Axillary Lymph Nodes Evaluation

8/9/2019 Axillary Lymph Nodes Evaluation

1/9

KEVIN D. EVANS, PHD, RT, RDMS, RVS, FSDMS

STEFFEN SAMMET, MD, PHD

YVETTE RAMOS, RDMS, RVT

MICHAEL V. KNOPP, MD, PHD

The use of computer algorithms for the delin-

eation of anatomical structures or other regions of

interest (ROIs) is called image segmentation.1

Image segmentation is not a new evaluation tech-

nique, but the use has proliferated to provide more

information that is locked inside a medical image.

Segmenting a medical image can be extremely

helpful in quantifying tissue volumes, diagnosis,

localization of pathology, and the study of anatom-

ical structures.2–5

Unfortunately, image segmen-

tation has been conducted with only a limited

number of sonographic cases. Examples of suc-

cessful clinical research using image segmentation

of sonography images are those determining heel

density, ovarian cysts, breast cysts, and fetal, liver,

and cardiac pathology.6–15

The ability to segment anatomic and patho-

logic information from an image is only possible

because of the composition of voxels. Extracting

From The Ohio State University, School of Allied Medical

Professions, Columbus, Ohio.

Correspondence: Kevin D. Evans, PhD, RT, RDMS, RVS,

FSDMS, The Ohio State University, School of Allied Medical

Professions, 410 W. 10th Avenue, 340 A. Atwell Hall, Columbus, OH

43210. E-mail: [email protected].

The authors thank GE Healthcare Ultrasound for providing the

equipment, transducers, and software to conduct this research.

DOI: 10.1177/8756479308324954

JDMS 24:329-336 November/December 2008 329

ImageSegmentation

for Evaluating Axillary Lymph

Nodes

A review is provided of the literature that has

been published on image segmentation relative

to sonography. Manual and automatic techniques

for partitioning a sonogram are highlighted. In

addition, a preliminary set of results is provided

on the interrater reliability of the manual

segmentation of axillary lymph nodes that havebeen sonographically imaged. A correlation

between sonographers conducting manual

segmentation is very high (r = 0.9 with P < .00 at

the .01 alpha level). This work is set to provide

additional information on lymph node cubic

volume and the agreement between manual and

automatic segmentation of axillary lymph nodes.

Key words: image segmentation, breast sono-

graphy, axillary lymph nodes

RESEARCH ARTICLES


2/9

330 JOURNAL OF DIAGNOSTIC MEDICAL SONOGRAPHY November/December 2008 VOL. 24, NO. 6

information from within the image is done by

partitioning the image into nonoverlapping,

homogeneous regions based on the intensity of

reflected acoustic energy. The clinical applica-tion of image segmentation has yielded a number

of more effective techniques for conducting this

process with sonograms. The following image

segmentation techniques are commonly used

with sonograms: textural classifiers, manual

interaction to place ROIs, and deformable mod-

els.1

A brief description is provided of the image

segmentation techniques that were considered for

this feasibility study.

Segmentation Methods

1. Textural classifiers

• Clustering: Clustering is a form of textural clas-

sifying that depends on training data. In essence,

the algorithm trains itself during the data analy-

sis process.1

Once the region on the image is

selected for extraction, the pixels within the

extracted area are evaluated for a mean intensity,

and subsequent segmentations are made based

on finding like mean intensities.16

2. Regions of interest

• Region growing: Region growing requires thata manual interaction be made with the image

and a “seed” placed in the area of interest. The

algorithm moves outward from the seed to

encompass voxels that are of like intensity and

extracts them for the background image.1

3. Deformable models: Deformable models are a

graphic representation of elastic theory that

permits graphic molding around a selected voxel

composition and deforms by responding to

energy internally.17

Deformable models can be

manual or automated. Obviously, the reliability

and consistency of automated deformable modelsare ideal to reduce bias and time.

17

• The “snake” is the most popular deform-

able model that has been used for image

segmentation.18

• Level-set segmentation allows a 3D image

volume set to be extracted using a deformable

surface model and adjusts throughout the

volume.

