Key result
An automated CNN-based semantic segmentation method estimated left ventricular end-systolic and end-diastolic volumes from MR images with mean absolute errors of 14.688 mL and 19.222 mL, respectively.
Why the study?
Current clinical procedures for LV volume estimation from MR images rely on manual inspection by cardiologists, which is often a time-consuming process.
Can a convolutional neural network accurately estimate left ventricular volume from MR images?
Can a convolutional neural network accurately estimate left ventricular volume from MR images?
An automated CNN-based method can estimate left ventricular end-systolic and end-diastolic volumes from MR images with mean absolute errors of approximately 14.7 mL and 19.2 mL.
Supports technical feasibility of CNN LV volumetry on MR; leaves open prospective validation vs manual segmentation.
The left ventricle (LV) volume is a major indicator of heart disease. Current clinical procedure for volume estimation from magnetic resonance (MR) images include manual inspection by the experienced cardiologists, which is often a time-consuming process. This paper presents an automated method for LV volume estimation at two points in the time. The method consists of training a convolutional neural network (CNN) with the MR images from the Sunnybrook dataset. After that, the trained model is used to predict left ventricular segments in MR images from the Kaggle dataset. From predicted segments, the ventricular volumes at end-systole (ESV) and end-diastole (EDV) are calculated using numerical integration. The obtained results estimate the ESV and EDV with a mean absolute error of 14.688 and 19.222 mL, respectively.
No takes yet. Share an insight, caveat, or question.
Habijan et al. (2019) studied Heart disease. Automated CNN-based semantic segmentation was evaluated on Mean absolute error for end-systolic (ESV) and end-diastolic (EDV) volume estimation. An automated CNN-based semantic segmentation method estimated left ventricular end-systolic and end-diastolic volumes from MR images with mean absolute errors of 14.688 mL and 19.222 mL, respectively.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: