Abstract: Image compression is one of the most important
applications Digital Image Processing. Advanced medical imaging
requires storage of large quantities of digitized clinical data. Due to
the constrained bandwidth and storage capacity, however, a medical
image must be compressed before transmission and storage. There
are two types of compression methods, lossless and lossy. In Lossless
compression method the original image is retrieved without any
distortion. In lossy compression method, the reconstructed images
contain some distortion. Direct Cosine Transform (DCT) and Fractal
Image Compression (FIC) are types of lossy compression methods.
This work shows that lossy compression methods can be chosen for
medical image compression without significant degradation of the
image quality. In this work DCT and Fractal Compression using
Partitioned Iterated Function Systems (PIFS) are applied on different
modalities of images like CT Scan, Ultrasound, Angiogram, X-ray
and mammogram. Approximately 20 images are considered in each
modality and the average values of compression ratio and Peak
Signal to Noise Ratio (PSNR) are computed and studied. The quality
of the reconstructed image is arrived by the PSNR values. Based on
the results it can be concluded that the DCT has higher PSNR values
and FIC has higher compression ratio. Hence in medical image
compression, DCT can be used wherever picture quality is preferred
and FIC is used wherever compression of images for storage and
transmission is the priority, without loosing picture quality
diagnostically.
Abstract: In this paper we investigate the watermarking authentication when applied to medical imagery field. We first give an overview of watermarking technology by paying attention to fragile watermarking since it is the usual scheme for authentication.We then analyze the requirements for image authentication and integrity in medical imagery, and we show finally that invertible schemes are the best suited for this particular field. A well known authentication method is studied. This technique is then adapted here for interleaving patient information and message authentication code with medical images in a reversible manner, that is using lossless compression. The resulting scheme enables on a side the exact recovery of the original image that can be unambiguously authenticated, and on the other side, the patient information to be saved or transmitted in a confidential way. To ensure greater security the patient information is encrypted before being embedded into images.
Abstract: For about two decades scientists have been
developing techniques for enhancing the quality of medical images
using Fourier transform, DWT (Discrete wavelet transform),PDE
model etc., Gabor wavelet on hexagonal sampled grid of the images
is proposed in this work. This method has optimal approximation
theoretic performances, for a good quality image. The computational
cost is considerably low when compared to similar processing in the
rectangular domain. As X-ray images contain light scattered pixels,
instead of unique sigma, the parameter sigma of 0.5 to 3 is found to
satisfy most of the image interpolation requirements in terms of high
Peak Signal-to-Noise Ratio (PSNR) , lower Mean Squared Error
(MSE) and better image quality by adopting windowing technique.
Abstract: Discrete Wavelet Transform (DWT) has demonstrated
far superior to previous Discrete Cosine Transform (DCT) and
standard JPEG in natural as well as medical image compression. Due
to its localization properties both in special and transform domain,
the quantization error introduced in DWT does not propagate
globally as in DCT. Moreover, DWT is a global approach that avoids
block artifacts as in the JPEG. However, recent reports on natural
image compression have shown the superior performance of
contourlet transform, a new extension to the wavelet transform in two
dimensions using nonseparable and directional filter banks,
compared to DWT. It is mostly due to the optimality of contourlet in
representing the edges when they are smooth curves. In this work, we
investigate this fact for medical images, especially for CT images,
which has not been reported yet. To do that, we propose a
compression scheme in transform domain and compare the
performance of both DWT and contourlet transform in PSNR for
different compression ratios (CR) using this scheme. The results
obtained using different type of computed tomography images show
that the DWT has still good performance at lower CR but contourlet
transform performs better at higher CR.
Abstract: This paper proposes an algorithm which automatically aligns and stitches the component medical images (fluoroscopic) with varying degrees of overlap into a single composite image. The alignment method is based on similarity measure between the component images. As applied here the technique is intensity based rather than feature based. It works well in domains where feature based methods have difficulty, yet more robust than traditional correlation. Component images are stitched together using the new triangular averaging based blending algorithm. The quality of the resultant image is tested for photometric inconsistencies and geometric misalignments. This method cannot correct rotational, scale and perspective artifacts.