Literature Review

Mammography is an imaging modality in which

segmentation techniques have been used exten-sively. In this area of research, a combination of

multiple image segmentation techniques has been

evaluated. An early study that was conducted with

2D digital mammography used segmentation of

breast tumors in two steps.19

In this study, regions of

interest were first extracted after a histogram was

created, based on the frequency of pixel magnitude.

The pixel frequency spanned a range of intensities

from 70 to 120. Those pixel magnitudes that were

greater than the threshold were deemed to be the

breast tissue. After breast tissue was isolated, amodified Markov random field model was used to

separate the tumor based on the extremely high

pixel value that exceeded the typical breast tissue

pixel density. Markov random field (MRF) models

are considered advanced segmentation techniques,

and this low-level model is based on the individual

behavior of pixels relative to one another in the

matrix.20

MRF models are classified as a form of

clustering.21

These sets of segmentation steps were

able to successfully isolate minimal breast cancers

that were<

10 mm.Another landmark study in this area was con-

ducted to extract morphologic features of malig-

nant and benign breast masses. This study used a

combination of clustering, a deformable model,

and a hybrid technique called speculation detec-

tion stages.22

One of the problems with this study

was the need to digitize the film to begin the

process of extraction. This allows the possibility of

noise in the image and degrades the ability to dis-

cretely assess the pixels within the selected region.

Breast imaging has embraced the use of com-

puter-aided detection (CAD) software specifically

developed for digital mammography. CAD makes

use of layers of analysis that are focused on spe-

cific ROIs and classifies them for potential pathol-

ogy. CAD’s primary function is to reduce the

false-positive diagnoses that are made during

breast imaging. CAD makes use of image analysis

techniques that aid in making a diagnosis. The first


3/9

layer of analysis is contrast enhancement, and the

next progressive layer is optimal image segmenta-

tion.23

In studies to develop optimum segmenta-

tion methods for CAD, an unsupervised Gaussianmixture method model and a hidden MRF model

developed by Zang et al.24

were used. These ana-

lytical models were fused with a template of

model images that represent normal pixel densi-

ties. The template model was considered a super-

vised test that was used to find the optimum

segmentation maneuver to accentuate the CAD

diagnosis. The study used 400 digital mammo-

grams to determine the best mix of segmentation

strategies with the CAD program. The result of the

experiment demonstrated that a supervised seg-mentation method, as developed by Zang et al.,

24

was a superior technique for CAD.23

This study

was based on 2D images and building a system

that was sensitive to gray-scale pixel differences.

Calcifications in breast tissue also have been

explored as a target for image segmentation and

enhancement during the use of CAD. An experi-

ment was conducted using 260 single-view film

screen mammograms that were digitized and ready

for CAD. In addition, image segmentation was per-

formed using symmlet wavelet and a new techniquecalled the “donut filter.”

25ROIs were placed over

the 138 benign calcifications and 122 microcalcifi-

cations, and the signals that emanated from these

particular pixels were used to cue segmentation.

The study provided promising results and should be

replicated with images from a variety of digitizers

as well as digital mammography. The researchers

also felt that other clinical applications could be

found for this type of 2D image segmentation.

Level-set segmentation, a specific method used

with 3D volume image sets, can be affected by

inherent noise from the imaging technique. The

problem with noisy images within a 3D volume set

is that smoothing or enhancing the data causes dis-

tortion of the anatomy, which has been targeted for

segmentation. The trick is to find a method that

strikes a balance between 3D resolution and inher-

ent digital noise. The use of level-set segmentation

relies on a surface-fitting strategy that helps in

dealing with small-scale noise from the modality

and smoothes the intensity of the signal fluctua-

tions in the volume data.26

There are many

deformable models for segmenting 3D volume

data. Using an implicit model, which specifies thesurface as a level set and allows for the variation

descending through the volume, would be ideal.27

This allows the data set to be defined by the

deformable surface and vary dynamically over

time. An additional concern is that volume data

sets are collected in the X, Y, and Z planes. The Z

plane has the lowest resolution due to data being

collected in the axial direction. The introduction of

this kind of inherent noise can be the source of

inaccuracy within the targeted anatomy for seg-

mentation. A group of researchers dealt with thisproblem by using multiple sets of scans on an

object and merging them prior to segmentation.

