ISSN:2229-6093

G Anil Kumar et al, Int.J.Computer Technology & Applications,Vol 5 (3),851-860

Analysis of Medical Image Processing and its Applications in Healthcare

Industry

G.Anil Kumar, Prof.NistalaV.E.S.Murthy

Research scholar, Department Of CS&SE,
Department Of CS&SE, AU college Of Engineering,
AU college Of Engineering, Visakhapatnam.
Visakhapatnam. [email protected]
[email protected]

Abstract
in disease diagnosis and accuracy in clinical practices
Medical image processing needs continuous
and improvement in state-of-the-art equipment is the
enhancements in terms of techniques and
ever-ending necessity in the health care industry.
applications to help improve quality of services in
This has led to various best practices which are
health care industry. The techniques used for
clinically proven. However, more needs to be done
interpolation, image registration, compression,
with ever-growing medical data, called big data now
medical diagnosis are to be improved to be abreast
days, in order to discover hidden knowledge from the
with growing demands in the industry and emerging
data.
technologies pertaining to mobile computing and
Health care industry generates huge amount of data.
cloud computing. In this paper we present the present
Intelligent processing of such data can reveal hidden
state-of-the-art of medical image processing and its
relationships among the data items which will help in
abilities to harness the hardware resources including
clinical practices. The growth in usage of medical
ever growing GPGPU platforms for improving
image processing can improve quality of services to
quality of clinical practices in terms of speed,
reduce death toll and improve health standards of
accuracy, innovation, and globalization and so on.
citizens of a country. For instance a survey in 2010
From the analysis of the literature it is understood
has released statistics pertaining to deaths due to
that the health care domain has got much scope for
malign cancer in Germany as shown in Figure 1. This
further research in the areas of diagnosing life
situation can be improved with focused usage of
threatening diseases, usage of remote health
technologies for medical image processing to
monitoring applications for real time functioning to
leverage diagnosis, treatment and other clinical
alert healthcare personnel. The integration of
practices.
medical equipment and applications with wearable
devices is also promising area for further research.
This paper provides useful insights into the field of
medical image processing and tries to define the
future scope of work.
Index Terms – Medical image processing (MIP),
medical diagnosis, MIP methods and applications

I. INTRODUCTION

Growing interest in health care domain has paved

way for innovative approaches for medical diagnosis
and clinical practices. Since health is considered to be
wealth, the healthcare industry has been striving to
use innovative medical procedures and treatment
practices coupled with technologies in computations,
harnessing advances in hardware resources. Precision Figure 1 – Death due to malign cancer in
Germany in 2010 [1]

IJCTA | May-June 2014 851

Available [email protected]
 ISSN:2229-6093

G Anil Kumar et al, Int.J.Computer Technology & Applications,Vol 5 (3),851-860

As can be seen in Figure 1 it is alarming that many harnessing GPGPU platforms for high
deaths in Germany are due to cancer. Research into quality healthcare services.
this area by exploiting computing innovations can
improve the situation. Wongthanavasu and The remainder of the paper is structured as follows.
Tangvoraphonkchai [2] presented cellular automata- Section II reviews literature pertaining to medical
based algorithms and their desired applications in image processing, its methods and applications.
diagnosis of breast cancer which facilitates accurate Section III discusses the finding made in the
and expert decision making which helps in combating literature review. Section IV concludes the paper.
the dangerous endemic disease. A typical medical
imaging system appears as shown in Figure 1 which II. RELATED WORK
has provision for image capture and sharing of in
health care industry thorough public network such as
Internet. It can have various clinically useful methods Literature on medical image processing has been
conforming to DICOM to help healthcare reviewed and presented in this section in terms of
professional make expert decisions. general medical image processing approaches,
harnessing the power of GPGPU platforms for
medical image processing, exploiting the cloud
computing advantages and so on.

