Fully automated lumen and vessel contour segmentation in intravascular ultrasound datasets.

Blanco, Pablo J; Ziemer, Paulo G P; Bulant, Carlos A; Ueki, Yasushi; Bass, Ronald; Räber, Lorenz; Lemos, Pedro A; García-García, Héctor M (2022). Fully automated lumen and vessel contour segmentation in intravascular ultrasound datasets. Medical image analysis, 75, p. 102262. Elsevier 10.1016/j.media.2021.102262

[img] Text
Fully_automated.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (4MB)

Segmentation of lumen and vessel contours in intravascular ultrasound (IVUS) pullbacks is an arduous and time-consuming task, which demands adequately trained human resources. In the present study, we propose a machine learning approach to automatically extract lumen and vessel boundaries from IVUS datasets. The proposed approach relies on the concatenation of a deep neural network to deliver a preliminary segmentation, followed by a Gaussian process (GP) regressor to construct the final lumen and vessel contours. A multi-frame convolutional neural network (MFCNN) exploits adjacency information present in longitudinally neighboring IVUS frames, while the GP regression method filters high-dimensional noise, delivering a consistent representation of the contours. Overall, 160 IVUS pullbacks (63 patients) from the IBIS-4 study (Integrated Biomarkers and Imaging Study-4, Trial NCT00962416), were used in the present work. The MFCNN algorithm was trained with 100 IVUS pullbacks (8427 manually segmented frames), was validated with 30 IVUS pullbacks (2583 manually segmented frames) and was blindly tested with 30 IVUS pullbacks (2425 manually segmented frames). Image and contour metrics were used to characterize model performance by comparing ground truth (GT) and machine learning (ML) contours. Median values (interquartile range, IQR) of the Jaccard index for lumen and vessel were 0.913, [0.882,0.935] and 0.940, [0.917,0.957], respectively. Median values (IQR) of the Hausdorff distance for lumen and vessel were 0.196mm, [0.146,0.275]mm and 0.163mm, [0.122,0.234]mm, respectively. Also, the mean value of lumen area predictions, and limits of agreement were -0.19mm2, [1.1,-1.5]mm2, while the mean value and limits of agreement of plaque burden were 0.0022, [0.082,-0.078]. The results obtained with the model developed in this work allow us to conclude that the proposed machine learning approach delivers accurate segmentations in terms of image metrics, contour metrics and clinically relevant variables, enabling its use in clinical routine by mitigating the costs involved in the manual management of IVUS datasets.

Item Type:

Journal Article (Original Article)

Division/Institute:

04 Faculty of Medicine > Department of Cardiovascular Disorders (DHGE) > Clinic of Cardiology

UniBE Contributor:

Ueki, Yasushi, Räber, Lorenz

Subjects:

600 Technology > 610 Medicine & health

ISSN:

1361-8415

Publisher:

Elsevier

Language:

English

Submitter:

Nadia Biscozzo

Date Deposited:

21 Jan 2022 09:18

Last Modified:

05 Dec 2022 15:59

Publisher DOI:

10.1016/j.media.2021.102262

PubMed ID:

34670148

Uncontrolled Keywords:

Deep learning Gaussian process IVUS Lumen Segmentation Vessel

BORIS DOI:

10.48350/163272

URI:

https://boris.unibe.ch/id/eprint/163272

Actions (login required)

Edit item Edit item
Provide Feedback