This preprint is under consideration at BioMedical Engineering OnLine. A preprint is a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Research
Automatic Segmentation of Coronary Lumen and External Elastic Membrane in Intravascular Ultrasound Images Using 8-layer U-Net
Jianping Xiang
ArteryFlow Techology Co., Ltd.
Corresponding Author
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Background: Intravascular ultrasound (IVUS) is the golden standard in accessing the coronary lesions, stenosis, and atherosclerosis plaques. In this paper, a fully-automatic approach by an 8-layer U-Net is developed to segment the coronary artery lumen and the area bounded by external elastic membrane (EEM), i.e. cross section area (EEM-CSA). The database comprises of single-vendor and single-frequency IVUS data. Particularly, the proposed data augmentation of MeshGrid combined with flip and rotation operations is implemented, improving the model performance without pre- or post-processing of the raw IVUS images.
Results: The mean intersection of union (mIoU) of 0.937 and 0.804 for the lumen and EEM-CSA respectively were achieved, which exceeded the manual labeling accuracy of the clinician. Conclusion: The accuracy shown by the proposed method is sufficient for subsequent reconstruction of 3D IVUS images, which is essential for doctors’ diagnosis in the tissue characterization of coronary artery walls and plaque compositions, qualitatively and quantitatively.
Keywords
IVUS, Coronary, Segmentation, Lumen, EEM, MeshGrid, U-Net.
Figure 1
Figure 2
Figure 3
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Under Review
Version 4
Posted 12 Jan, 2021
No community comments so far
Editorial decision: Minor revision
On 09 Jan, 2021
Review #3 received
Received 06 Jan, 2021
Review #1 received
Received 04 Jan, 2021
Review #2 received
Received 03 Jan, 2021
Reviewer #3 agreed
On 02 Jan, 2021
Reviewer #2 agreed
On 30 Dec, 2020
Editor assigned
On 30 Dec, 2020
Reviewers invited
Invitations sent on 30 Dec, 2020
Reviewer #1 agreed
On 30 Dec, 2020
Submission checks complete
On 30 Dec, 2020
Editor invited
On 30 Dec, 2020
No comments provided
Editorial decision: Major revision
On 13 Dec, 2020
Review #4 received
Received 05 Dec, 2020
Review #2 received
Received 30 Nov, 2020
Reviewer #4 agreed
On 29 Nov, 2020
Review #1 received
Received 29 Nov, 2020
Reviewer #3 agreed
On 27 Nov, 2020
Review #3 received
Received 27 Nov, 2020
Reviewer #2 agreed
On 26 Nov, 2020
Editor assigned
On 26 Nov, 2020
Reviewers invited
Invitations sent on 26 Nov, 2020
Reviewer #1 agreed
On 26 Nov, 2020
Submission checks complete
On 26 Nov, 2020
Editor invited
On 26 Nov, 2020
No comments provided
Editorial decision: Major revision
On 20 Oct, 2020
Review #3 received
Received 26 Sep, 2020
Review #5 received
Received 26 Sep, 2020
Review #2 received
Received 24 Sep, 2020
Review #4 received
Received 24 Sep, 2020
Review #6 received
Received 23 Sep, 2020
Reviewer #6 agreed
On 22 Sep, 2020
Review #1 received
Received 21 Sep, 2020
Reviewer #5 agreed
On 19 Sep, 2020
Reviewer #4 agreed
On 18 Sep, 2020
Editor assigned
On 17 Sep, 2020
Reviewers invited
Invitations sent on 17 Sep, 2020
Reviewer #1 agreed
On 17 Sep, 2020
Reviewer #2 agreed
On 17 Sep, 2020
Reviewer #3 agreed
On 17 Sep, 2020
Submission checks complete
On 16 Sep, 2020
Editor invited
On 16 Sep, 2020
No comments provided
Editor assigned
On 29 Jul, 2020
Editorial decision: Revise before peer review
On 29 Jul, 2020
Submission checks complete
On 28 Jul, 2020
Editor invited
On 28 Jul, 2020
First submitted
On 27 Jul, 2020
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Biomedical Engineering
Learn more about our company.