This hybrid image volume set was composed of

individually higher resolution planes of informa-

tion. The use of level-set segmentation on a hybrid

3D image volume was conducted using a magnetic

resonance (MR) scan of a mouse embryo, a laser

scan of a figurine, and an MR scan of a zucchini.26

The result was a high-resolution level-set model

that contained all the significant features of the

original scan for all three items. Because sonogra-phy is traditionally considered an imaging modal-

ity fraught with a certain level of digital noise, this

segmentation technique could be quite helpful.

Work conducted in Japan with image segmenta-

tion used 3D volume sets with the intent to better

plan breast cancer surgeries.28,29

The 3D images

were created from volume-rendered 2D sonograms

and manually selected ROIs chosen from a his-

togram of pixel intensities. These 3D models were

created while the patient was prepared for surgery.

Creating these segmented models of the tumor

helped to direct the surgeon to minimize the amount

of tissue removed while maintaining appropriate

borders. This work demonstrated the translational

value of working with segmentation of 3D breast

images and the potential to minimize the invasive-

ness of surgery.

Previous research that has been conducted with

the segmentation of sonographic images has

demonstrated the value of increasing our diagnostic

IMAGE SEGMENTATION FOR EVALUATING AXILLARY LYMPH NODES / Evans et al 331


4/9


capability and assisting the radiologist with addi-

tional diagnostic data. The evaluation of axillary

lymph nodes has yet to be demonstrated with this

set of imaging techniques, and the feasibility of creating these images remains to be explored. To

fill this gap in the literature, we devised a feasibil-

ity study to explore the use of a manual technique

for segmenting the sonographic voxel density of

axillary lymph nodes.

Materials and Methods

Image segmentation has been used more exten-

sively with computed tomography (CT), magnetic

resonance imaging (MRI), and now digital mam-mography. These techniques have developed in

response to the increasing ability to capture large

volume sets of imaging information. Data sets

have varied anatomic and pathologic information

that may need to be located and segmented away

for the larger data set. A robust set of maneuvers is

needed to determine the coordinates of the item

that will be segmented away from the background

image. Predominately, sonography images are

captured in 2D frames that are composed of pixels.

This can limit the ability to accurately capture animage’s boundaries for segmentation. A volume

set of image data, which is provided with 3D sono-

graphic imaging, provides more digital informa-

tion but has added complexities for conducting

accurate image segmentation.

Presently, the focus of this research team

has been an attempt to use both manual and auto-

mated deformable models (snakes and level sets) to

determine the best method for conducting segmenta-

tion of axillary lymph nodes. Attempts have been

made to perform automated image segmentation

with an existing data set to provide either a pixel

count or a voxel count. The secondary data segmen-

tation with automated techniques was attempted on

the following sample images:

a. A 2D lymph node with color Doppler imaging

b. A 2D lymph node without color Doppler imaging

c. A 3D lymph node with color Doppler imaging

d. A 3D lymph node without color Doppler imaging

In addition, a manual deformable model of image

segmentation was used to provide a voxel count

on a sample 3D lymph node image without color

Doppler imaging (see Figure 1). Unfortunately,

these attempts were not successful, in part, because

these images were not collected for this expressed

purpose. A fresh data collection was needed

to properly determine the feasibility of thesetechniques to isolate lymph nodes from surrounding

breast tissue.

