.png){kind=icon}
Return
Automatic reorientation algorithm for myocardial perfusion SPECT using segmentation
.png){kind=icon}
PRE
AI
DOI：10.1111/eci.70016.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
BackgroundCardiac reorientation is a necessary step in processing myocardial perfusion images. This task usually requires manual intervention and thus introduces intra- and inter-operator variability in the processing workflow that may lead to reduced reproducibility of the results.MethodsA deep learning model was trained to perform segmentation of cardiac structures from SPECT images simulated from a real PET/CT dataset. Labels used for training were automatically generated in a semi-supervised fashion by using TotalSegmentator on CT images. Segmentation results from the trained model were used to calculate cardiac landmarks from which the cardiac axes were defined, and reorientation was performed. Automatic reorientation was compared against the manual reorientation defined by three expert nuclear cardiologists.ResultsThe average rotation difference between cardiac axes calculated from predicted segmentations and ground-truth segmentations was 5.3 degrees +/- 3.1 degrees on the simulated SPECT test dataset. In real SPECT images, the standard deviation of the angle difference between the automatic method and human experts was lower in all axes and operators compared to the maximum inter-operator standard deviation.ConclusionsThe proposed deep learning-based algorithm provides an automatic method to perform cardiac reorientation in myocardial perfusion SPECT images with an error range like the variability between operators and with the advantage of using objective anatomical landmarks for the definition of cardiac axes.
Keywords:
AI
automation
machine learning
myocardial perfusion imaging
reorientation
SPECT
Journal
IF:
3.6
Papers:
4.5K
Citations:
8.2K
Organization
View more organizations
Cited Papers
No cited papers available