Semi-supervised coronary vessels segmentation from invasive coronary angiography with connectivity-preserving loss function
The segmentation of arteries in invasive coronary angiography is necessary to build quantitative models and eventually improve the diagnosis of cardiovascular diseases. Standard segmentation algorithms suffer due to the lack of fully annotated datasets and tend to return disconnected vessels. Thus,...
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2022
|
| _version_ | 1797108138409721856 |
|---|---|
| author | He, H Banerjee, A Beetz, M Choudhury, RP Grau, V Ieee |
| author_facet | He, H Banerjee, A Beetz, M Choudhury, RP Grau, V Ieee |
| author_sort | He, H |
| collection | OXFORD |
| description | The segmentation of arteries in invasive coronary angiography is necessary to build quantitative models and eventually improve the diagnosis of cardiovascular diseases. Standard segmentation algorithms suffer due to the lack of fully annotated datasets and tend to return disconnected vessels. Thus, we explore a semi-supervised segmentation framework to address these issues. Specifically, we use a student model and a teacher model as the main framework with Nested U-Nets (UNet++) as their backbones. The student model learns by minimizing a segmentation loss between the output and the ground truth, and a consistency loss guided by the uncertainty information. Additionally, a special loss function based on elastic interaction is used to improve the connectivity of arterial branches. We demonstrate the effectiveness of our proposed techniques over 42 labeled and 60 unlabeled samples and find relative improvement of 5.59% for Dice score and 69.99% for Betti number compared to a U-Net. |
| first_indexed | 2024-03-07T07:23:36Z |
| format | Conference item |
| id | oxford-uuid:ebb4ba88-a555-4738-9409-3022ff86fa2e |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:23:36Z |
| publishDate | 2022 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:ebb4ba88-a555-4738-9409-3022ff86fa2e2022-11-09T12:28:07ZSemi-supervised coronary vessels segmentation from invasive coronary angiography with connectivity-preserving loss functionConference itemhttp://purl.org/coar/resource_type/c_5794uuid:ebb4ba88-a555-4738-9409-3022ff86fa2eEnglishSymplectic ElementsIEEE2022He, HBanerjee, ABeetz, MChoudhury, RPGrau, VIeeeThe segmentation of arteries in invasive coronary angiography is necessary to build quantitative models and eventually improve the diagnosis of cardiovascular diseases. Standard segmentation algorithms suffer due to the lack of fully annotated datasets and tend to return disconnected vessels. Thus, we explore a semi-supervised segmentation framework to address these issues. Specifically, we use a student model and a teacher model as the main framework with Nested U-Nets (UNet++) as their backbones. The student model learns by minimizing a segmentation loss between the output and the ground truth, and a consistency loss guided by the uncertainty information. Additionally, a special loss function based on elastic interaction is used to improve the connectivity of arterial branches. We demonstrate the effectiveness of our proposed techniques over 42 labeled and 60 unlabeled samples and find relative improvement of 5.59% for Dice score and 69.99% for Betti number compared to a U-Net. |
| spellingShingle | He, H Banerjee, A Beetz, M Choudhury, RP Grau, V Ieee Semi-supervised coronary vessels segmentation from invasive coronary angiography with connectivity-preserving loss function |
| title | Semi-supervised coronary vessels segmentation from invasive coronary angiography with connectivity-preserving loss function |
| title_full | Semi-supervised coronary vessels segmentation from invasive coronary angiography with connectivity-preserving loss function |
| title_fullStr | Semi-supervised coronary vessels segmentation from invasive coronary angiography with connectivity-preserving loss function |
| title_full_unstemmed | Semi-supervised coronary vessels segmentation from invasive coronary angiography with connectivity-preserving loss function |
| title_short | Semi-supervised coronary vessels segmentation from invasive coronary angiography with connectivity-preserving loss function |
| title_sort | semi supervised coronary vessels segmentation from invasive coronary angiography with connectivity preserving loss function |
| work_keys_str_mv | AT heh semisupervisedcoronaryvesselssegmentationfrominvasivecoronaryangiographywithconnectivitypreservinglossfunction AT banerjeea semisupervisedcoronaryvesselssegmentationfrominvasivecoronaryangiographywithconnectivitypreservinglossfunction AT beetzm semisupervisedcoronaryvesselssegmentationfrominvasivecoronaryangiographywithconnectivitypreservinglossfunction AT choudhuryrp semisupervisedcoronaryvesselssegmentationfrominvasivecoronaryangiographywithconnectivitypreservinglossfunction AT grauv semisupervisedcoronaryvesselssegmentationfrominvasivecoronaryangiographywithconnectivitypreservinglossfunction AT ieee semisupervisedcoronaryvesselssegmentationfrominvasivecoronaryangiographywithconnectivitypreservinglossfunction |