PROTOCOL FOR SEGMENTATION

The proposal was to use normal female volunteers

to allow for a collection of images of lymph nodes in

the axilla. This allowed for a manual segmentation

with a sonographic transducer that was specifically

built to make volume measurements and segment the

image at the time it was collected. The TRU

3D/Vocal transducer setup was provided by GeneralElectric Healthcare along with a GE Logic 9

(Milwaukee, Wisconsin). This equipment allowed

the segmentation to be done manually using the

deformable model techniques. The Institutional

Review Board of Ohio State University approved this

project. The number of volunteers was set at 40 to

achieve a moderate effect size of .5 at an alpha of .05

with a power of .59.

FIGURE 1. 3D axillary lymph node image with color Doppler

that was problematic for automatic image segmentation.


5/9

Each normal female volunteer consented to

have 20 minutes of diagnostic medical sonogra-

phy, and after three lymph nodes were imaged in

volume sets, they were dismissed. The volume sets

of lymph node images were then manually

segmented using the deformable model snake (see

Figures 2–5). Once the images had been through

the segmentation process, a cubic volume was

determined, and the voxel density was determined

mathematically. All the images were de-identified

and retained on a flash drive that was kept in a

locked office and used only for transferring the

volume data sets to Dr. Sammet’s computer lab for

future automated processing.


FIGURE 2. Image segmentation of an axillary lymph node

using the deformable model snake technique.

FIGURE 3. Larger, more oval node segmented with a

deformable model snake technique.

FIGURE 4. Small node that would be classified as abnormal

and the model created with the snake technique.

FIGURE 5. Image segmentation of a small node with image

optimization prior to manual segmentation.


6/9


Results

Preliminary results are provided on 23 partici-

pants who provided a total of 45 lymph nodes forevaluation. The mean age of these 23 participants is

24 years of age, with the hope that younger partic-

ipants would provide more normal-shaped nodes

free of inflammatory or chronic disease changes.

One of the key initiatives at this juncture in the

research was to use these 45 lymph nodes for

manual segmentation but to check for interrater

reliability. The principal investigator (KE) and the

application specialist sonographer (YR) worked

independently to perform manual image segmen-

tation for each node. The resulting 3D model thatwas created was recorded and the cubic volume

compared for consistency. A mean cubic volume

of .28 m3

(SD .26) was determined for the 45

nodes that were manually segmented by the prin-

cipal investigator. The application specialist pro-

vided a mean cubic volume of .31 m3

(SD .27) for

those nodes that she manually segmented.

The Pearson correlation coefficient was chosen

to determine the statistical correlation of measures

that were made by the two sonographers per node.

The set of nodes was compared between sonogra-phers, according to the order in which the nodes

were captured (node 1, node 2, and node 3). For

node 1 in the series, the correlation coefficient was

r = 0.91, which indicates a very high positive cor-

relation between the sonographers’ measurements

for all those first nodes segmented in the series.

The statistical significance of this agreement was

P < .00 at the .01 alpha level. The scatterplot for

those manually segmented nodal volumes is

depicted in Figure 6. For node 2 in the series, the

correlation coefficient was r = 0.97, which indi-

cates a very high positive correlation between the

sonographers’ measurements for all those second

nodes segmented in the series. The statistical sig-

nificance of this agreement was P < .00 at the .01

alpha level. The scatterplot for those manually

segmented nodal volumes is depicted in Figure 7.

For node 3 in the series, the correlation coefficient

was r = 0.99, which again indicates a very high

positive correlation between the sonographers’

measurements for all those third nodes segmented

in the series. The statistical significance of this

agreement was P < .00 at the .01 alpha level. The

scatterplot for those manually segmented nodalvolumes is depicted in Figure 8.

Discussion

The very high correlation between the sonogra-

phers’ measurements for manual segmentation of

the axillary lymph nodes imaged is a promising

FIGURE 6. Scatterplot of the manual segmentation of the

cubic volume of the first axillary lymph node imaged.


cubic volume of the second axillary lymph node imaged.


7/9

early result for the continuation of this research.

