DTU-Net: Learning Topological Similarity for Curvilinear Structure Segmentation
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
DTU-Net : Learning Topological Similarity for Curvilinear Structure Segmentation. / Lin, Manxi; Zepf, Kilian; Christensen, Anders Nymark; Bashir, Zahra; Svendsen, Morten Bo Søndergaard; Tolsgaard, Martin; Feragen, Aasa.
Information Processing in Medical Imaging - 28th International Conference, IPMI 2023, Proceedings. ed. / Alejandro Frangi; Marleen de Bruijne; Demian Wassermann; Nassir Navab. Springer, 2023. p. 654-666 (Lecture Notes in Computer Science, Vol. 13939).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - DTU-Net
T2 - 28th International Conference on Information Processing in Medical Imaging, IPMI 2023
AU - Lin, Manxi
AU - Zepf, Kilian
AU - Christensen, Anders Nymark
AU - Bashir, Zahra
AU - Svendsen, Morten Bo Søndergaard
AU - Tolsgaard, Martin
AU - Feragen, Aasa
N1 - Publisher Copyright: © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - Curvilinear structure segmentation is important in medical imaging, quantifying structures such as vessels, airways, neurons, or organ boundaries in 2D slices. Segmentation via pixel-wise classification often fails to capture the small and low-contrast curvilinear structures. Prior topological information is typically used to address this problem, often at an expensive computational cost, and sometimes requiring prior knowledge of the expected topology. We present DTU-Net, a data-driven approach to topology-preserving curvilinear structure segmentation. DTU-Net consists of two sequential, lightweight U-Nets, dedicated to texture and topology, respectively. While the texture net makes a coarse prediction using image texture information, the topology net learns topological information from the coarse prediction by employing a triplet loss trained to recognize false and missed splits in the structure. We conduct experiments on a challenging multi-class ultrasound scan segmentation dataset as well as a well-known retinal imaging dataset. Results show that our model outperforms existing approaches in both pixel-wise segmentation accuracy and topological continuity, with no need for prior topological knowledge.
AB - Curvilinear structure segmentation is important in medical imaging, quantifying structures such as vessels, airways, neurons, or organ boundaries in 2D slices. Segmentation via pixel-wise classification often fails to capture the small and low-contrast curvilinear structures. Prior topological information is typically used to address this problem, often at an expensive computational cost, and sometimes requiring prior knowledge of the expected topology. We present DTU-Net, a data-driven approach to topology-preserving curvilinear structure segmentation. DTU-Net consists of two sequential, lightweight U-Nets, dedicated to texture and topology, respectively. While the texture net makes a coarse prediction using image texture information, the topology net learns topological information from the coarse prediction by employing a triplet loss trained to recognize false and missed splits in the structure. We conduct experiments on a challenging multi-class ultrasound scan segmentation dataset as well as a well-known retinal imaging dataset. Results show that our model outperforms existing approaches in both pixel-wise segmentation accuracy and topological continuity, with no need for prior topological knowledge.
KW - Curvilinear segmentation
KW - topology preservation
KW - triplet loss
U2 - 10.1007/978-3-031-34048-2_50
DO - 10.1007/978-3-031-34048-2_50
M3 - Article in proceedings
AN - SCOPUS:85164012711
SN - 978-3-031-34047-5
T3 - Lecture Notes in Computer Science
SP - 654
EP - 666
BT - Information Processing in Medical Imaging - 28th International Conference, IPMI 2023, Proceedings
A2 - Frangi, Alejandro
A2 - de Bruijne, Marleen
A2 - Wassermann, Demian
A2 - Navab, Nassir
PB - Springer
Y2 - 18 June 2023 through 23 June 2023
ER -
ID: 366267126