=Paper= {{Paper |id=Vol-1194/visceralISBI14-1 |storemode=property |title=Rule-Based Ventral Cavity Multi-Organ Automatic Segmentation in CT Scans |pdfUrl=https://ceur-ws.org/Vol-1194/visceralISBI14-1.pdf |volume=Vol-1194 }} ==Rule-Based Ventral Cavity Multi-Organ Automatic Segmentation in CT Scans== https://ceur-ws.org/Vol-1194/visceralISBI14-1.pdf

Rule-Based Ventral Cavity Multi-Organ Automatic
Segmentation in CT Scans

Assaf B. Spanier Leo Joskowicz
School of Eng. and Computer Science School of Eng. and Computer Science
The Hebrew Univ. of Jerusalem, Israel The Hebrew Univ. of Jerusalem, Israel
assaf.spanier@mail.huji.ac.il josko@cs.huji.ac.il

Abstract

We describe 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 sim-
plest one to the most difficult one. First, the body is isolated
from the background. Second, the trachea and the left and
right lungs are segmented based on their air content. Third,
the spleen and the kidneys – the organs with high blood con-
tent – are segmented. Finally, the kidney is segmented based
on the surrounding organs segmentation. Each organ is indi-
vidually segmented with a four-step procedure that consists
of: 1) definition of an inclusive region of interest; 2) identi-
fication of the largest axial cross-section slice; 3) removal of
background structures by morphological operations, and; 4)
3D region growing segmentation. 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 re-
sults on 15 CT scans of the VISCERAL Anatomy2 Challenge
training datasets yield a Dice volume overlap similarity score
of 79.1 for the trachea, 97.4 and 97.6 for the left and right
lungs, 89.2 for the spleen, and 92.8 for the left kidney. For
the 5 CT scans test datasets, the Dice scores are 97.9, 97.0,
85.6, 93.4 and 90.2, respectively. Our method achieved an
overall DICE score of 92.8 and was ranked first among the
five methods that participated in the challenge.

Copyright c by the paper’s authors. Copying permitted only for private and academic purposes.
In: O. Goksel (ed.): Proceedings of the VISCERAL Organ Segmentation and Landmark Detection Benchmark at
the 2014 IEEE International Symposium on Biomedical Imaging (ISBI), Beijing, China, May 1st , 2014
published at http://ceur-ws.org

16
Spanier and Joskowicz: Rule-Based Ventral Cavity Segmentation in CT

1 Introduction
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 research due to the complexity, richness, high dimen-
sionality, and data size [1].
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 which is impractical
for all but a few dozen datasets for research. Consequently, a plethora of methods for automatic
segmentation of ventral body cavity organs in CT scans have been proposed. Liver segmentation
methods are thoroughly summarized and reviewed by Mharib et al. [4]. Lungs segmentation from
CT scans has been addressed by Sluimer et al. [5]. Kidney segmentation methods are described
in Freiman et al [6]. While very different from each other, all these methods target a single organ
and do not use information about other organs’ segmentations. Thus, multi-organ segmentation
requires a specific method for each organ, which yields variable quality results and quickly becomes
unmanagable as the number of organs to be segmented grows. It is thus desirable to develop a
single, generic approach that can be customized for each organ and that uses the information about
other organs’ segmentations.
The rule-based approach to medical image segmentation calls for using each organ anatomical
context and prior knowledge about its location and its extension for enhancing, improving, and
automating the segmentation process. In this pipeline-oriented approach, the organs of interest
are successively extracted from the CT scan. Previous research has focused mainly on liver seg-
mentation [3]. In this paper, we extend and generalize the rule-based approach to the automatic
segmentation of multiple ventral cavity organs in CT scans.

2 Method
The basic premise of the rule-based paradigm is to sequentially extract different organs based on
prior information on the organs of interest and their characteristics in the CT scan. Simple and
context-free organs are segmented first, followed by more complex and context-based identfication
and delineation. Our proposed approach extends the established rule-based approach by providing
a unified, generic four-step approach that is customized for each organ and incorporates information
about other organs prior segmentations.

