The increasing amount of medical imaging data acquired in clinical practice constitutes a vast database of untapped diagnostically relevant information. Today, only a small fraction of this information is used during clinical routine or for research due to its complexity, richness, high dimensionality, and size. Content-based image retrieval (CBIR) techniques have been proposed to access this information and to identify similar cases to assist radiologists in the clinical decision support process [2]. The segmentation of individual ventral cavity organs in CT scans is expected to improve the diagnostic accuracy and performance of CBIR systems. While the manual delineation of these organs is considered the gold standard, this is a tedious and very time-consuming process.


A fully automatic method for the segmentation of body organs in volumetric CT and MRI scans to support patient-specific automatic region of interest identification.


We have developed a new method for the automatic segmentation of multiple organs of the ventral cavity in CT scans. The method is based on a set of rules that determine the order in which the organs are isolated and segmented, from the simplest one to the most difficult one. First, the organs filled with air: the trachea and the lungs are segmented. Then, the organs with high blood content: the spleen, the kidneys and the liver, are segmented. Each organ is individually segmented with a generic four-step procedure consisting of: 1) Region of Interest Identification; 2) Thresholding; 3) 2D-seed identification; 4) Slice region growing clustering classification. Our method is unique in that it uses the same generic segmentation approach for all organs and in that it relies on the segmentation difficulty of organs to guide the segmentation process.


Experimental results on 20 CT scans of the VISCERAL Anatomy2 Challenge training datasets yield a Dice volume overlap similarity score of 81.4% for the trachea, 97.4% and 97.6% for the left and right lungs, 89.2% for the spleen, 92.8% and 90.2% for the left and right kidneys, respectively.  It ranked first for the trachea and the left and right kidney, and second for the liver and kidneys.

Participants: A. Spanier L. Biton, H. Weinfeld, L. Joskowicz, CASMIP Lab.

Publication: Rule-based ventral Cavity multi-organ automatic segmentation in CT scans. A. Spanier, L. Joskowicz. Proc. MICCAI 2014 Workshop on Medical Computer Vision: Algorithms for Big Data.

One-page description (pdf) >

2-Picture1 2-Picture2

Automatic segmentation of body organs in CT scans