Standard

The Robust Vessel Segmentation and Centerline Extraction: One-Stage Deep Learning Approach. / Epifanov, Rostislav; Fedotova, Yana; Dyachuk, Savely et al.

In: Journal of Imaging, Vol. 11, No. 7, 209, 26.06.2025.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Epifanov R, Fedotova Y, Dyachuk S, Gostev A, Karpenko A, Mullyadzhanov R. The Robust Vessel Segmentation and Centerline Extraction: One-Stage Deep Learning Approach. Journal of Imaging. 2025 Jun 26;11(7):209. doi: 10.3390/jimaging11070209

Author

BibTeX

@article{c40d619b6e78495cba45627bad43a5bb,
title = "The Robust Vessel Segmentation and Centerline Extraction: One-Stage Deep Learning Approach",
abstract = "The accurate segmentation of blood vessels and centerline extraction are critical in vascular imaging applications, ranging from preoperative planning to hemodynamic modeling. This study introduces a novel one-stage method for simultaneous vessel segmentation and centerline extraction using a multitask neural network. We designed a hybrid architecture that integrates convolutional and graph layers, along with a task-specific loss function, to effectively capture the topological relationships between segmentation and centerline extraction, leveraging their complementary features. The proposed end-to-end framework directly predicts the centerline as a polyline with real-valued coordinates, thereby eliminating the need for post-processing steps commonly required by previous methods that infer centerlines either implicitly or without ensuring point connectivity. We evaluated our approach on a combined dataset of 142 computed tomography angiography images of the thoracic and abdominal regions from LIDC-IDRI and AMOS datasets. The results demonstrate that our method achieves superior centerline extraction performance (Surface Dice with threshold of 3 mm: 97.65% (Formula presented.) 2.07%) compared to state-of-the-art techniques, and attains the highest subvoxel resolution (Surface Dice with threshold of 1 mm: 72.52% (Formula presented.) 8.96%). In addition, we conducted a robustness analysis to evaluate the model stability under small rigid and deformable transformations of the input data, and benchmarked its robustness against the widely used VMTK toolkit.",
keywords = "computed tomography angiography images, multitask neural network, one-stage centerline reconstruction, vascular modeling toolkit, vessel centerline extraction, vessel segmentation",
author = "Rostislav Epifanov and Yana Fedotova and Savely Dyachuk and Alexandr Gostev and Andrei Karpenko and Rustam Mullyadzhanov",
note = "The work of Epifanov R., Fedotova Y., and Gostev A. is supported by the Russian Science Foundation grant No. 23-75-10047. The work of Dyachuk S. and Mullyadzhanov R. was supported by the Mathematical Center in Akademgorodok under the Agreement No. 075-15-2025-349 with the Ministry of Science and Higher Education of the Russian Federation.",
year = "2025",
month = jun,
day = "26",
doi = "10.3390/jimaging11070209",
language = "English",
volume = "11",
journal = "Journal of Imaging",
issn = "2313-433X",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "7",

}

RIS

TY - JOUR

T1 - The Robust Vessel Segmentation and Centerline Extraction: One-Stage Deep Learning Approach

AU - Epifanov, Rostislav

AU - Fedotova, Yana

AU - Dyachuk, Savely

AU - Gostev, Alexandr

AU - Karpenko, Andrei

AU - Mullyadzhanov, Rustam

N1 - The work of Epifanov R., Fedotova Y., and Gostev A. is supported by the Russian Science Foundation grant No. 23-75-10047. The work of Dyachuk S. and Mullyadzhanov R. was supported by the Mathematical Center in Akademgorodok under the Agreement No. 075-15-2025-349 with the Ministry of Science and Higher Education of the Russian Federation.

PY - 2025/6/26

Y1 - 2025/6/26

N2 - The accurate segmentation of blood vessels and centerline extraction are critical in vascular imaging applications, ranging from preoperative planning to hemodynamic modeling. This study introduces a novel one-stage method for simultaneous vessel segmentation and centerline extraction using a multitask neural network. We designed a hybrid architecture that integrates convolutional and graph layers, along with a task-specific loss function, to effectively capture the topological relationships between segmentation and centerline extraction, leveraging their complementary features. The proposed end-to-end framework directly predicts the centerline as a polyline with real-valued coordinates, thereby eliminating the need for post-processing steps commonly required by previous methods that infer centerlines either implicitly or without ensuring point connectivity. We evaluated our approach on a combined dataset of 142 computed tomography angiography images of the thoracic and abdominal regions from LIDC-IDRI and AMOS datasets. The results demonstrate that our method achieves superior centerline extraction performance (Surface Dice with threshold of 3 mm: 97.65% (Formula presented.) 2.07%) compared to state-of-the-art techniques, and attains the highest subvoxel resolution (Surface Dice with threshold of 1 mm: 72.52% (Formula presented.) 8.96%). In addition, we conducted a robustness analysis to evaluate the model stability under small rigid and deformable transformations of the input data, and benchmarked its robustness against the widely used VMTK toolkit.

AB - The accurate segmentation of blood vessels and centerline extraction are critical in vascular imaging applications, ranging from preoperative planning to hemodynamic modeling. This study introduces a novel one-stage method for simultaneous vessel segmentation and centerline extraction using a multitask neural network. We designed a hybrid architecture that integrates convolutional and graph layers, along with a task-specific loss function, to effectively capture the topological relationships between segmentation and centerline extraction, leveraging their complementary features. The proposed end-to-end framework directly predicts the centerline as a polyline with real-valued coordinates, thereby eliminating the need for post-processing steps commonly required by previous methods that infer centerlines either implicitly or without ensuring point connectivity. We evaluated our approach on a combined dataset of 142 computed tomography angiography images of the thoracic and abdominal regions from LIDC-IDRI and AMOS datasets. The results demonstrate that our method achieves superior centerline extraction performance (Surface Dice with threshold of 3 mm: 97.65% (Formula presented.) 2.07%) compared to state-of-the-art techniques, and attains the highest subvoxel resolution (Surface Dice with threshold of 1 mm: 72.52% (Formula presented.) 8.96%). In addition, we conducted a robustness analysis to evaluate the model stability under small rigid and deformable transformations of the input data, and benchmarked its robustness against the widely used VMTK toolkit.

KW - computed tomography angiography images

KW - multitask neural network

KW - one-stage centerline reconstruction

KW - vascular modeling toolkit

KW - vessel centerline extraction

KW - vessel segmentation

UR - https://www.mendeley.com/catalogue/add42b1f-dd22-38c7-8ece-22fca57544e0/

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105011415375&origin=inward

U2 - 10.3390/jimaging11070209

DO - 10.3390/jimaging11070209

M3 - Article

C2 - 40710596

VL - 11

JO - Journal of Imaging

JF - Journal of Imaging

SN - 2313-433X

IS - 7

M1 - 209

ER -

ID: 68614281