A. Medical Image Processing in Healthcare

Industry
Lehmann et al. [4] explored B-Spline interpolation
techniques for medical imaging in order to improve
the quality of images. This has an important utility as
healthcare users need to have good visual perception
of images. Banos Jr, Sehn and Krechel [5] proposed a
service model known as “Integrated Image Access
and Distributed Processing Service” which is a
distributed environment which facilitates radiological
medical personnel to gain access to image processing
features. Matthew J et al. [6] proposed an application
for medical image processing as well as visualization
which enabled professional to study, diagnose
Figure 2 – Illustrates a typical medical imaging clinical disorders. Later 3D imaging came into
existence to leverage medical image processing. Li,
system [3] Papachristou and Shekhar [7] provided a
reconfigurable architecture for 3D medical image
As can be seen in Figure 2, it is evident that the processing. The system has four operational stages
medical imaging system has provision for capturing namely parameter generation, input brick fetching,
images, storing them, processing them and sharing medical data stream processing and output brick
them across the industry through reliable storing. Tian and Ha [8] reviewed applications for
communication networks. Section II provides more medical image processing that make use of wavelet
details about the present status of the medical image and inverse transforms. These applications are used
processing area which is relevant to healthcare for clinical diagnosis. Chen, Yi and Ni [9] proposed a
industry. Our contributions in this paper are as platform known as Medical Image Processing
follows. Platform (MIPP), which is used for web based
processing of medical images. The platform was used
 We bring about insights from the review of for design and manufacturing of stents used for heart
literature on medical image processing. This patients.
knowledge helps in understanding the
technical innovations in the industry and In 2005 Regrain et al. [10] built an open source
further research needs. library of functions using Python language meant for
 We analyze the usage of innovative medical image processing. This library has improved
technologies in the area of mobile the pace in application development. Ogiela et al.
computing and cloud computing besides [11] proposed a cognitive approach for analyzing

IJCTA | May-June 2014 852

Available [email protected]
 ISSN:2229-6093

G Anil Kumar et al, Int.J.Computer Technology & Applications,Vol 5 (3),851-860

diagnostic features of images. Thus obtained Wang et al. [23] proposed an algorithm for contour
knowledge was used to analyze pathological cases in extraction and denoising which can be used for
health care domain. Srinivasan N and Vaidehi V [12] medical image analysis, feature extraction, image
studied cluster computing in medical image smoothing, image enhancement, and image
processing for improving diagnostic methods. Hui et reconstruction. The algorithm makes use of
al. [13] studied medical image processing and then combinations of wavelet transform and median
constructed a knowledge center which is helpful to filtering and contour tracing and canny edge
community in healthcare domain to improve their detection. The experimental results reveal that their
knowledge through the e-Learning platform algorithm is capable of processing images which
(knowledge center). It is being used by Tsinghua were captured with poor quality containing high
University. spatial redundancy, and noise. Khayati et al. [24]
presented a distributed system which enables
Vaida and Todica [14] explored the integration of computer aided diagnosis to physicians remotely. The
medical image processing applications in distributed system also keeps requests transparent and ensures
environment using service oriented architecture privacy of sensitive details. Zhu et al. [25] proposed a
(SOA). The medical applications are used as reusable system that can pre-process medical X-Ray images.
components such as Healthlmag and Image Diagnose Especially they used a filter named “temporal
that are dynamically adapted for medical image recursive self adaptive filter”. Field Programmable
processing. The distributed medical application is Gate Array (FPGA) and other devices were used to
thus capable of supporting operations pertaining to achieve this. The system has enhanced the signal-
DNA, echography measurements stereo logy. noise ratio (SNR) of X-Ray images through the pre-
Wongthanavasu and Tangvoraphonkchai [15] processing. Wu and Chi [26] proposed a novel pre-
presented cellular automata-based algorithms and processing method that can enhance the quality of
their desired applications in diagnosis of breast medical images before being processed. Unlike the
cancer. The application is useful for medical technique in [25] it uses shape-preserving fitting for
professionals. Peng et al. [16] presented a new way of pre-processing of medical images. The medical
using stochastic resonance for quality image images obtained by CT scanner are improved before
processing in medical domain. Sarkar et al. [17] processing them. Wang and Kang [27] applied a
proposed an interpolation kernel for medical image novel algorithm on correlation theory and contourlet
processing. The technique uses many Gaussian filters transform for medical image processing. Especially
at various levels to improve images based on their algorithm has better compression performance
perception of human eye. Siemens Medical then wavelet transform. Digital Imaging and
Ultrasound Scanner is used to capture video frames Communications in Medicine (DICOM) has been
for empirical study. Selvarasu et al. [18] proposed an considered a standard in processing medical images
algorithm for automatic interpretation of thermo in terms of transmitting, printing, storing, and
grams and quantify them in order to find abnormality. handling. Hu et al. [28] proposed an interactive
The hotspots in thermograms can reveal approach for medical image processing that is in
abnormalities in medical thermograms. The conformance with DICOM. The methods provided by
algorithm is efficient in terms of time, image them assisted doctors to make well informed
specificity and parameter dependency. Tian et al. [19] diagnostic and treatment decisions.
designed and implemented a software platform for
medical image processing with activities like Lee et al. [29] combined wavelet edge detection and
registration, segmentation, reconstruction and segmentation for quantitative coronary analysis. It
visualization. Todica and Vaida [20] proposed an helps doctors to diagnose heart diseases like heart
SOA based distributed architecture as platform for artery stenosis. This method is supported by 3D
medical image processing. This is a flexible platform image processing to improve quality coronary
which allows components as service renderers which angiography images.
can be plugged dynamically. Thus the application can
improve its services over a period of time. Han and B. Medical Image Registration
Jia [21] explored the processing of Computed
Tomography (CT) and Medical Rapid Prototyping Medical image registration is a process of
(MRP) models. These models were further used in establishing correspondence among a series of
3D visualization. Qi and Yu [22] also focused on images. This is a challenging task. Du et al. [30]
edge detection of CT images using multifractal proposed a mixed-type approach for medical image
theory for best detection medical CT images. registration under the standards of DICOM. For
image matching Mutual Information (MI) is used as

