Semi-supervised, Topology-Aware Segmentation of Tubular Structures from Live Imaging 3D Microscopy

Kasra Arnavaz, Oswin Krause, Jelena Miskovic Krivokapic, Silja Heilmann, Jakob Andreas Bærentzen, Pia Nyeng, Aasa Feragen

Research output: Other contributionNet publication - Internet publicationResearch


Motivated by a challenging tubular network segmentation task, this paper tackles two commonly encountered problems in biomedical imaging: Topological consistency of the segmentation, and limited annotations. We propose a topological score which measures both topological and geometric consistency between the predicted and ground truth segmentations, applied for model selection and validation. We apply our topological score in three scenarios: i. a U-net ii. a U-net pretrained on an autoencoder, and iii. a semisupervised U-net architecture, which offers a straightforward approach to jointly training the network both as an autoencoder and a segmentation algorithm. This allows us to utilize un-annotated data for training a representation that generalizes across test data variability, in spite of our annotated training data having very limited variation. Our contributions are validated on a challenging segmentation task, locating tubular structures in the fetal pancreas from noisy live imaging confocal microscopy.
Original languageEnglish
Publication date20 May 2021 - Cornell University
Number of pages10
Publication statusPublished - 20 May 2021

Cite this