Format

Send to

Choose Destination
BMC Med Imaging. 2016 Mar 5;16:19. doi: 10.1186/s12880-016-0124-1.

Automatic segmentation of myocardium at risk from contrast enhanced SSFP CMR: validation against expert readers and SPECT.

Author information

1
Department of Clinical Physiology, Skåne University Hospital in Lund, Lund University, Lund, Sweden. jane.tufvesson@med.lu.se.
2
Department of Biomedical Engineering, Faculty of Engineering, Lund University, Lund, Sweden. jane.tufvesson@med.lu.se.
3
Department of Clinical Physiology, Skåne University Hospital in Lund, Lund University, Lund, Sweden. marcus.carlsson@med.lu.se.
4
Department of Clinical Physiology, Skåne University Hospital in Lund, Lund University, Lund, Sweden. aletras@hotmail.com.
5
Laboratory of Medical Informatics, School of Medicine, Aristotle University of Thessaloniki, Thessaloniki, Greece. aletras@hotmail.com.
6
Department of Clinical Physiology, Skåne University Hospital in Lund, Lund University, Lund, Sweden. henrik.engblom@med.lu.se.
7
Department of Cardiology, Henri Mondor Hospital, Creteil, France. jean-francois.deux@hmn.aphp.fr.
8
Department of Cardiology, Lund University, Lund, Sweden. sasha.koul@med.lu.se.
9
Department of Medicine, Karolinska Institutet, Karolinska University Hospital, Stockholm, Sweden. peder.sorensson@karolinska.se.
10
Department of Medicine, Karolinska Institutet, Karolinska University Hospital, Stockholm, Sweden. john.pernow@ki.se.
11
Department of Cardiology B, Oslo, University Hospital Ullevål and Faculty of Medicine, University of Oslo, Oslo, Norway. dan.atar@online.no.
12
Department of Cardiology, Lund University, Lund, Sweden. david.erlinge@med.lu.se.
13
Department of Clinical Physiology, Skåne University Hospital in Lund, Lund University, Lund, Sweden. hakan.arheden@med.lu.se.
14
Department of Clinical Physiology, Skåne University Hospital in Lund, Lund University, Lund, Sweden. einar.heiberg@med.lu.se.
15
Department of Biomedical Engineering, Faculty of Engineering, Lund University, Lund, Sweden. einar.heiberg@med.lu.se.

Abstract

BACKGROUND:

Efficacy of reperfusion therapy can be assessed as myocardial salvage index (MSI) by determining the size of myocardium at risk (MaR) and myocardial infarction (MI), (MSI = 1-MI/MaR). Cardiovascular magnetic resonance (CMR) can be used to assess MI by late gadolinium enhancement (LGE) and MaR by either T2-weighted imaging or contrast enhanced SSFP (CE-SSFP). Automatic segmentation algorithms have been developed and validated for MI by LGE as well as for MaR by T2-weighted imaging. There are, however, no algorithms available for CE-SSFP. Therefore, the aim of this study was to develop and validate automatic segmentation of MaR in CE-SSFP.

METHODS:

The automatic algorithm applies surface coil intensity correction and classifies myocardial intensities by Expectation Maximization to define a MaR region based on a priori regional criteria, and infarct region from LGE. Automatic segmentation was validated against manual delineation by expert readers in 183 patients with reperfused acute MI from two multi-center randomized clinical trials (RCT) (CHILL-MI and MITOCARE) and against myocardial perfusion SPECT in an additional set (n = 16). Endocardial and epicardial borders were manually delineated at end-diastole and end-systole. Manual delineation of MaR was used as reference and inter-observer variability was assessed for both manual delineation and automatic segmentation of MaR in a subset of patients (n = 15). MaR was expressed as percent of left ventricular mass (%LVM) and analyzed by bias (mean ± standard deviation). Regional agreement was analyzed by Dice Similarity Coefficient (DSC) (mean ± standard deviation).

RESULTS:

MaR assessed by manual and automatic segmentation were 36 ± 10% and 37 ± 11%LVM respectively with bias 1 ± 6%LVM and regional agreement DSC 0.85 ± 0.08 (n = 183). MaR assessed by SPECT and CE-SSFP automatic segmentation were 27 ± 10%LVM and 29 ± 7%LVM respectively with bias 2 ± 7%LVM. Inter-observer variability was 0 ± 3%LVM for manual delineation and -1 ± 2%LVM for automatic segmentation.

CONCLUSIONS:

Automatic segmentation of MaR in CE-SSFP was validated against manual delineation in multi-center, multi-vendor studies with low bias and high regional agreement. Bias and variability was similar to inter-observer variability of manual delineation and inter-observer variability was decreased by automatic segmentation. Thus, the proposed automatic segmentation can be used to reduce subjectivity in quantification of MaR in RCT.

CLINICAL TRIAL REGISTRATION:

NCT01379261. NCT01374321.

PMID:
26946139
PMCID:
PMC4779553
DOI:
10.1186/s12880-016-0124-1
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for BioMed Central Icon for PubMed Central
Loading ...
Support Center