IJCTA | May-June 2014 853

Available [email protected]
 ISSN:2229-6093

G Anil Kumar et al, Int.J.Computer Technology & Applications,Vol 5 (3),851-860

similarity measure. This method proved to have less performs medical image processing and visualization
computational complexity, high accuracy and more concurrently. This method is capable of exploiting
speed. Sugimoto et al. [31] built many image hardware resources to speed up medical image
processing application in collaboration with processing. Thus this image processing approach can
researchers in healthcare domain. Their applications cater to temographic imaging and medical diagnosis.
support dynamic image processing, especially for Suresh and Babu [34] explored the research on
images pertaining to cardiovascular disease. Figure 1 medical image processing techniques that can harness
shows functionality of one of the applications the power of GPGPU platforms. Thus the pressure on
explored in [31] that is meant for image registration. rendering quality diagnosis and treatment is possible
when GPU is used to speed up the processing.

D. XML Based Medical Image Processing

XML has been used widely for data representation

since it is platform and device independent. Miri et
al. [35] presented a web based framework for medical
image processing. The framework makes use of
Image Markup Language (IML). It provides a
platform for distributed medical image processing
and renders good ideas to have customized
workflows useful for different users in the health care
industry. Oa-Zhe et al. [36] studied Medical Image
Understanding Process Definition Language (MPDL)
which is meant for an array of medical image
processing activities. The MPDL helps in medical
image understanding. It is a tool which leverages
software development for medical image processing
besides having the abilities to control image
Figure 3 – 2D/3D image registration method [31] presentation and data flow.
As can be seen in Figure 3, it is evident that the
image registration method is required to have a series E. Imaging Devices vs. their 2D, 3D and 4D
of images to be processed in order to make them
ready for various processes and decision making Representations
exercises.
In healthcare domain various devices are used as
C. Exploiting GPGPU Platforms for Medical imaging devices such as scintigraphy, roentgen, ultra
sound, CT, MRT, PET, SPECT, and 4D-CT. These
Image Processing imaging devices have varied capabilities to work in
2D, 3D, and 4D representations as shown in Figure 4.
General Purpose Graphics Processing Units are many
times powerful than CPUs. These platforms can be
used to enhance the services in healthcare industry.
Wei-Hung et al. [32] proposed acceleration of the
NMI (Normalized Mutual Information) procedure for
medical image registration. They employed an
approach that makes use of the power of Graphical
Processing Units (GPUs) for parallel processing to
leverage the performance image registration. The
experiments were done using GPU platform CUDA
with graphical processor GeForce 9600 GT from
NVIDIA.

