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 -