TY - GEN

T1 - Differentiable Boundary Point Extraction for Weakly Supervised Star-shaped Object Segmentation

AU - Camarasa, Robin

AU - Kervadec, Hoel

AU - Bos, Daniel

AU - de Bruijne, Marleen

N1 - Funding Information: This work was funded by Netherlands Organisation for Scientific Research (NWO) VICI project VI.C.182.042. Publisher Copyright: © 2022 H. Kervadec, D. Bos & M. de Bruijne.

PY - 2022

Y1 - 2022

N2 - 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.

AB - 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.

KW - Carotid artery stenosis

KW - Image segmentation

KW - weak annotations

M3 - Conference article

AN - SCOPUS:85162721921

VL - 172

SP - 188

EP - 198

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

SN - 2640-3498

T2 - 5th International Conference on Medical Imaging with Deep Learning, MIDL 2022

Y2 - 6 July 2022 through 8 July 2022

ER -