Tiejian et al. [33] presented embedded 3D medical

image processing which overcomes the limitations of
the present approaches. The proposed method

IJCTA | May-June 2014 854

Available [email protected]
 ISSN:2229-6093

G Anil Kumar et al, Int.J.Computer Technology & Applications,Vol 5 (3),851-860

Figure 4 – Overview of imaging devices vs. 2D, 3D Figure 5 – Medical Image Processing Assistant
and 4D imaging representations [1] running in Tablet PC (a) and iPad (b) [37]

Irradiation of moving tumors is performed as part of As can be seen in Figure 5 it is evident that the
medical irradiation therapy which is of three types application takes care of medical image processing
again namely resection, radiation therapy and based on the images provided and notify doctor for
chemotherapy [1]. Recently mobile devices are also possible ailments to improve the quality of service in
used for medical image processing. For instance Lin health care domain.
et al. [37] proposed a mobile application that works
in small hand held devices. The application takes F. Diagnosis of Cancer & Heart Ailments
medical images and extracts haptic parameters from
visual features. Then the application notifies doctors
concerned for possible findings of unwanted diseases Data mining techniques are being used for processing
with the aid of medical imaging. This will help medical databases. Kharya [38] proposed a
doctors to make decisions in further diagnosis. methodology for diagnosis and prognosis of breast
cancer. Decision tree model was used to represent
actionable knowledge pertaining to breast cancer.
Artificial Neural Networks (ANNs) were also used to
diagnose breast cancer. Krishnaiah et al. [39] used
classification techniques for lung cancer prediction.
Their system is used for early detection of lung
cancer and accurate diagnosis of it which will save
time of doctors besides helping them in clinical
practices. Srinivas et al. [40] used data mining
techniques for prediction of heart attacks.

G. Cloud and Medical Image Processing

Cloud computing has evolved as a new computing

model which can provide huge computing resources
in pay per use fashion. It has promising
characteristics to help healthcare industry. Chiang et
al. [41] proposed and implemented a Service
Oriented Architecture (SOA) for building a cloud

IJCTA | May-June 2014 855

Available [email protected]
 ISSN:2229-6093

G Anil Kumar et al, Int.J.Computer Technology & Applications,Vol 5 (3),851-860

service that can be used by general public and III. DISCUSSION
medical personnel for reliable medical image
processing. They combined the resource integration
of cloud and “ImageJ”, the image processing In this section we analyze the developments in the
software into a cloud service. This has paved way for area of medical image processing technologies,
applications worldwide to gain access to the cloud applications in healthcare domain. From the
service seamlessly. Figure 2 presents the SOA with preceding sections various insights were considered
cloud and a sample image processing activity that can for this discussion. At a broader level it is understood
be supported by the cloud service. that medical image processing has promising
consequences in leveraging quality practices in
clinical practices. State of the art equipment and
technologies are available these days and there is
quest for excelling in medical diagnosis and
treatment with utmost quality. Towards this various
technologies came into existence. Though the
corporate hospitals do not disclose their proprietary
methods, in this paper, we focused on the available
methods in the literature. The evolution of techniques
and applications in medical image processing has
made the professions in the domain to have more
effective practices. Some techniques pertaining to
interpolation, image registration, diagnosing lung
cancer, breast cancer, heart ailments were known in
the literature. Data mining techniques and image
mining techniques were also found in the literature
which improved the quality of services in the health
care domain.
Recently medical image processing is making strides
Figure 6 – Illustrates (a) cloud architecture and in using powerful technologies like virtualization and
(b) the steps followed for EMROI extraction [3] cloud computing to speed up processing. It is also
making use of GPGPU platforms for high speed
computation of medical procedures. Mobile
As can be seen in Figure 6, it is evident that the technologies are also used to exploit the convenience
business logic required by various image processing the mobile devices provide for doctors and patients
activities such as EMROI extraction are kept over by making suitable applications. Wearable devices
cloud and the services are made available to public in are also used to processes patients’ vital signs and
order to access the business logic in platform help professionals to make well informed decisions.
independent fashion [3]. Eilam et al. [42] explored Thus patients are saved from unnecessary round trips
medical ultrasound imaging and possible usage of to hospital premises by using remote medical image
cloud computing. They developed a medical imaging processing applications. The summary of the findings
system for medical ultra sound imaging with the help with respect to techniques used in medical image
of cloud. Their results were encouraging and thus processing are presented in Table 1.
concluded it to be feasible to use cloud help for
ultrasound imaging.

