Knowledge of whole heart anatomy is a prerequisite for many clinical applications. Whole heart segmentation (WHS), which delineates substructures of the heart, can be very valuable for modeling and analysis of the anatomy and functions of the heart. However, automating this segmentation can be challenging due to the large variation of the heart shape, and different image qualities of the clinical data. To achieve this goal, an initial set of training data is generally needed for constructing priors or for training. Furthermore, it is difficult to perform comparisons between different methods, largely due to differences in the datasets and evaluation metrics used. This manuscript presents the methodologies and evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction with MICCAI 2017. The challenge provided 120 three-dimensional cardiac images covering the whole heart, including 60 CT and 60 MRI volumes, all acquired in clinical environments with manual delineation. Ten algorithms for CT data and eleven algorithms for MRI data, submitted from twelve groups, have been evaluated. The results showed that the performance of CT WHS was generally better than that of MRI WHS. The segmentation of the substructures for different categories of patients could present different levels of challenge due to the difference in imaging and variations of heart shapes. The deep learning (DL)-based methods demonstrated great potential, though several of them reported poor results in the blinded evaluation. Their performance could vary greatly across different network structures and training strategies. The conventional algorithms, mainly based on multi-atlas segmentation, demonstrated good performance, though the accuracy and computational efficiency could be limited. The challenge, including provision of the annotated training data and the blinded evaluation for submitted algorithms on the test data, continues as an ongoing benchmarking resource via its homepage (www.sdspeople.fudan.edu.cn/zhuangxiahai/0/mmwhs/).

Many methods have been proposed for tissue segmentation in brain MRI scans. The multitude of methods proposed complicates the choice of one method above others. We have therefore established the MRBrainS online evaluation framework for evaluating (semi)automatic algorithms that segment gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) on 3T brain MRI scans of elderly subjects (65–80 y). Participants apply their algorithms to the provided data, after which their results are evaluated and ranked. Full manual segmentations of GM, WM, and CSF are available for all scans and used as the reference standard. Five datasets are provided for training and fifteen for testing. The evaluated methods are ranked based on their overall performance to segment GM, WM, and CSF and evaluated using three evaluation metrics (Dice, H95, and AVD) and the results are published on the MRBrainS13 website. We present the results of eleven segmentation algorithms that participated in the MRBrainS13 challenge workshop at MICCAI, where the framework was launched, and three commonly used freeware packages: FreeSurfer, FSL, and SPM. The MRBrainS evaluation framework provides an objective and direct comparison of all evaluated algorithms and can aid in selecting the best performing method for the segmentation goal at hand.

To define and evaluate coronary contrast opacification gradients using prospectively ECG-gated single heart beat 320-detector row coronary angiography (CTA). Thirty-six patients with normal coronary arteries determined by 320 x 0.5-mm detector row coronary CTA were retrospectively evaluated with customized image postprocessing software to measure Hounsfield Units at 1-mm intervals orthogonal to the artery center line. Linear regression determined correlation between mean Hounsfield Units and distance from the coronary ostium (regression slope defined as the distance gradient G(d)), lumen cross-sectional area (G(a)), and lumen short-axis diameter (G(s)). For each gradient, differences between the 3 coronary arteries were analyzed with ANOVA. Linear regression determined correlations between measured gradients, heart rate, body mass index, and cardiac phase. To determine feasibility in lesions, all 3 gradients were evaluated in 22 consecutive patients with left anterior descending artery lesions > or =50% stenosis. For all 3 coronary arteries in all patients, the gradients G(a) and G(s) were significantly different from zero (P0.503). The distance gradient G(d) demonstrated nonlinearities in a small number of vessels and was significantly smaller in the right coronary artery when compared with the left coronary system (P<0.001). Gradient variations between cardiac phases, heart rates, body mass index, and readers were low. Gradients in patients with lesions were significantly different (P<0.021) than in patients considered normal by CTA. Measurement of contrast opacification gradients from temporally uniform coronary CTA demonstrates feasibility and reproducibility in patients with normal coronary arteries. For all patients, the gradients defined with respect to the coronary lumen cross-sectional area and short-axis diameters are highly linear, not significantly influenced by the coronary artery (left anterior descending artery versus left circumflex versus right coronary artery), and have only small variation with respect to patient parameters. Preliminary evaluation of gradients across coronary artery lesions is promising but requires additional study.

Subscription and open access journals from SAGE Publishing, the world's leading independent academic publisher.