2.1 Generic organ segmentation framework
In our generic framework, the segmentation of each organ is performed in four successive steps
(Fig. 1):

1. Definition of the organ’s Binary Inclusive Region Of Interest (BI-ROI) based on the target
organ intensity values.

2. Identification of the organ’s Largest Axial Cross Section Slice (LACSS). This is the CT scan
slice where the organ has the largest axial area.

3. Removal of remaining background structures from the LACSS by morphological operations.

4. Organ segmentation by 3D region growing starting from the LACSS inside the BI-ROI.

17
Spanier and Joskowicz: Rule-Based Ventral Cavity Segmentation in CT

Figure 1: The four steps of the generic organ segmentation framework exemplified on the spleen.

We start with a preprocessing step that isolates the patient body from the background (air
and scan gantry) based on location and intensity values. The generic four-step framework is then
applied to the ventral body cavity organs in the following order. First, the breathing system organs
are segmented: the trachea and the left and right lungs. Next, the organs with high blood content
are segmented: the spleen, the liver, and the left and right kidneys. This organ segmentation
order prevents ambiguous assignment of the same image region to multiple organs, as previously
segmented image regions are excluded from the segmentation process. Due to space limitations, we
illustrate below each step for the breathing system only.

2.2 Breathing system segmentation

The breathing system consists of the trachea and the left and right lung.

Step 1: Definition of the BI-ROI: Binary Inclusive Region of Interest

We perform a simple thresholding with the Houndsfiel Unit (HU) of air and fat (< -500HU). This
results in a binary map consisting of air, fat, and other background structures. Then, the trachea
and the lungs are separated from the from the undesired surrounding fat by finding the the largest
connected component. The resulting structure includes the breathing system defines the trachea
and lungs BI-ROI (Fig. 2a). This BI-ROI is further refined for the trachea and the left and right
lungs.

Step 2: Identification of the LACSS: Largest Axial Cross Section Slice

The Largest Axial Cross Section Slice (LACSS) of the trachea and the lungs are identified by finding
the CT slices in the BI-ROI with the narrowest and widest perimeters, respectively (Figs. 2b and
2c). Note that the lungs slice contains two connected components, for the left and right lungs.

Step 3: Removal of background structures

No further background removal is required for the trachea and lungs, since the lungs LACSS contains
exactly two connected components corresponding to the left and right lungs and the trachea LACSS
contains exactly one connected component (Fig. 2).

18
Spanier and Joskowicz: Rule-Based Ventral Cavity Segmentation in CT

Figure 2: Illustration of the results of the first two steps of the generic organ segmentation frame-
work on the breathing system: a) Binary Inclusive Region of Interest; b) Largest Axial Cross
Section Slice plane for the trachea, and c) Largest Axial Cross Section Slice plane for the lungs.
Step 4: Segmentation by 3D region growing
The trachea and the left and right lungs are segmented by 3D region growing. The process starts
at the LACSS and proceeds to adjacent CT slices withing the volume defined by the BI-ROI.
First, the distance map between the LACSS contour (Fig 3a) and the adjacent slice (Fig 3b) is
computed, with the LACSS contour distance set to 0 (Fig 3c). Next, the adjacent slice and the
distance map are intersected to identify regions of high change (Fig 3d). In the resulting intersection,
we define a series of windows along the contour (Fig 3e) and compute the intensity histogram in each
window. Finally, windows whose histograms have a positive kurtosis are considered as segmentation
leakage, e.g. windows R1 and R2 in Fig 3e. These windows contain undesired structures whose
voxels are removed from the organ segmentation. Windows whose histograms have zero or negative
kurtosis, e.g. window R3 in Fig 3e, are considered smooth and are thus segmented as part of the
organ of interest. This process is repeated throughout the slices of the image until the number of
segmented pixels in the slice is below a predefined threshold.
The idea behind this step is that ventral cavity organs are relatively smooth, so two adjacent
slices of the same organ cannot exceed some level of variability. From a geometric point of view,
we constrain the expansion of the region growing boundary curve to have variable speed according
to the context. Our method takes into account the local geometry of the curvature: when the
magnitude of the curvature is above a predefined threshold, we stop its propagation and allow it to
continue only in low curvature regions. The rationale is once again that ventral body cavity organs
should preserve some level of smoothness constraint. The final result is the 3D segmentation of the
organ (Fig 4).