Author (s) YEAR Techniques Purpose Advantages

Lehmann, Gönner and 2001 High degree B- Improves the quality of  Reasonable
Spitzer [4] Spline images in medical computing times
Interpolation imaging  Smallest interpolation
error
 Superior Fourier
properties

IJCTA | May-June 2014 856

Available [email protected]
 ISSN:2229-6093

G Anil Kumar et al, Int.J.Computer Technology & Applications,Vol 5 (3),851-860

Tian and Ha [8] 2004 Wavelet ECG signal processing Clinical diagnosis and therapy
transform and
inverse transform
Wongthanavasu and 2007 Cellular To determine hypothesis Diagnosis of breast cancer
Tangvoraphonkchai [2] automata spots of breast cancer
algorithms
Wang et al. [23] 2008 Denoising and Denoising and contour  Medical image
contour extraction analysis
extraction  Feature extraction
algorithm  Image smoothing
 Image enhancement
 Image reconstruction
Khayati et al. [24] 2008 Distributed For medical request Helps physicians to have
system processing. diagnosis requests remotely.
Zhu et al. [25] 2008 Temporal Pre-processing of Improves SNR of X-Ray
Recursive Self- medical X-Ray images images
Adaptive Filter
Wu and Chi [26] 2008 Shape – Pre-processing of Quality of CT scanned images
preserved fitting medical images are improved further
Wang and Kang [27] 2008 Contourlet Time frequency  Performance is
transform localization and multi- improved in denoising
scale analysis and image
compression
 Better than wavelet
transform
Hu and Gui [28] 2009 Interactive image For user-friendly and  Clinically useful
processing interactive image  Assists diagnosis
technique processing technique.
Du et al. [30] 2009 Mixed-type For medical image  Speed of registration
registration registration is more
approach  Accuracy of
registration is more

Lee et al. [29] 2009 Wavelet edge Quantitative coronary Helps doctors to diagnose heart
detection and analysis ailments like heart artery
segmentation stenosis

IJCTA | May-June 2014 857

Available [email protected]
 ISSN:2229-6093

G Anil Kumar et al, Int.J.Computer Technology & Applications,Vol 5 (3),851-860

Wei-Hung et al. [32] 2009 acceleration of For acceleration of  23.4x increase in
the NMI medical image speed in registration
procedure registration  Computationally cost
effective
Tiejian et al. [33] 2010 Embedded 3D Temographi imaging and  Disease diagnosis
medical image visualization  Exploits hardware
processing resources
 Space and
computation efficient

Oa-Zhe et al. [36] 2010 MPDL Building prototypes for  Cost effective and
framework medical image processing user friendly
development of
software for medical
image processing
Chiang et al. [41] 2011 Cloud service for Providing access to  Consistency
BL sharing applications across the  Interoperability
world to share BL of  Security
medical image processing

Table 1 – Summary of findings

As can be seen in Table 1, the medical image processing approaches, applications and techniques have given
insights to ascertain the present state of the art as much as possible. However, the research on medical image
processing has much scope to proceed further. This we will continue further in future.

IV. CONCLUSION practices. An important insight from the literature is

that though there are improvements in medical image
processing, lot of research is left unattended which
In this paper we studied medical image processing in encourages researchers to focus on. For instance
health care domain for valuable insights into the remote health care systems can be enhanced so as to
subject. The analysis of medical image processing, its let patients use them for preliminary health decisions.
applications in healthcare industry are presented in Another research direction is to integrate wearable
this paper. Medical image processing has revealed devices of patients to health care servers so as to alert
significant growth in harnessing new technologies physicians concerned to take steps early to keep
and processing capabilities. It is capable of situation in control before proceeding further. Yet
leveraging the power of GPGPU platforms, cloud another research direction in future is to develop
computing and other technologies. Medical image software systems that interface with medical
processing is also involved in data mining and image hardware for accurate and real time diagnosis of life
mining in order to improve quality of services in threatening diseases like heart ailments, cancers of
hospitals. Usage of hand held devices, cloud various kinds and diabetes.
computing and wearable computing is witnessed
which reflects the progress being made in usage of
emerging technologies for diagnosis and clinical

