MRI texture-based machine learning models for the evaluation of renal function on different segmentations: a proof-of-concept study

Abstract

Key points 1. Texture analysis based on coronal T2-weighted MR images could evaluate the renal function in patients with diabetes. 2. The All-K and LC-K outperformed other segmentation methods in the evaluation of renal function impairment. 3. The segmentation methods could affect the results of renal function evaluation and the integrity of the coronal slices was crucial for renal imaging texture analysis.

Keywords

• Chronic renal insufficiency
• Glomerular filtration rate
• Magnetic resonance imaging
• Texture analysis
• Machine learning