Kidney segmentation using 3D U-Net localized with Expectation Maximization
This work addresses kidney segmentation for renal disease assessment, but it is incremental as it adapts existing methods to specific MRI constraints.
The paper tackled the challenge of segmenting kidneys from 3D MRI data with small foreground objects and limited samples, achieving a Dice similarity coefficient of 0.88 on a dataset of n=196.
Kidney volume is greatly affected in several renal diseases. Precise and automatic segmentation of the kidney can help determine kidney size and evaluate renal function. Fully convolutional neural networks have been used to segment organs from large biomedical 3D images. While these networks demonstrate state-of-the-art segmentation performances, they do not immediately translate to small foreground objects, small sample sizes, and anisotropic resolution in MRI datasets. In this paper we propose a new framework to address some of the challenges for segmenting 3D MRI. These methods were implemented on preclinical MRI for segmenting kidneys in an animal model of lupus nephritis. Our implementation strategy is twofold: 1) to utilize additional MRI diffusion images to detect the general kidney area, and 2) to reduce the 3D U-Net kernels to handle small sample sizes. Using this approach, a Dice similarity coefficient of 0.88 was achieved with a limited dataset of n=196. This segmentation strategy with careful optimization can be applied to various renal injuries or other organ systems.