Comparison of automatic liver volumetry performance using different types of magnetic resonance images

Measurements of liver volume from MR images can be valuable for both clinical and research applications. Automated methods using convolutional neural networks have been used successfully for this using a variety of different MR image types as input. In this work, we sought to determine which types of magnetic resonance images give the best performance when used to train convolutional neural networks for liver segmentation and volumetry. Abdominal MRI scans were performed at 3 Tesla on 42 adolescents with obesity. Scans included Dixon imaging (giving water, fat, and T2* images) and low-resolution T2-weighted scout images. Multiple convolutional neural network models using a 3D U-Net architecture were trained with different input images. Whole-liver manual segmentations were used for reference. Segmentation performance was measured using the Dice similarity coefficient (DSC) and 95% Hausdorff distance. Liver volume accuracy was evaluated using bias, precision, intraclass correlation coefficient, normalized root mean square error (NRMSE), and Bland-Altman analyses. The models trained using both water and fat images performed best, giving DSC = 0.94 and NRMSE = 4.2%. Models trained without the water image as input all performed worse, including in participants with elevated liver fat. Models using the T2-weighted scout images underperformed the Dixon-based models, but provided acceptable performance (DSC ≥ 0.92, NMRSE ≤6.6%) for use in longitudinal pediatric obesity interventions. The model using Dixon water and fat images as input gave the best performance, with results comparable to inter-reader variability and state-of-the-art methods.