Abstract: The automatic construction of large, high-resolution
image vistas (mosaics) is an active area of research in the fields of
photogrammetry [1,2], computer vision [1,4], medical image
processing [4], computer graphics [3] and biometrics [8]. Image
stitching is one of the possible options to get image mosaics. Vista
Creation in image processing is used to construct an image with a
large field of view than that could be obtained with a single
photograph. It refers to transforming and stitching multiple images
into a new aggregate image without any visible seam or distortion in
the overlapping areas. Vista creation process aligns two partial
images over each other and blends them together. Image mosaics
allow one to compensate for differences in viewing geometry. Thus
they can be used to simplify tasks by simulating the condition in
which the scene is viewed from a fixed position with single camera.
While obtaining partial images the geometric anomalies like rotation,
scaling are bound to happen. To nullify effect of rotation of partial
images on process of vista creation, we are proposing rotation
invariant vista creation algorithm in this paper. Rotation of partial
image parts in the proposed method of vista creation may introduce
some missing region in the vista. To correct this error, that is to fill
the missing region further we have used image inpainting method on
the created vista. This missing view regeneration method also
overcomes the problem of missing view [31] in vista due to cropping,
irregular boundaries of partial image parts and errors in digitization
[35]. The method of missing view regeneration generates the missing
view of vista using the information present in vista itself.
Abstract: Content-Based Image Retrieval (CBIR) has been
one on the most vivid research areas in the field of computer vision
over the last 10 years. Many programs and tools have been
developed to formulate and execute queries based on the visual or
audio content and to help browsing large multimedia repositories.
Still, no general breakthrough has been achieved with respect to
large varied databases with documents of difering sorts and with
varying characteristics. Answers to many questions with respect to
speed, semantic descriptors or objective image interpretations are
still unanswered. In the medical field, images, and especially
digital images, are produced in ever increasing quantities and used
for diagnostics and therapy. In several articles, content based
access to medical images for supporting clinical decision making
has been proposed that would ease the management of clinical data
and scenarios for the integration of content-based access methods
into Picture Archiving and Communication Systems (PACS) have
been created. This paper gives an overview of soft computing
techniques. New research directions are being defined that can
prove to be useful. Still, there are very few systems that seem to be
used in clinical practice. It needs to be stated as well that the goal
is not, in general, to replace text based retrieval methods as they
exist at the moment.
Abstract: Feature-based registration is an effective technique for clinical use, because it can greatly reduce computational costs. However, this technique, which estimates the transformation by using feature points extracted from two images, may cause misalignments. To handle with this limitation, we propose to extract the salient edges and extracted control points (CP) of medical images by using efficiency of multiresolution representation of data nonsubsampled contourlet transform (NSCT) that finds the best feature points. The MR images were first decomposed using the NSCT, and then Edge and CP were extracted from bandpass directional subband of NSCT coefficients and some proposed rules. After edge and CP extraction, mutual information was adopted for the registration of feature points and translation parameters are calculated by using particle swarm optimization (PSO). The experimental results showed that the proposed method produces totally accurate performance for registration medical CT-MR images.
Abstract: Medical image modalities such as computed
tomography (CT), magnetic resonance imaging (MRI), ultrasound
(US), X-ray are adapted to diagnose disease. These modalities
provide flexible means of reviewing anatomical cross-sections and
physiological state in different parts of the human body. The raw
medical images have a huge file size and need large storage
requirements. So it should be such a way to reduce the size of those
image files to be valid for telemedicine applications. Thus the image
compression is a key factor to reduce the bit rate for transmission or
storage while maintaining an acceptable reproduction quality, but it is
natural to rise the question of how much an image can be compressed
and still preserve sufficient information for a given clinical
application. Many techniques for achieving data compression have
been introduced. In this study, three different MRI modalities which
are Brain, Spine and Knee have been compressed and reconstructed
using wavelet transform. Subjective and objective evaluation has
been done to investigate the clinical information quality of the
compressed images. For the objective evaluation, the results show
that the PSNR which indicates the quality of the reconstructed image
is ranging from (21.95 dB to 30.80 dB, 27.25 dB to 35.75 dB, and
26.93 dB to 34.93 dB) for Brain, Spine, and Knee respectively. For
the subjective evaluation test, the results show that the compression
ratio of 40:1 was acceptable for brain image, whereas for spine and
knee images 50:1 was acceptable.
