The Lazy Luna software enabled automatic multilevel comparison of ventricular function quantification, demonstrating an average Dice similarity coefficient of 91.9% for all images between two expert readers.
Observational (n=13)
No
Does Lazy Luna software accurately automate the multilevel comparison of ventricular function quantification in CMR imaging?
Lazy Luna provides a feasible, automated software solution for multilevel comparison of CMR segmentations and clinical results, facilitating both clinical training and convolutional neural network development.
Cardiovascular magnetic resonance imaging is the gold standard for cardiac function assessment. Quantification of clinical results (CR) requires precise segmentation. Clinicians statistically compare CRs to ensure reproducibility. Convolutional Neural Network developers compare their results via metrics. Aim: Introducing software capable of automatic multilevel comparison. A multilevel analysis covering segmentations and CRs builds on a generic software backend. Metrics and CRs are calculated with geometric accuracy. Segmentations and CRs are connected to track errors and their effects. An interactive GUI makes the software accessible to different users. The software's multilevel comparison was tested on a use case based on cardiac function assessment. The software shows good reader agreement in CRs and segmentation metrics (Dice > 90%). Decomposing differences by cardiac position revealed excellent agreement in midventricular slices: > 90% but poorer segmentations in apical (> 71%) and basal slices (> 74%). Further decomposition by contour type locates the largest millilitre differences in the basal right cavity (> 3 ml). Visual inspection shows these differences being caused by different basal slice choices. The software illuminated reader differences on several levels. Producing spreadsheets and figures concerning metric values and CR differences was automated. A multilevel reader comparison is feasible and extendable to other cardiac structures in the future.
Hadler et al. (Fri,) conducted a observational in Cardiac function assessment (n=13). Lazy Luna software vs. Manual segmentation by expert readers was evaluated on Average Dice similarity coefficient for all images. The Lazy Luna software enabled automatic multilevel comparison of ventricular function quantification, demonstrating an average Dice similarity coefficient of 91.9% for all images between two expert readers.