IJCTA | May-June 2014 858

Available [email protected]
 ISSN:2229-6093

G Anil Kumar et al, Int.J.Computer Technology & Applications,Vol 5 (3),851-860

REFERENCES Algorithms for Automatic Detection and Quantification of

Abnormality in Medical Thermograms. IEEE.p388-393.
[19] Jie Tian, Jian Xue, Yakang Dai, Jian Chen, and Jian
[1] Detlef RICHTER. (2012). Current State of Image Zheng. (2008). A Novel Software Platform for Medical
Processing for Medical Irradiation Therapy. IEEE. p1-5. Image Processing and Analyzing. IEEE. 12 (6), p800-812.
[2] S. Wongthanavasu and V. Tangvoraphonkchai. (2007). [20] V.Todica and M. F. Vaida. (2008). SOA-Based
CELLULAR AUTOMATA-BASED ALGORITHM AND Medical Image Processing Platform. IEEE. P1-6.
ITS APPLICATION IN MEDICAL IMAGE [21] Jiman Han and Yi Jia. (2008). CT Image Processing
PROCESSING. IEEE. P41-44. and Medical Rapid Prototyping. IEEE. p67-71.
[3] Viralkumar Bulsara, Surabhi Bothra, Poonam Sharma, [22] Dawai Qi and Lei Lu. (2008). Analysis and processing
K.M.M.Rao. (2011). Low Cost Medical Image Processing of Medical CT Image Based Multifractal Theory. IEEE.
System for Rural/Semi Urban Healthcare. IEEE. p724-728. p2168-2173.
[4] Thomas M. Lehmann, Claudia Gönner and Klaus [23] Yu Wang1, Jinjin Zheng, Hongjun Zhou, Lianguan
Spitzer. (2001). Addendum: B-Spline Interpolation in Shen. (2008). Medical Image Processing by Denoising and
Medical Image Processing. IEEE. 20 (7), p660-665. Contour Extraction. IEEE. p618-623.
[5] Euclides de Moraes Banos Jr., Michel Sehn and Dirk [24] N. Khayati, W. Lejouad-Chaari and S. Sevestre-
Krechel. (2001). A Model for Distributed Medical Image Ghalila. (2008). A Distributed Image Processing Support
Processing using CORBA. IEEE. p189-194. System Application to Medical Imaging. IEEE. p1-4.
[6] Matthew J. McAuliffe’, Francois M . Lalonde’, Delia [25] Hong Zhu, Weizhen Sun, Minhua Wu, Guixia Guan,
McGarry’, William Gandler’, Karl Csaky, Benes L. Trus. Yong Guan. (2008). Pre-Processing of X-Ray Medical
(n.d). Medical Image Processing, Analysis & Visualization Image Based on Improved Temporal Recursive Self-
In Clinical Research. IEEE. p381-386. Adaptive Filter. IEEE. p758-763.
[7] Jianchun Li, Christos Papachristou and Raj Shekhar. [26] Xiaoming Wu and Jing Chi. (2008). Shape-Preserving
(2004). A Reconfigurable SoC Architecture and Caching Fitting Used for Medical Image Pre-processing. IEEE.
Scheme for 3D Medical Image Processing. IEEE. p1-2. p826-829.
[8] DA-ZENG TIAN and MING-HU HA. (2004). [27] Jun Wang and Yan Kang. (2008). Study on Medical
APPLICATIONS OF WAVELET TRANSFORM IN Image Processing Algorithm based on Contourlet
MEDICAL IMAGE PROCESSING. IEEE. p1816-1821. Transform and Correlation Theory. IEEE. p233-238.
[9] Gong Chen, Hong Yi, Zhonghua Ni. (2005). MIPP: A [28] Zhanli Hu , Hairong Zheng and Jianbao Gui. (2009). A
Web-Based Medical Image Processing System for Stent Novel Interactive Image Processing Approach for DICOM
Design and Manufacturing. IEEE. p1484-1488. Medical Image Data. IEEE. p1-4.
[10] B. Regrain, E. Boix, C. Odet, H. Benoit-Cattin. (2005). [29] Tsair-Fwu Lee, Chang-Yu Lee, Pei-Ju Chao, Chieh
DaVaW: A Python Library for Medical Image Processing Lee, Chang-Yu Wang and Chun-Hsiung Fang. (2009).
Applications. IEEE. p1-4. Quantitative Coronary Analysis Medical Image Processing
[11] Marek R. Ogiela and Ryszard Tadeusiewicz. (2005). Improved by Combining Wavelet Edge Detection and
Nonlinear Processing and Semantic Content Analysis in Segmentation. IEEE. p1196-1199.
Medical Imaging—A Cognitive Approach. IEEE. 54 (6), [30] Yongsheng Du, Anping Song, Lei Zhu, and Wu
p2149-2155. Zhang. (2009). A Mixed-type Registration Approach in
[12] Srinivasan N and Vaidehi V. (2005). Application of Medical Image Processing. IEEE. p1-4.
Cluster Computing in Medical Image Processing. IEEE. [31] Naozo Sugimoto, Hiroshi Imamura, Hiroyuki
p84-87. Sekiguchi and Shigeru Eiho. (2007). Medical Image
[13] Ding Hui, Wang Guangzhi, Hong Bo, Zhou Yiyi, Processing in Collaboration with Medical Researchers.
Yang Zhi, Meng Meng Gao ShangKai. (2005). IEEE. p1-8.
Construction of a Knowledge Center for Medical Image [32] Wei-Hung Cheng and Cheng-Chang Lu. (2009).
Processing. IEEE. p82-85. Acceleration of Medical Image Registration using Graphics
[14] Mircea-Florin Vaidal, Valeriu Todica. (2007). Process Units in Computing Normalized Mutual
Dynamic Adaptability of Image Processing Components in Information. IEEE. p814-818.
Medical Applications. IEEE. p1-4. [33] Chen Tiejian, Wang Yaonan, Zhang Hui, Xiao
[15] S. Wongthanavasu and V. Tangvoraphonkchai. Changyan. (2010). An Embedded 3D Medical Image
(2007).Cellular Automata-Based Algorithm And Its Processing and Visualization Platform Based on Dual-core
Application In Medical Image Processing. IEEE. P41-44. Processor. IEEE. p2936-2941.
[16] Renbin Peng, Hao Chen, Pramod K. Varshney and [34] K.Suresh and Dr.M.Rajasekhara babu. (2013).
James H. Michels . (2008). Stochastic Resonance: An Towards on High Performance Computing of Medical
Approach for Enhanced Medical Image Processing. IEEE. Imaging based on Graphical Processing Units. IEEE. p1-6.
p253-256. [35] Majid Pourdadash Miri, Hamidreza Pooshfam,
[17] Sandip Sarkar1, Kuntal Ghosh2, Kamales Bhaumik. Mandava Rajeswari and Dhanesh Ramchandram. (2009). A
(2007). A Bio-inspired Interpolation Kernel for Medical Web Based Framework for Distributed Medical Image
Image Processing Implemented on DSP Processor. IEEE. Processing Using Image Markup Language. IEEE p470-
p159-163. 475.
[18] N.Selvarasu, Sangeetha Vivek and N.M.Nandhitha. [36] ZHAO Oa-Zhe, LI Wei and YANG Jin-Zhu . (2010).
(2008). Performance Evaluation of Image Processing An XML-Based Process Definition Language for Medical
Image Understanding. IEEE. p679-683.

