Right ventricular endocardial segmentation in CMR images using a novel inter-modality statistical shape modelling approach

Concetta Piazzese; M. Chiara Carminati; Rolf Krause; Angelo Auricchio; Lynn Weinert; Gloria Tamborini; Mauro Pepi; Roberto M. Lang; Enrico G. Caiani

doi:10.22489/cinc.2016.026-356

Right ventricular endocardial segmentation in CMR images using a novel inter-modality statistical shape modelling approach

Concetta Piazzese, M. Chiara Carminati, Rolf Krause, Angelo Auricchio, Lynn Weinert, Gloria Tamborini, Mauro Pepi, Roberto M. Lang, Enrico G. Caiani

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Statistical shape modelling (SSM) approaches have been proposed as a powerful tool to segment the left ventricle in cardiac magnetic resonance (CMR) images. Our aim was to extend this method to segment the RV cavity in CMR images and validate it compared to the conventional gold-standard (GS) manual tracing. A SSM of the RV was built using a database of 4347 intrinsically 3D surfaces, extracted from transthoracic 3D echo cardiographic (3DE) images of 219 retrospective patients. The SSM was then scaled and deformed on the base of some features extracted, with different strategies, from each short-axis plane until a stable condition was reached. The proposed approach, tested on 14 patients, resulted in a high correlation (r²=0.97) and narrow limits of agreement (± 17% error) when comparing the semiautomatic volumes to the GS, confirming the accuracy of this approach in segmenting the RV endocardium.

Original language	English
Title of host publication	Computing in Cardiology Conference, CinC 2016
Editors	Alan Murray
Publisher	IEEE Computer Society
Number of pages	4
Volume	43
ISBN (Electronic)	9781509008957
ISBN (Print)	9781509008964
DOIs	https://doi.org/10.22489/cinc.2016.026-356
Publication status	Published - 11 Sep 2016
Externally published	Yes
Event	43rd Computing in Cardiology Conference - Vancouver, Canada Duration: 11 Sep 2016 → 14 Sep 2016 Conference number: 43 http://www.cinc2016.org/ https://www.cinc.org/past-computing-in-cardiology-conferences/ https://www.cinc.org/archives/2016/ (Full program)

Publication series

Name	Computing in Cardiology
Volume	43
ISSN (Print)	2325-8861
ISSN (Electronic)	2325-887X

Conference

Conference	43rd Computing in Cardiology Conference
Abbreviated title	CinC 2016
Country/Territory	Canada
City	Vancouver
Period	11/09/16 → 14/09/16
Internet address	http://www.cinc2016.org/ https://www.cinc.org/past-computing-in-cardiology-conferences/ https://www.cinc.org/archives/2016/ (Full program)

Access to Document

10.22489/cinc.2016.026-356Licence: CC BY

Cite this

Piazzese, C., Carminati, M. C., Krause, R., Auricchio, A., Weinert, L., Tamborini, G., Pepi, M., Lang, R. M., & Caiani, E. G. (2016). Right ventricular endocardial segmentation in CMR images using a novel inter-modality statistical shape modelling approach. In A. Murray (Ed.), Computing in Cardiology Conference, CinC 2016 (Vol. 43). [7868685] (Computing in Cardiology; Vol. 43). IEEE Computer Society. https://doi.org/10.22489/cinc.2016.026-356

@inproceedings{a6e63a392fda47e69ce6741c4687444a,

title = "Right ventricular endocardial segmentation in CMR images using a novel inter-modality statistical shape modelling approach",

abstract = "Statistical shape modelling (SSM) approaches have been proposed as a powerful tool to segment the left ventricle in cardiac magnetic resonance (CMR) images. Our aim was to extend this method to segment the RV cavity in CMR images and validate it compared to the conventional gold-standard (GS) manual tracing. A SSM of the RV was built using a database of 4347 intrinsically 3D surfaces, extracted from transthoracic 3D echo cardiographic (3DE) images of 219 retrospective patients. The SSM was then scaled and deformed on the base of some features extracted, with different strategies, from each short-axis plane until a stable condition was reached. The proposed approach, tested on 14 patients, resulted in a high correlation (r2=0.97) and narrow limits of agreement (± 17% error) when comparing the semiautomatic volumes to the GS, confirming the accuracy of this approach in segmenting the RV endocardium.",

keywords = "Three-dimensional displays, Image segmentation, Computational modelling, Shape, Manuals, Solid modeling, Valves",

author = "Concetta Piazzese and Carminati, {M. Chiara} and Rolf Krause and Angelo Auricchio and Lynn Weinert and Gloria Tamborini and Mauro Pepi and Lang, {Roberto M.} and Caiani, {Enrico G.}",

year = "2016",

month = sep,

day = "11",

doi = "10.22489/cinc.2016.026-356",

language = "English",

isbn = "9781509008964",

volume = "43",

series = "Computing in Cardiology",

publisher = "IEEE Computer Society",

editor = "Alan Murray",

booktitle = "Computing in Cardiology Conference, CinC 2016",

address = "United States",

note = "43rd Computing in Cardiology Conference, CinC 2016 ; Conference date: 11-09-2016 Through 14-09-2016",

url = "http://www.cinc2016.org/, https://www.cinc.org/past-computing-in-cardiology-conferences/, https://www.cinc.org/archives/2016/",

