Automatic Segmentation of Coronary Lumen and External Elastic Membrane in Intravascular Ultrasound Images Using 8-layer U-Net
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
On 21 Jan, 2021
On 21 Jan, 2021
On 21 Jan, 2021
Posted 12 Jan, 2021
On 09 Jan, 2021
Received 06 Jan, 2021
Received 04 Jan, 2021
Received 03 Jan, 2021
On 02 Jan, 2021
On 30 Dec, 2020
On 30 Dec, 2020
Invitations sent on 30 Dec, 2020
On 30 Dec, 2020
On 30 Dec, 2020
On 30 Dec, 2020
On 13 Dec, 2020
Received 05 Dec, 2020
Received 30 Nov, 2020
On 29 Nov, 2020
Received 29 Nov, 2020
On 27 Nov, 2020
Received 27 Nov, 2020
On 26 Nov, 2020
On 26 Nov, 2020
Invitations sent on 26 Nov, 2020
On 26 Nov, 2020
On 26 Nov, 2020
On 26 Nov, 2020
On 20 Oct, 2020
Received 26 Sep, 2020
Received 26 Sep, 2020
Received 24 Sep, 2020
Received 24 Sep, 2020
Received 23 Sep, 2020
On 22 Sep, 2020
Received 21 Sep, 2020
On 19 Sep, 2020
On 18 Sep, 2020
On 17 Sep, 2020
Invitations sent on 17 Sep, 2020
On 17 Sep, 2020
On 17 Sep, 2020
On 17 Sep, 2020
On 16 Sep, 2020
On 16 Sep, 2020
On 29 Jul, 2020
On 29 Jul, 2020
On 28 Jul, 2020
On 28 Jul, 2020
On 27 Jul, 2020
Automatic Segmentation of Coronary Lumen and External Elastic Membrane in Intravascular Ultrasound Images Using 8-layer U-Net
On 21 Jan, 2021
On 21 Jan, 2021
On 21 Jan, 2021
Posted 12 Jan, 2021
On 09 Jan, 2021
Received 06 Jan, 2021
Received 04 Jan, 2021
Received 03 Jan, 2021
On 02 Jan, 2021
On 30 Dec, 2020
On 30 Dec, 2020
Invitations sent on 30 Dec, 2020
On 30 Dec, 2020
On 30 Dec, 2020
On 30 Dec, 2020
On 13 Dec, 2020
Received 05 Dec, 2020
Received 30 Nov, 2020
On 29 Nov, 2020
Received 29 Nov, 2020
On 27 Nov, 2020
Received 27 Nov, 2020
On 26 Nov, 2020
On 26 Nov, 2020
Invitations sent on 26 Nov, 2020
On 26 Nov, 2020
On 26 Nov, 2020
On 26 Nov, 2020
On 20 Oct, 2020
Received 26 Sep, 2020
Received 26 Sep, 2020
Received 24 Sep, 2020
Received 24 Sep, 2020
Received 23 Sep, 2020
On 22 Sep, 2020
Received 21 Sep, 2020
On 19 Sep, 2020
On 18 Sep, 2020
On 17 Sep, 2020
Invitations sent on 17 Sep, 2020
On 17 Sep, 2020
On 17 Sep, 2020
On 17 Sep, 2020
On 16 Sep, 2020
On 16 Sep, 2020
On 29 Jul, 2020
On 29 Jul, 2020
On 28 Jul, 2020
On 28 Jul, 2020
On 27 Jul, 2020
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