IJCTA | May-June 2014 859

Available [email protected]
 ISSN:2229-6093

G Anil Kumar et al, Int.J.Computer Technology & Applications,Vol 5 (3),851-860

[37] Jiaqing LIN, 2Hiroaki NISHINO, Tsuneo KAGAWA
and Kouichi UTSUMIYA. (2012). A Tangible Medical
Image Processing Assistant with Haptic Modality. IEEE.
p723-728.
[38] Shweta Kharya. (2012). Using Data Mining
Techniques For Diagnosis And Prognosis Of Cancer
Disease. IJCSEIT. 2 (2), P55-66.
[39] .Krishnaiah, Dr.G.Narsimha, Dr.N.Subhash Chandra.
(2013). Diagnosis of Lung Cancer Prediction System Using
Data Mining Classification Techniques. IJCSIT. 4 (1), p39-
45.
[40] K.Srinivas, B.Kavihta Rani and Dr. A.Govrdhan.
(2010). Applications of Data Mining Techniques in
Healthcare and Prediction of Heart Attacks. IJCSE. 2 (2),
P250-255.
[41] Wen-Chung Chiang, Hsiu-Hsia Lin, Tung-Shen Wu
and Chin-Fa Chen. (2011). Bulding a Cloud Service for
Medical Image Processing Based on Service-Orient
Archtecture. IEEE. p1459-1465.
[42] Alon Eilam, Tanya Chernyakova , Yonina C. Eldar
and Arcady Kempinski. (2013). Sub-Nyquist Medical
Ultrasound Imaging: En Route to Cloud Processing. IEEE.
p1017-1020

IJCTA | May-June 2014 860

Available [email protected]