Abstract: Volume rendering is widely used in medical CT image
visualization. Applying 3D image visualization to diagnosis
application can require accurate volume rendering with high
resolution. Interpolation is important in medical image processing
applications such as image compression or volume resampling.
However, it can distort the original image data because of edge
blurring or blocking effects when image enhancement procedures
were applied. In this paper, we proposed adaptive tension control
method exploiting gradient information to achieve high resolution
medical image enhancement in volume visualization, where restored
images are similar to original images as much as possible. The
experimental results show that the proposed method can improve
image quality associated with the adaptive tension control efficacy.
Abstract: Segmenting the lungs in medical images is a
challenging and important task for many applications. In particular,
automatic segmentation of lung cavities from multiple magnetic
resonance (MR) images is very useful for oncological applications
such as radiotherapy treatment planning. However, distinguishing of
the lung areas is not trivial due to largely changing lung shapes, low
contrast and poorly defined boundaries. In this paper, we address
lung segmentation problem from pulmonary magnetic resonance
images and propose an automated method based on a robust regionaided
geometric snake with a modified diffused region force into the
standard geometric model definition. The extra region force gives the
snake a global complementary view of the lung boundary
information within the image which along with the local gradient
flow, helps detect fuzzy boundaries. The proposed method has been
successful in segmenting the lungs in every slice of 30 magnetic
resonance images with 80 consecutive slices in each image. We
present results by comparing our automatic method to manually
segmented lung cavities provided by an expert radiologist and with
those of previous works, showing encouraging results and high
robustness of our approach.
Abstract: In this paper we present the deep study about the Bio-
Medical Images and tag it with some basic extracting features (e.g.
color, pixel value etc). The classification is done by using a nearest
neighbor classifier with various distance measures as well as the
automatic combination of classifier results. This process selects a
subset of relevant features from a group of features of the image. It
also helps to acquire better understanding about the image by
describing which the important features are. The accuracy can be
improved by increasing the number of features selected. Various
types of classifications were evolved for the medical images like
Support Vector Machine (SVM) which is used for classifying the
Bacterial types. Ant Colony Optimization method is used for optimal
results. It has high approximation capability and much faster
convergence, Texture feature extraction method based on Gabor
wavelets etc..
Abstract: As the use of registration packages spreads, the number of the aligned image pairs in image databases (either by manual or automatic methods) increases dramatically. These image pairs can serve as a set of training data. Correspondingly, the images that are to be registered serve as testing data. In this paper, a novel medical image registration method is proposed which is based on the a priori knowledge of the expected joint intensity distribution estimated from pre-aligned training images. The goal of the registration is to find the optimal transformation such that the distance between the observed joint intensity distribution obtained from the testing image pair and the expected joint intensity distribution obtained from the corresponding training image pair is minimized. The distance is measured using the divergence measure based on Tsallis entropy. Experimental results show that, compared with the widely-used Shannon mutual information as well as Tsallis mutual information, the proposed method is computationally more efficient without sacrificing registration accuracy.
Abstract: This paper presents a dominant color descriptor
technique for medical image retrieval. The medical image system
will collect and store into medical database. The purpose of
dominant color descriptor (DCD) technique is to retrieve medical
image and to display similar image using queried image. First, this
technique will search and retrieve medical image based on keyword
entered by user. After image is found, the system will assign this
image as a queried image. DCD technique will calculate the image
value of dominant color. Then, system will search and retrieve again
medical image based on value of dominant color query image.
Finally, the system will display similar images with the queried
image to user. Simple application has been developed and tested
using dominant color descriptor. Result based on experiment
indicates this technique is effective and can be used for medical
image retrieval.
