Nested star-shaped objects segmentation using diameter annotations
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Nested star-shaped objects segmentation using diameter annotations. / Camarasa, Robin; Kervadec, Hoel; Kooi, M. Eline; Hendrikse, Jeroen; Nederkoorn, Paul J.; Bos, Daniel; de Bruijne, Marleen.
In: Medical Image Analysis, Vol. 90, 102934, 2023.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Nested star-shaped objects segmentation using diameter annotations
AU - Camarasa, Robin
AU - Kervadec, Hoel
AU - Kooi, M. Eline
AU - Hendrikse, Jeroen
AU - Nederkoorn, Paul J.
AU - Bos, Daniel
AU - de Bruijne, Marleen
N1 - Publisher Copyright: © 2023 The Authors
PY - 2023
Y1 - 2023
N2 - Most current deep learning based approaches for image segmentation require annotations of large datasets, which limits their application in clinical practice. We observe a mismatch between the voxelwise ground-truth that is required to optimize an objective at a voxel level and the commonly used, less time-consuming clinical annotations seeking to characterize the most important information about the patient (diameters, counts, etc.). In this study, we propose to bridge this gap for the case of multiple nested star-shaped objects (e.g., a blood vessel lumen and its outer wall) by optimizing a deep learning model based on diameter annotations. This is achieved by extracting in a differentiable manner the boundary points of the objects at training time, and by using this extraction during the backpropagation. We evaluate the proposed approach on segmentation of the carotid artery lumen and wall from multisequence MR images, thus reducing the annotation burden to only four annotated landmarks required to measure the diameters in the direction of the vessel's maximum narrowing. Our experiments show that training based on diameter annotations produces state-of-the-art weakly supervised segmentations and performs reasonably compared to full supervision. We made our code publicly available at https://gitlab.com/radiology/aim/carotid-artery-image-analysis/nested-star-shaped-objects.
AB - Most current deep learning based approaches for image segmentation require annotations of large datasets, which limits their application in clinical practice. We observe a mismatch between the voxelwise ground-truth that is required to optimize an objective at a voxel level and the commonly used, less time-consuming clinical annotations seeking to characterize the most important information about the patient (diameters, counts, etc.). In this study, we propose to bridge this gap for the case of multiple nested star-shaped objects (e.g., a blood vessel lumen and its outer wall) by optimizing a deep learning model based on diameter annotations. This is achieved by extracting in a differentiable manner the boundary points of the objects at training time, and by using this extraction during the backpropagation. We evaluate the proposed approach on segmentation of the carotid artery lumen and wall from multisequence MR images, thus reducing the annotation burden to only four annotated landmarks required to measure the diameters in the direction of the vessel's maximum narrowing. Our experiments show that training based on diameter annotations produces state-of-the-art weakly supervised segmentations and performs reasonably compared to full supervision. We made our code publicly available at https://gitlab.com/radiology/aim/carotid-artery-image-analysis/nested-star-shaped-objects.
KW - Carotid artery
KW - Image segmentation
KW - Weak annotations
UR - http://www.scopus.com/inward/record.url?scp=85172397329&partnerID=8YFLogxK
U2 - 10.1016/j.media.2023.102934
DO - 10.1016/j.media.2023.102934
M3 - Journal article
C2 - 37688981
AN - SCOPUS:85172397329
VL - 90
JO - Medical Image Analysis
JF - Medical Image Analysis
SN - 1361-8415
M1 - 102934
ER -
ID: 369547919