Engineering, 2013, 5, 326-331 Published Online Octob er 2013 (
Copyright © 2013 SciRes. ENG
Contrast Limited Adaptive Histogram Equalization for
Qualitative Enhancem ent of Myocardial Perfusion Imag es
Neethu M. Sasi, V. K. Jayasree
Govt. Model Engineering College, Cochin University of Science and Technology, Thrikkakkara, Kerala, India
Email: neeth u msasi@g mail .co m, ja yasreevk@g mail .co m
Received May 2013
This paper establishes an efficient color space for the contrast enhancement of myocardial perfusion images. The effects
of histogram equalization and contrast limited adaptive histogram equalization are investigated and the one which gives
good enhancement results is extended to the suitable color space. The color space which gives better results is chosen
experimentally. Uniq ueness of this work is that contrast li mited adaptive histogra m equalizatio n technique is applied to
the chrominance channels of the cardiac nuclear image, leaving the luminance channel unaffected which results in an
enha nced image o utput in color space.
Keywords: Myocardial Perfusion Images; Single Photon Emission Computed Tomography; Histogram Equaliz a tion
1. Introduction
Medical i maging app lies a lot o f digital ima ge pr ocessin g
techniques for better interpretation. Different enhance-
ment techniques are available in literature for improving
the quality of medical images. The major challenge in
this area is that a specific algorithm which gives better
results for a particular type of application may fail in
giving good results for another type of application. Dif-
ferent popular imaging modalities are now available for
detecting cardiac disorders. This work mainly concen-
trates on color images obtained from Single Photon Emi-
ssion Computed Tomography (SPECT) systems which
are designed to analyze the functioning of the heart [1].
This work is meant for improving the pictorial represen-
tation of the above mentioned images, thus providing a
more accurate diagnosis of cardiac abnormalities.
One of the many purposes of taking nuclear heart scan
is to check the blood flow to the heart muscle. If the heart
muscle is not getting enough blood it may be a sign of
coronary heart disease. When a nuclear heart scan is
done for this purpose, it is called myocardial perfusion
scanning [2].
Different image enhancement techniques are available
in the literature [3]. Primarily, an image enhancement
technique is done to process an image so that the result-
ing image gives more visual information than the o riginal
image. Nuclear medicine images suffer from a large
amount of blur. A few studies are available in literature
regarding the enhancement of nuclear images. A method
of enhancement of noisy planar nuclear images using
mean field annealing was proposed by Falk et al. [4].
Wang et al. uses a combined technique of mean field
annealing and gradient edge detection to extract the
boundary of left ventricle in [5]. The work discussed so
far focused on gray scale images.
Contrast limited adaptive histogram equalization have
been successfully proven to be effective in biomedical
image analysis. Pisano et al. proposed contrast limited
adaptive histogram equalization for detecting abnormali-
ties in dense mammograms in [ 6].
This work presents the effect of contrast limited adap-
tive histogram equalization techniques on myocardial
perfusion images in color space. The paper is organized
as follows. T he basic histogram equalization tec hnique is
presented and it discusses abo ut contra st limited ad aptive
histogra m equalizatio n. The method suitable for myocar-
dial images is explained and the experimental results are
analyzed and finally the paper is concluded.
2. Histogram Equalization
Histogram equalization is one of the well-known en-
hancement techniques. In histogram equalization [3], the
dynamic range and contrast of an image is modified by
altering the image such that its intensity histogram has a
desired shape. This is achieved by using cumulative dis -
tribution functio n as the mapping function. The intensity
levels are changed such that the peaks of the histogram
are stretched and the troughs are compressed. If a digital
image has N pixels distributed in L discrete intensity le-
vels and nk is the number of pixels with intensity level ik
Copyright © 2013 SciRes. ENG
and then the probability density function (PDF) of the
image is given by Equation (1). The cumulative density
functi on (C DF) i s defined in Equati on (2).
fi N
() ()
kk ij
Fi fi
Though this method is simple, it fails in myocardial
nuclear images since the gray values are physically far
apart from each other in the image. Due to this reason,
histogram equalization gives very poor result for myo-
cardial images.
3. Contrast Limited Adaptive Histogram
In contrast limited histogram equalization (CLHE), the
histogram is cut at some threshold and then equalization
is applied. Contrast limited adaptive histogram equaliza-
tion (CLAHE) is an adaptive contrast histogram equali-
zation method [7-10], where the contrast of an image is
enhanced by applying CLHE on small data regions called
tiles rather than the entire image. The resulting neigh-
boring tiles are then stitched back seamlessly using bili-
near interpolation. The contrast in the homogeneous re-
gion can be limited so that noise amplification can be
4. Contrast Limited Adaptive Histogram
Equalization for Myocardial Perfusion
Images in Color Space
In this method, the image which is read in RGB space is
converted into the color space with a luminance (Y) and
two c hro mina nce c o mpo nents (Cb, Cr) b y us ing t he r ela-
tion given in Equation (3).
1665.481 128.55324.966
12837.79774.203 112.000
128112.00093.786 18.214
Cb G
Cr B
 
 
= +−−
 
 
 