This preprint is under consideration at BioMedical Engineering OnLine. A preprint is a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Research
Automatic Segmentation of Coronary Lumen and External Elastic Membrane in Intravascular Ultrasound Images Using 8-layer U-Net
Jianping Xiang
ArteryFlow Techology Co., Ltd.
Corresponding Author
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Under Review
Version 4
Posted 12 Jan, 2021
No community comments so far
Editorial decision: Minor revision
On 09 Jan, 2021
Review #3 received
Received 06 Jan, 2021
Review #1 received
Received 04 Jan, 2021
Review #2 received
Received 03 Jan, 2021
Reviewer #3 agreed
On 02 Jan, 2021
Reviewer #2 agreed
On 30 Dec, 2020
Editor assigned
On 30 Dec, 2020
Reviewers invited
Invitations sent on 30 Dec, 2020
Reviewer #1 agreed
On 30 Dec, 2020
Submission checks complete
On 30 Dec, 2020
Editor invited
On 30 Dec, 2020
No comments provided
Editorial decision: Major revision
On 13 Dec, 2020
Review #4 received
Received 05 Dec, 2020
Review #2 received
Received 30 Nov, 2020
Reviewer #4 agreed
On 29 Nov, 2020
Review #1 received
Received 29 Nov, 2020
Reviewer #3 agreed
On 27 Nov, 2020
Review #3 received
Received 27 Nov, 2020
Reviewer #2 agreed
On 26 Nov, 2020
Editor assigned
On 26 Nov, 2020
Reviewers invited
Invitations sent on 26 Nov, 2020
Reviewer #1 agreed
On 26 Nov, 2020
Submission checks complete
On 26 Nov, 2020
Editor invited
On 26 Nov, 2020
No comments provided
Editorial decision: Major revision
On 20 Oct, 2020
Review #3 received
Received 26 Sep, 2020
Review #5 received
Received 26 Sep, 2020
Review #2 received
Received 24 Sep, 2020
Review #4 received
Received 24 Sep, 2020
Review #6 received
Received 23 Sep, 2020
Reviewer #6 agreed
On 22 Sep, 2020
Review #1 received
Received 21 Sep, 2020
Reviewer #5 agreed
On 19 Sep, 2020
Reviewer #4 agreed
On 18 Sep, 2020
Editor assigned
On 17 Sep, 2020
Reviewers invited
Invitations sent on 17 Sep, 2020
Reviewer #1 agreed
On 17 Sep, 2020
Reviewer #2 agreed
On 17 Sep, 2020
Reviewer #3 agreed
On 17 Sep, 2020
Submission checks complete
On 16 Sep, 2020
Editor invited
On 16 Sep, 2020
No comments provided
Editor assigned
On 29 Jul, 2020
Editorial decision: Revise before peer review
On 29 Jul, 2020
Submission checks complete
On 28 Jul, 2020
Editor invited
On 28 Jul, 2020
First submitted
On 27 Jul, 2020
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Subject Areas
Biomedical Engineering
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Background: Intravascular ultrasound (IVUS) is the golden standard in accessing the coronary lesions, stenosis, and atherosclerosis plaques. In this paper, a fully-automatic approach by an 8-layer U-Net is developed to segment the coronary artery lumen and the area bounded by external elastic membrane (EEM), i.e. cross section area (EEM-CSA). The database comprises of single-vendor and single-frequency IVUS data. Particularly, the proposed data augmentation of MeshGrid combined with flip and rotation operations is implemented, improving the model performance without pre- or post-processing of the raw IVUS images.
Results: The mean intersection of union (mIoU) of 0.937 and 0.804 for the lumen and EEM-CSA respectively were achieved, which exceeded the manual labeling accuracy of the clinician. Conclusion: The accuracy shown by the proposed method is sufficient for subsequent reconstruction of 3D IVUS images, which is essential for doctors’ diagnosis in the tissue characterization of coronary artery walls and plaque compositions, qualitatively and quantitatively.
Figure 1
Figure 2
Figure 3