: Transplantation; Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) (UOCHB-X)
Impact factor: 2.2, year: 2022
Method of publishing: Open access
https://doi.org/10.1080/19382014.2023.2189873

We previously developed a deep learning-based web service (IsletNet) for an automated counting of isolated pancreatic islets. The neural network training is limited by the absent consensus on the ground truth annotations. Here, we present a platform (IsletSwipe) for an exchange of graphical opinions among experts to facilitate the consensus formation. The platform consists of a web interface and a mobile application. In a small pilot study, we demonstrate the functionalities and the use case scenarios of the platform. Nine experts from three centers validated the drawing tools, tested precision and consistency of the expert contour drawing, and evaluated user experience. Eight experts from two centers proceeded to evaluate additional images to demonstrate the following two use case scenarios. The Validation scenario involves an automated selection of images and islets for the expert scrutiny. It is scalable (more experts, images, and islets may readily be added) and can be applied to independent validation of islet contours from various sources. The Inquiry scenario serves the ground truth generating expert in seeking assistance from peers to achieve consensus on challenging cases during the preparation for IsletNet training. This scenario is limited to a small number of manually selected images and islets. The experts gained an opportunity to influence IsletNet training and to compare other experts’ opinions with their own. The ground truth-generating expert obtained feedback for future IsletNet training. IsletSwipe is a suitable tool for the consensus finding. Experts from additional centers are welcome to participate.
Permanent Link: https://hdl.handle.net/11104/0342639