Improving myocardium segmentation in cardiac CT angiography using spectral information

Abstract

Accurate segmentation of the left ventricle myocardium in cardiac CT angiography (CCTA) is essential for e.g. the assessment of myocardial perfusion. Automatic deep learning methods for segmentation in CCTA might suffer from differences in contrast-agent attenuation between training and test data due to non-standardized contrast administration protocols and varying cardiac output. We propose augmentation of the training data with virtual mono-energetic reconstructions from a spectral CT scanner which show different attenuation levels of the contrast agent. We compare this to an augmentation by linear scaling of all intensity values, and combine both types of augmentation. We train a 3D fully convolutional network (FCN) with 10 conventional CCTA images and corresponding virtual mono-energetic reconstructions acquired on a spectral CT scanner, and evaluate on 40 CCTA scans acquired on a conventional CT scanner. We show that training with data augmentation using virtual mono-energetic images improves upon training with only conventional images (Dice similarity coefficient (DSC) 0.895 ± 0.039 vs. 0.846 ± 0.125). In comparison, training with data augmentation using linear scaling improves the DSC to 0.890 ± 0.039. Moreover, combining the results of both augmentation methods leads to a DSC of 0.901 ± 0.036, showing that both augmentations lead to different local improvements of the segmentations. Our results indicate that virtual mono-energetic images improve the generalization of an FCN used for myocardium segmentation in CCTA images.

Deep learning from dual‐energy information for whole‐heart segmentation in dual‐energy and single‐energy non‐contrast‐enhanced cardiac CT

“…These structures were: LV myocardium, LV cavity, RV, LA, RA, ascending aorta, and pulmonary artery trunk until the first bifurcation. Initial reference segmentations were obtained using a previously described automatic method 28 , and medical students subsequently performed manual voxel-wise correction using 3D Slicer (3D Slicer 4.8.1, http://www.slicer.org). All reference segmentations were verified and if necessary corrected by a resident (RAPT, with 7 years of experience in cardiothoracic imaging).…”

Automated left ventricular myocardium segmentation using 3D deeply supervised attention U‐net for coronary computed tomography angiography; CT myocardium segmentation

“…by using virtual mono‐energetic images reconstruction upon 40 CCTA scans has achieved the best DSC of 90.1% ± 3.6% through a method combing 3D FCN with linear intensity scaling augmentation. There are also methods combining image modalities, for example, Mortazi et al have reported DSC 85% for LVM segmentation in CT using a multi‐planner deep CNN with adaptive fusion combining CT and MRI. Using voxel classification with CNN, Zreik et al .…”

A review of medical image data augmentation techniques for deep learning applications

“…trained a deep learning model for MRI reconstruction and were able to augment their data by undersampling the k‐space. A similar approach can be applied to images captured using a spectral (dual energy) CT scanner since two separate energy spectra are captured, these can be combined in different ways to produce different augmentations 171,172 . Omigbodun et al 173 .…”

“…A similar approach can be applied to images captured using a spectral (dual energy) CT scanner since two separate energy spectra are captured, these can be combined in different ways to produce different augmentations. 171,172 Omigbodun et al 173 also augmented images simulating different parameters available on a CT scanner, such as slice thickness or dose. Fig.…”