Abstract: In recent years image watermarking has become an
important research area in data security, confidentiality and image
integrity. Many watermarking techniques were proposed for medical
images. However, medical images, unlike most of images, require
extreme care when embedding additional data within them because
the additional information must not affect the image quality and
readability. Also the medical records, electronic or not, are linked to
the medical secrecy, for that reason, the records must be confidential.
To fulfill those requirements, this paper presents a lossless
watermarking scheme for DICOM images. The proposed a fragile
scheme combines two reversible techniques based on difference
expansion for patient's data hiding and protecting the region of
interest (ROI) with tamper detection and recovery capability.
Patient's data are embedded into ROI, while recovery data are
embedded into region of non-interest (RONI). The experimental
results show that the original image can be exactly extracted from the
watermarked one in case of no tampering. In case of tampered ROI,
tampered area can be localized and recovered with a high quality
version of the original area.
Abstract: This paper presents the application of a signal intensity independent registration criterion for non-rigid body registration of medical images. The criterion is defined as the weighted ratio image of two images. The ratio is computed on a voxel per voxel basis and weighting is performed by setting the ratios between signal and background voxels to a standard high value. The mean squared value of the weighted ratio is computed over the union of the signal areas of the two images and it is minimized using the Chebyshev polynomial approximation. The geometric transformation model adopted is a local cubic B-splines based model.
Abstract: Lossless compression schemes with secure
transmission play a key role in telemedicine applications that helps in
accurate diagnosis and research. Traditional cryptographic algorithms
for data security are not fast enough to process vast amount of data.
Hence a novel Secured lossless compression approach proposed in
this paper is based on reversible integer wavelet transform, EZW
algorithm, new modified runlength coding for character
representation and selective bit scrambling. The use of the lifting
scheme allows generating truly lossless integer-to-integer wavelet
transforms. Images are compressed/decompressed by well-known
EZW algorithm. The proposed modified runlength coding greatly
improves the compression performance and also increases the
security level. This work employs scrambling method which is fast,
simple to implement and it provides security. Lossless compression
ratios and distortion performance of this proposed method are found
to be better than other lossless techniques.
Abstract: The class of geometric deformable models, so-called
level sets, has brought tremendous impact to medical imagery. In
this paper we present yet another application of level sets to medical
imaging. The method we give here will in a way modify the speed
term in the standard level sets equation of motion. To do so we
build a potential based on the distance and the gradient of the
image we study. In turn the potential gives rise to the force field:
F~F(x, y) = P
∀(p,q)∈I
((x, y) - (p, q)) |ÔêçI(p,q)|
|(x,y)-(p,q)|
2 . The direction
and intensity of the force field at each point will determine the
direction of the contour-s evolution. The images we used to test
our method were produced by the Univesit'e de Sherbrooke-s PET
scanners.
Abstract: This paper presents the application of a signal
intensity independent registration criterion for 2D rigid body
registration of medical images using 1D binary projections. The
criterion is defined as the weighted ratio of two projections. The ratio
is computed on a pixel per pixel basis and weighting is performed by
setting the ratios between one and zero pixels to a standard high
value. The mean squared value of the weighted ratio is computed
over the union of the one areas of the two projections and it is
minimized using the Chebyshev polynomial approximation using
n=5 points. The sum of x and y projections is used for translational
adjustment and a 45deg projection for rotational adjustment. 20 T1-
T2 registration experiments were performed and gave mean errors
1.19deg and 1.78 pixels. The method is suitable for contour/surface
matching. Further research is necessary to determine the robustness
of the method with regards to threshold, shape and missing data.
Abstract: This paper presents the region based segmentation method for ultrasound images using local statistics. In this segmentation approach the homogeneous regions depends on the image granularity features, where the interested structures with dimensions comparable to the speckle size are to be extracted. This method uses a look up table comprising of the local statistics of every pixel, which are consisting of the homogeneity and similarity bounds according to the kernel size. The shape and size of the growing regions depend on this look up table entries. The algorithms are implemented by using connected seeded region growing procedure where each pixel is taken as seed point. The region merging after the region growing also suppresses the high frequency artifacts. The updated merged regions produce the output in formed of segmented image. This algorithm produces the results that are less sensitive to the pixel location and it also allows a segmentation of the accurate homogeneous regions.