Skip to main content

Medical-image Analysis and Statistical Interpretation Lab

Multi-atlas Segmentation Enables Robust Multi-contrast MRI Spleen Segmentation for Splenomegaly

Posted by on Tuesday, November 1, 2016 in Abdomen Imaging, Multi-atlas Segmentation.

Yuankai Huo, Jiaqi Liu, Zhoubing Xu, Robert L. Harrigan, Albert Assad, Richard G. Abramson, Bennett A. Landman. “Multi-atlas Segmentation Enables Robust Multi-contrast MRI Spleen Segmentation for Splenomegaly” In Proceedings of the SPIE Medical Imaging Conference. Orlando, Florida, February 2017. Oral presentation.

Full Text:

Abstract

Multi-atlas segmentation has shown to be a promising approach for spleen segmentation. To deal with the registration errors between the heterogeneous abdominal CT images, the context learning method for performance level estimation (CLSIMPLE) method was previously proposed. However, the CLSIMPLE typically trains a single GMM from the entire heterogeneous training atlas set. Therefore, the estimated prior maps might not represent specific target images accurately. We propose an adaptive context learning SIMPLE (A-CLSIMPLE) to train the GMM adaptively using subsets of the training data with the subsets tailored for different target images. From the results, A-CLSIMPLE achieved more accurate spleen segmentation.

Flow chart of the four different MAS pipelines. Pipeline 1 conducts the label fusion without atlas selection. Pipeline 2 conducts the atlas selection using the SIMPLE statistical selection method. Pipeline 3 selects atlases which have the closer L to the target image. Pipeline 4 is the L-SIMPLE method, which combines the advantages in Pipelines 2 and 3. A spatial prior is derived using L to guide the statistical atlas selection procedure.
Flow chart of the four different MAS pipelines. Pipeline 1 conducts the label fusion without atlas selection. Pipeline 2 conducts the atlas selection using the SIMPLE statistical selection method. Pipeline 3 selects atlases which have the closer L to the target image. Pipeline 4 is the L-SIMPLE method, which combines the advantages in Pipelines 2 and 3. A spatial prior is derived using L to guide the statistical atlas selection procedure.