The two chrominance channels are separated and for
each chrominance channel the number of rectangular
contextual tiles into which the image is divided is ob-
tained. The optimal value for this is decided experimen-
tally. Uniform distribution is used as the basis for creat-
ing the contrast trans for m function. Let ic_min and ic_max be
the minimum and maximum permissible intensity levels
and the optimal value of this clip limit is also set. Let
Fk(ic_in) be the cumulative distribution function for input
contextual tile ic_in. Then the expression of the modified
chrominance channel tile with uniform distribution is
given in Equation (4). The flowchart for the method is
given in Figure 1.
__max _min__min
*( )
c outcckc inc
5. Experimental Results
The algorith m described in Section 4 has been applied to
myocardial perfusion images obtained from a SPECT
device. Nuclear image data sets from ten different pa-
tients, including both normal and abnormal, have been
tested with the pr op osed algorith m in the follo w up exp e-
riments. This paper has included a few images and their
results following the enhancements. The original myo-
cardial image is given in Figure 2. The histogram of the
image can be seen in Figure 3. The equalized histogram
by using simple histogram equalization is given in Fig-
Figure 1 . Enhancement method for cardia c SPECT image.
Copyright © 2013 SciRes. ENG
Figure 2 . Original cardiac S PECT image.
Figure 3 . Histogram of the image shown in Figure 2.
ure 4 and the correspondingly processed image is shown
in Figure 5. The loss of information due to over en-
hancement is evident if we compare the original image in
Figure 2 and the enhanced image in Figure 5.
The proposed method extracts the chrominance chan-
nels from the original image. Then each channel is di-
vided into rectangular tiles of size 32 × 32 and the clip
limit is set at 0.01. The above parameters have been cho-
Copyright © 2013 SciRes. ENG
Figure 4. Equalized histogram.
Figure 5 . Image after simple histogram equalization.
sen by conducting experiments using different image
datasets of the same type. Better histogram equalization
is obtained by the method described in Section 4 using
the said parameters. The contrast of the image has regis-
tere d an i mpr o ve me nt wit ho ut loss in i n fo r mation as s ee n
in the result in Figure 6. The histogram of the enhanced
image by the proposed method is given in Figure 7.
Comparing Figure 2, Figure 5 and Figure 6, it can be
concluded that the proposed method provides better en-
hancement conserving image data inte grity.
Figure 8 shows a stress-rest portion of the SPECT
image. The result o f simple histogram eq ualization is giv-
en in Figure 9 . The result of applying proposed extension
of CLAHE is given in Figure 10 . The resul t in Figure 10
concludes that the extended method of CLAHE gives
better enhancement for cardiac SPECT images in color
6. Conclusion
The paper investigates the effect of histogram enhance-
ment techniques on myocardial perfusion images from
SPECT scan devices. Due to wide difference in intensity
values, simple hi stogram equalization fa ils in these types
of images as shown in Figure 5 and Figure 9. The si m-
ple histogram method suffers from intensity saturation
which results i n infor mation l oss which is not acce ptable
in the case of medical images. Visually appreciable re-
Copyright © 2013 SciRes. ENG
Figure 6 . Processed i mage using propos ed algorit hm.
Figure 7 . Histogram of the image shown in Figure 6.
Figure 8. A portion of SPECT image showing stress and
rest condit ions of the heart.
Figure 9 . Image after si mple histogram equalization.
Copyright © 2013 SciRes. ENG
Figure 1 0. Processed image through prop osed algorit hm.
sults with image data integrity are obtained by extendin g
CLAHE method to suitable color space containing chro-
minance and luminance components. This technique ef-
fectively improves the visual interpretation of these types
of images thereby ensuring a more accurate guidance to
the post-diagnostic procedures in cardiac ailments.
[1] M. T. M adsen , “Recent Advan ces in Spect Imagin g,” The
Journal of Nuclear Medicine, Vol. 48, No. 4, 2007, pp.
[2] S. Burrell and A. MacDonald, “Artifacts And Pitfalls in
Myocardial Perfusion Imaging,” Journal of Nuclear
Medicine Technology, Vol. 34, No. 4, 200 6, pp . 193-211.
[3] R. C. Gonzalez, R. E. Woods and S. L. Eddins, “Digital
Image Pro cessing,” 2nd Edition, Pearson Education, New
Jersey, 2002.
[4] D.L. Falk, D. M. Rubin and T. Marwala, “Enhancement
of Noisy Planar Nuclear Medicine Images Using Mean
Field Annealing,” World Congress on Medical Physics
and Biomedical Engineering, IFMBE Proceedings, Vol . 4,
Track 14, Korea, 2006, pp. 2415-2418.
[5] C. X. Wang, L. Small, W. E. Snyder and R. Williams,
“Edge Detection in Gated Cardiac Nuclear Medicine Im-
ages,” IEEE 7th Symposium on Computer Based Medical
Systems, Winston-Salem, 10-12 June 1994, pp. 28-33.
[6] E. D. Pisano, S. Zong, B. M. Hemminger, M . DeLuca, R .
E. Johnston, K. Muller, M. P. Braeuning and S. M. Pizer,
“Contrast Limited Adaptive Histogram Equalization Im-
age Processing to Improve the Detection of Simulated
Spiculations in Dense Mammograms,” Journal of Digit
Imaging, Vol. 11, N o. 4, 1998, pp. 193-200.
[7] R. Garg, B. Mittal and S. Garg, “Histogram Equalization
Techniques for Image Enhancement,” International Jour-
nal of Electronics and Communication Technology, Vol.
2, No. 1, 2011, pp. 107-111.
[8] S. Srinivasan an d N. Balram, “Adaptive Contrast En-
hancement Using Local Region Stretching,” Proceedings
of ASID ’06, New Delhi, 8-12 Octobe r 20 06, pp. 152-155.
[9] S. K. Shome and S. R. K. Vadali, “Enhancement of Di-
abetic Retinopathy Imagery Using Contrast Limited Ada-
ptive Histogram Equalization,” International Journal of
Computer Science and Information Technologies, Vol. 2,
No. 6, 2011, pp. 2694-2699.
[10] J. A Stark, “Adaptive Image Contarst Enhancement Using
Generalizations of Histogram Equalization,” IEEE Tran-
sactions on Image Processing, Vol. 9, No. 5, 2000, pp.