One criticism of manual segmentation is that the

variability of the models is attributed to the opera-

tor; however, this does not appear to be a factor in

the research that we are conducting. The scatter-

plots are highly effective tools that can be used to

look for those nodal volumes that do not line up

close to 1.0. These may be nodes that need to bereviewed to determine what caused the sonogra-

phers to disagree on their method of manual

segmentation of the cubic volume.

The impact of this research will be boosted by

securing all 40 volunteers and completing the man-

ual segmentation of axillary lymph nodes that are

visualized. Once these nodes are segmented, the

data set will be segmented automatically using

automated level sets or region-growing algorithms.

Interestingly, a study was done using a mixed

model of image segmentation in which sonographic

images were partitioned using a method of outlining

the contour of the image, with the automated region-

growing technique completing the segmentation.30

The software was “trained” to be more accurate by

incorporating the contour outlines provided by the

operator. In this study, the gallbladder and kidney

were the organs segmented on sample sonograms.

In addition, segmentation with both automated

and manual techniques was conducted with

sonographic breast lesions in a study of 400 sono-

grams that spanned a variety of pathologies.31

The

researchers concluded that automated and manual

segmentation were similar in their ability to con-sistently delineate borders of breast masses. The

next phase of the current research will be to com-

plete a comparison between automated and man-

ual segmentation with the existing data set. The

limitations inherent with a feasibility study of this

size are that the results are unique and may not

generalize to a larger population.

Conclusion

Continued use of manual segmentation withsonographic images will help build a body of evi-

dence-based research and promote translational

implementation. The next specific aim is not only

to demonstrate consistency with segmenting

lymph nodes but also to compute the normal mean

volume of a lymph node. This will allow the

research team to compute the number of voxels

that are expected to comprise a node’s normal

cubic volume.

References 1. Pham D, Xu C, Prince J: A survey of current methods in

medical image segmentation. Ann Rev Biomed Eng

2000;2:315–337.

2. Larie S, Abukmeil S: Brain abnormality in schizophre-

nia: a systematic and quantitative review of magnetic res-

onance imaging studies. Br J Psychiarty 1998;172:

110–120.

3. Taylor P: Invited review: computer aids for decision-

making in diagnostic radiology—A literature review. Br

J Radiol 1995;68:945–957.

4. Zijdenbos A, Dawant B: Brain segmentation and white

matter lesion detection in MRI images. Crit Rev Biomed

Eng 1994;22:401–465.5. Worth A, Makris N, Caviness V, Kennedy D: Neuroana-

tomical segmentation of MRI: technological objectives.

Int J Patt Recog Art Intell 1997;11:1161–1187.

6. Zimmerand Y, Tepper R, Akselrod S: A two-dimensional

extension of minimum cross entropy thresholding for the

segmentation of ultrasound images. Ultrasound Med Biol

1996;22:1183–1190.

7. Coppini G, Poli R, Valli G: Recovery of the 3-D shape of

the left ventricle from echocardiographic images. IEEE

Trans Med Imaging 1995;14:301–317.



cubic volume of the third axillary lymph node imaged.


8/9


8. Sebbahi A, Herment A, deCessare A, Mousseaux E:

Multimodality cardiovascular image segmentation using

a deformable contour model. Comput Med Imaging

Graphics 1997;21:79–89.9. Jones T, Metaxas D: Segmentation using deformable

models with affinity-based localization. Lect Notes

Comput Sci 1997;1205:53–62.

10. Kucera D, Martin R: Segmentation of sequences of

echocardiographic images using a simplified 3D active

contour model with region based external forces. Comput

Med Imaging Graphics 1997;21:1–21.

11. Lefebvre F, Berger G, Laugier P: Automatic detection of

the boundary of the calcaneus from ultrasound paramet-

ric imaging using an active contour model: clinical

assessment. IEEE Trans Med Imaging 1998;17:45–52.

12. Caselles V, Catte F, Coll T, Dibos F: A geometric model

for active contours. Numerishche Mathematik 1993;66:

1–31.

13. Pathak S, Chalana V, Kim Y: Interactive automatic fetal

head measurements from ultrasound images using multi-

media computer technology. Ultrasound Med Biol

1997;23:665–673.