}

Piazzese, C, Carminati, MC, Krause, R, Auricchio, A, Weinert, L, Tamborini, G, Pepi, M, Lang, RM & Caiani, EG 2016, Right ventricular endocardial segmentation in CMR images using a novel inter-modality statistical shape modelling approach. in A Murray (ed.), Computing in Cardiology Conference, CinC 2016. vol. 43, 7868685, Computing in Cardiology, vol. 43, IEEE Computer Society, 43rd Computing in Cardiology Conference, Vancouver, British Columbia, Canada, 11/09/16. https://doi.org/10.22489/cinc.2016.026-356

Right ventricular endocardial segmentation in CMR images using a novel inter-modality statistical shape modelling approach. / Piazzese, Concetta; Carminati, M. Chiara; Krause, Rolf et al.

Computing in Cardiology Conference, CinC 2016. ed. / Alan Murray. Vol. 43 IEEE Computer Society, 2016. 7868685 (Computing in Cardiology; Vol. 43).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Right ventricular endocardial segmentation in CMR images using a novel inter-modality statistical shape modelling approach

AU - Piazzese, Concetta

AU - Carminati, M. Chiara

AU - Krause, Rolf

AU - Auricchio, Angelo

AU - Weinert, Lynn

AU - Tamborini, Gloria

AU - Pepi, Mauro

AU - Lang, Roberto M.

AU - Caiani, Enrico G.

N1 - Conference code: 43

PY - 2016/9/11

Y1 - 2016/9/11

N2 - Statistical shape modelling (SSM) approaches have been proposed as a powerful tool to segment the left ventricle in cardiac magnetic resonance (CMR) images. Our aim was to extend this method to segment the RV cavity in CMR images and validate it compared to the conventional gold-standard (GS) manual tracing. A SSM of the RV was built using a database of 4347 intrinsically 3D surfaces, extracted from transthoracic 3D echo cardiographic (3DE) images of 219 retrospective patients. The SSM was then scaled and deformed on the base of some features extracted, with different strategies, from each short-axis plane until a stable condition was reached. The proposed approach, tested on 14 patients, resulted in a high correlation (r2=0.97) and narrow limits of agreement (± 17% error) when comparing the semiautomatic volumes to the GS, confirming the accuracy of this approach in segmenting the RV endocardium.

AB - Statistical shape modelling (SSM) approaches have been proposed as a powerful tool to segment the left ventricle in cardiac magnetic resonance (CMR) images. Our aim was to extend this method to segment the RV cavity in CMR images and validate it compared to the conventional gold-standard (GS) manual tracing. A SSM of the RV was built using a database of 4347 intrinsically 3D surfaces, extracted from transthoracic 3D echo cardiographic (3DE) images of 219 retrospective patients. The SSM was then scaled and deformed on the base of some features extracted, with different strategies, from each short-axis plane until a stable condition was reached. The proposed approach, tested on 14 patients, resulted in a high correlation (r2=0.97) and narrow limits of agreement (± 17% error) when comparing the semiautomatic volumes to the GS, confirming the accuracy of this approach in segmenting the RV endocardium.

KW - Three-dimensional displays

KW - Image segmentation

KW - Computational modelling

KW - Shape

KW - Manuals

KW - Solid modeling

KW - Valves

UR - http://www.scopus.com/inward/record.url?scp=85016131728&partnerID=8YFLogxK

U2 - 10.22489/cinc.2016.026-356

DO - 10.22489/cinc.2016.026-356

M3 - Conference contribution

AN - SCOPUS:85016131728

SN - 9781509008964

VL - 43

T3 - Computing in Cardiology

BT - Computing in Cardiology Conference, CinC 2016

A2 - Murray, Alan

PB - IEEE Computer Society

T2 - 43rd Computing in Cardiology Conference

Y2 - 11 September 2016 through 14 September 2016

ER -

Piazzese C, Carminati MC, Krause R, Auricchio A, Weinert L, Tamborini G et al. Right ventricular endocardial segmentation in CMR images using a novel inter-modality statistical shape modelling approach. In Murray A, editor, Computing in Cardiology Conference, CinC 2016. Vol. 43. IEEE Computer Society. 2016. 7868685. (Computing in Cardiology). doi: 10.22489/cinc.2016.026-356

Right ventricular endocardial segmentation in CMR images using a novel inter-modality statistical shape modelling approach

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint