Early detection of liver fibrosis using graph convolutional networks

Conference item

Detection of early onset of fibrosis is critical to detecting long term damage to identify potential loss of organ function. While formal grading systems for fibrosis have been established, we argue that a quantitative analysis of fibrosis patterns will improve diagnostic quality and help to standardise clinical reporting. Here we are using deep learning to identify elementary fibrosis patterns. Subsequently, a graphical model is utilised to model the spatial organisation of the fibrosis patterns. Our experimental results demonstrated that this approach correlates well with established clinical grading. The presented method holds the potential to be applied to histology in other organs (e.g. kidney).

Authors: Wojciechowska, M; Malacrino, S; Garcia Martin, N; Fehri, H; Rittscher, J

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer Nature
• Host title: Proceedings of Medical Image Computing and Computer Assisted Intervention – MICCAI 2021
• Volume: 12908
• Pages: 217-226
• Series: Lecture Notes in Computer Science
• Place of publication: Cham, Switzerland
• Publication date: 2021-09-21
• Acceptance date: 2021-06-11
• Event title: 24th International Conference of Medical Image Computing and Computer Assisted Intervention (MICCAI 2021)
• Event location: Strasbourg, France
• Event website: miccai2021.org/
• Event start date: 2021-09-27
• Event end date: 2021-10-01
• DOI: 10.1007/978-3-030-87237-3_21
• EISSN: 1611-3349
• ISBN: 9783030872366
• Language: English
• Keywords: digital pathology; fibrosis; graph neural networks