14. Yezzi A, Kichenassamy S, Kumar A, Oliver P, Tannenbaum

A: A geometric snake model for segmentation of medical

imagery. IEEE Trans Med Imaging 1997;16:199–209.

15. Kadah Y, Farag A, Zurada A, Badawi A, Youssef A:

Classification algorithms for quantitative tissue charac-

teristics of diffuse liver disease from ultrasound images.

IEEE Trans Med Imaging 1996;15:466–478.

16. Jain A, Dubes R: Algorithms for Clustering Data.

Englewood Cliffs, NJ: Prentice Hall; 1988.17. McInerney T, Terzopoulos D: Deformable models in

medical image analysis: a survey. Med Image Anal 1996;

1:91–108.

18. Kass M, Witkin A, Terzopoulos D: Snakes: active con-

tour models. Int J Comp Vision 1988;1:321–331.

19. Kalleergi M, Clarke L, Jain V: Markov random field for

tumor detection in digital mammography. IEEE Trans

Med Imaging 1995;14:565–576.

20. Farag A, Ahmed M, E-Baz A, Hassan H: Advanced seg-

mentation techniques, in Suri J,Wilson D, Laxminarayan S

(eds): Handbook of Biomedical Image Analysis:

Segmentation Models: Part A. Vol. 1. New York, Kluwer

Academic/Plenum, 2005, pp 479–533.

21. Pappas T: An adaptive clustering algorithm for image

segmentation. IEEE Trans Signal Processing 1995;40:

902–914.

22. Sahiner B, Chan H, Petrick N, Helvie M, Hadjiiski L:Improvement of mammographic mass characterization

using speculation measures and morphological features.

Am Assoc Physicists Med 2001;28:1455–1465.

23. Singh S, Bovis K: A knowledge-based scheme for digital

mammography, in Suri J, Wilson D, Laxminarayan S

(eds): Handbook of Biomedical Image Analysis:

Segmentation Models: Part B. Vol. 2. New York: Kluwer

Academic/Plenum, 2005, pp 591–660.

24. Zang Y, Brady M, Smith S: Segmentation of brain MR

images through a hidden Markov random field model and

the expectation minimization algorithm. IEEE Trans Med

Imaging 2001;20:45–57.

25. Kallergi M, Heine J, Tembey M: Computer-aided diag-

nosis of mammographic calcification clusters: impact of

segmentation, in Suri J, Wilson D, Laxminarayan S (eds):

Handbook of Biomedical Image Analysis: Segmentation

Models: Part B. Vol. 2. New York: Kluwer Academic/

Plenum, 2005, pp 707–751.

26. Breen D,Whitaker R, Museth K, Zhukov L: Level set seg-

mentation of biological volume datasets, in Suri J, Wilson

D, Laxminarayan S (eds): Handbook of Biomedical

Image Analysis: Segmentation Models: Part A. Vol. 1.

New York, Kluwer Academic/Plenum, 2005, pp 415–533.

27. Osher S, Sethian J: Fronts propagating with curvature

dependent speed: algorithms based on Hamilton-Jacobi

formulations. J Comp Phys 1988;79:12–49.

28. Sato Y, Nakamoto M, Tamaki Y, et al: Image guidance of breast cancer surgery using 3-D ultrasound images and

augmented reality visualization. IEEE Trans Med

Imaging 1998;17:681–693.

29. Inoue T, Tamaki Y, Sato Y, et al: Three dimensional ultra-

sound imaging of breast cancer by a real-time intraoper-

ative navigation system. Breast Cancer (Japan) 2005;12:

122–129.

30. Levienaise-Obadia B, Gee A: Adaptive segmentation of

ultrasound images. Image Vision Comp 1999;17:

583–588.

31. Horsch K, Giger M, Venta L, Vyborny C: Automatic

segmentation of breast lesions on ultrasound. Med Phys

2001;28:1652–1659.


9/9

Documents

Axillary Lymph Nodes Evaluation