Differentiable Boundary Point Extraction for Weakly Supervised Star-shaped Object Segmentation

Robin Camarasa*, Hoel Kervadec, Daniel Bos, Marleen de Bruijne

*Corresponding author for this work

Research output: Contribution to conferencePaperAcademic

2 Citations (Scopus)
5 Downloads (Pure)


Although Deep Learning is the new gold standard in medical image segmentation, the annotation burden limits its expansion to clinical practice. We also observe a mismatch between annotations required by deep learning methods designed with pixel-wise optimization in mind and clinically relevant annotations designed for biomarkers extraction (diameters, counts, etc.). Our study proposes a first step toward bridging this gap, optimizing vessel segmentation based on its diameter annotations. To do so we propose to extract boundary points from a star-shaped segmentation in a differentiable manner. This differentiable extraction allows reducing annotation burden as instead of the pixel-wise segmentation only the two annotated points required for diameter measurement are used for training the model. Our experiments show that training based on diameter is efficient; produces state-of-the-art weakly supervised segmentation; and performs reasonably compared to full supervision.

Original languageEnglish
Number of pages11
Publication statusPublished - 2022
EventMedical Imaging with Deep Learning - Zürich, Switzerland
Duration: 6 Jul 20228 Jul 2022


ConferenceMedical Imaging with Deep Learning
Abbreviated titleMIDL
Internet address

Bibliographical note

Publisher Copyright:
© 2022 H. Kervadec, D. Bos & M. de Bruijne.


Dive into the research topics of 'Differentiable Boundary Point Extraction for Weakly Supervised Star-shaped Object Segmentation'. Together they form a unique fingerprint.

Cite this