3 Experimental Results
We evaluated our method on two sets of scans of the VISCERAL Anatomy2 Challenge. The training
and test datasets consist of 15 and 5 CT clinical scans, respectively, acquired in 2004-08. Datasets
of patients younger than 18 years were not included following the recommendation of the local
ethical committee (S-465/2012, approval date Feb. 21th 2013). The CT scans in-plane resolution is
0.604-0.793/0.604-0.793mm; the in-between plane resolution is >=3mm. A VISCERAL team
radiologist manually produced ground-truth segmentations for each scan.
Table 1 summarizes the results for each type of dataset and organ: training and test datasets,
left lung, right lung, trachea, spleen and left kidney. Note that the DICE similarity coefficients
are high or very high, with a relatively small standard deviation. Our method achieved an overall
DICE score of 92.8 and was ranked first among the five methods that participated in the challenge.
Fig. 4 shows four representative examples of the multi-organ segmentation results.

19
Spanier and Joskowicz: Rule-Based Ventral Cavity Segmentation in CT

Figure 3: Illustration of step 4, 3D region growing, on the right lung: a) initial LACSS; b) adjacent
LACSS; c) distance map; d) intersection image of the adjacent LACSS and distance map, and e)
windows along the contour.

Training dataset Left Lung Right Lung Trachea Spleen Left Kidney
97.4 97.6 79.1 89.2 92.8
Test dataset Left Lung Right Lung Trachea Spleen Left Kidney
97.9 97.0 85.6 93.4 90.2

Table 1: Results: Mean Dice similarity coeffficient and standard deviation for the training and test
datasets on each organ.

Figure 4: Multi-organ segmentation results of four representative datasets of the VISCERAL
Anatomy2 Challenge.

4 Conclusions
We have developed a generic framework for the segmentation of ventral body cavity organs in CT
scans. Our approach consists of four-step pipeline method that takes into account prior information
about the locations of the organs and their appearance in CT scans. We have shown that the method
is applicable to a variety of ventral body cavity organs including the trachea, the left and right
lungs, the spleen, and the left kidney.
Current and future research is incorporating other structures, including the right kidney and the
liver. We are also extending the 3D region growing step to include different smoothing criteria in
different regions of the organ, to eliminate and avoid leakage to neighboring organs.

20
Spanier and Joskowicz: Rule-Based Ventral Cavity Segmentation in CT

References
[1] Langs G, Hanbury A, Menze B. VISCERAL: towards large data in medical imaging challenges
and directions. Proc. MICCAI LNCS: Medical Content-Based Retrieval for Clinical Decision
Support, pp 92-98, 2013.

[2] Rubin DL, Akgl CB, Napel S, Beaulieu CF, Greenspan H, Acar B. Content-based image retrieval
in radiology: current status and future directions. Journal of Digital Imaging, pp 24-32, 2011.

[3] Schmidt G. et al. Cognition network technology for a fully automated 3D segmentation of
the liver. Proc. MICCAI Workshop on 3D Segmentation in the Clinic: A Grand Challenge, pp
125-133, 2007.

[4] Mharib AM, Rahman A, Mashohor S, Binti R. Survey of liver CT image segmentation methods.
Artificial Intelligence Review, pp 37-42, 2012.

[5] Sluimer I, Schilham A, Prokop M, van Ginneken B. Computer analysis of computed tomography
scans of the lung: a survey. IEEE Transactions on Medical Imaging Vol 25(4), pp. 385, 2006.

[6] Freiman M, Kronman A, Esses SJ, Joskowicz L, Sosna J. Non-parametric iterative model
constraint graph min-cut for automatic kidney segmentation. Proc. MICCAI, LNCS 3217, pp.
73-80, 2010.