International Journal of Scientific & Engineering Research Volume 2, Issue 10, Oct-2011 1

ISSN 2229-5518

Survey of Databases Used in Image

Processing and Their Applications

Shubhpreet Kaur, Gagandeep Jindal

Abstract- This paper gives review of Medical image database (MIDB) systems which have been developed in the past few years for research for medical fraternity and students. In this paper, I have surveyed all available medical image databases relevant for research and their use.

Keywords: Image database, Medical Image Database System.

—————————— ——————————

1. INTRODUCTION

Medical imaging is the technique and process used to create images of the human for clinical purposes (medical procedures seeking to reveal, diagnose or examine disease) or medical science. As a discipline, it is part of biological imaging and incorporates radiology, nuclear medicine, investigative radiological sciences, endoscopy, (medical) thermography, medical photography and microscopy.

Shubhpreet Kaur is currently pursuing masters degree program in Computer Science and engineering in Chandigarh Engineering College, Mohali, India. E-mail: shubh_86@ymail.com

Gagandeep Jindal is currently assistant processor in department Computer Science and Engineering in Chandigarh Engineering College, Mohali, India. E-mail:

gaganpec@yahoo.com
Measurement and recording techniques, such as electroencephalography, magnetoencephalography (MEG), Electrocardiography (EKG) and others, can be seen as forms of medical imaging. Image Analysis is done to ensure database consistency and reliable image processing.

Open source software for medical image analysis Several open source software packages are available for performing analysis of medical images:

ImageJ

3D Slicer

ITK

OsiriX

GemIdent

MicroDicom

FreeSurfer

1.1 Images used in Medical Research

Here is the description of various modalities that are used for the purpose of research by medical and
engineering students as well as doctors.

IJSER © 2011 http://www.ijser.org

International Journal of Scientific & Engineering Research Volume 2, Issue 10, Oct-2011 2

ISSN 2229-5518

i) Computed Tomography (CT)



Computed Tomography, also known as computed axial tomography, or CAT scan is a medical technology that uses X-rays and computers to produce three-dimensional images of the human body. Unlike traditional X-rays, which highlight dense body parts, such as bones, CT provides detailed views of the body’s soft tissues, including blood vessels, muscle tissue, and organs, such as the lungs.
a) b)
Fig. 1.1:a) CT scanner and b) CT scan Image.

ii) Magnetic Resonance Imaging(MRI)

Magnetic resonance imaging (MRI), nuclear magnetic resonance imaging (NMRI), or magnetic resonance tomography (MRT) is a medical imaging technique used in radiology to visualize detailed internal structures. MRI makes use of the property of nuclear magnetic resonance (NMR) to image nuclei of atoms inside the body. MRI provides good contrast between the different soft tissues of the body, which make it especially useful in imaging the brain, muscles, the heart, and cancers compared with other medical imaging techniques such as computed tomography (CT) or X-rays.

Fig.1.2: MRI Image.

iii) Single-photon emission computed tomography

(SPECT)

SPECT, or less commonly, SPET is a nuclear medicine topographic imaging technique using gamma rays. SPECT imaging is performed by using a gamma camera to acquire multiple 2-D images (also called projections), from multiple angles thus, yielding a 3-D dataset. This dataset may then be manipulated to show thin slices along any chosen axis of the body, similar to those obtained from other tomographic techniques, such as MRI, CT, and PET.

iv) Positron emission tomography (PET)

PET is a nuclear medicine imaging technique that produces a three-dimensional image or picture of functional processes in the body. It is both a medical and research tool. It is used heavily in clinical oncology (medical imaging of tumors and the search for metastases), and for clinical diagnosis of certain diffuse brain diseases such as those causing various types of dementias. PET is also an important research
tool to map normal human brain and heart function.

IJSER © 2011 http://www.ijser.org

International Journal of Scientific & Engineering Research Volume 2, Issue 10, Oct-2011 3

ISSN 2229-5518



longer time and in the case of research work, they help the professionals as well as the practitioners to
clearly go through the problem. Talking about the
a) b)
Fig.1.3: a) Image of a typical positron emission tomography (PET) facility, b) A complete body PET / CT Fusion image.

v) Plain X-rays



X-rays are useful in the detection of pathology of the skeletal system as well as for detecting some disease processes in soft tissue. Some notable examples are the very common chest X-ray, which can be used to identify lung diseases such as pneumonia, lung cancer or pulmonary edema, and the abdominal X- ray, which can detect intestinal obstruction. X-rays may also be used to detect pathology such as gallstones or kidney stones which are often visible. Traditional plain X-rays are less useful in the imaging of soft tissues such as the brain or muscle.
a) b)
Fig.1.4: a) X-Ray machine, b) X-Ray of Neck.

1.2 WHY WE USE IMAGES FOR RESEARCH?

The images are the visual representations that help a person to retain the effects in his memory for a
use of medical images, they help the physicians and nurses, allied health professionals, medical students, graduate nursing students and other post-graduate trainees in identifying the pathology, thus saving their valuable time, resulting in improved clinical decisions and lowering the medical cost.

2. WHERE ONE CAN GET MEDICAL IMAGES FOR DOING RESEARCH?

Hereby, we have discussed various MIDB’s available world-wide, name of the database, their description and applications of these images.
2.1 LUNG IMAGE DATABASE CONSORTIUM (LIDC)

Description: Lung cancer is the leading cause of cancer death worldwide, both in men and women, with an estimate of over 164,000 new cases and over

156,000 deaths in 2000 in the United States alone. Preliminary clinical studies have shown that spiral
CT scanning of the lungs can improve early detection of lung cancer in high-risk individuals. Image processing algorithms have the potential to assist in lesion detection on spiral CT studies, and to assess
the stability or change in lesion size on serial CT
studies. The use of such computer-assisted
algorithms could significantly enhance the sensitivity and specificity of spiral CT lung screening, as well as lower costs by reducing physician time needed for interpretation.

IJSER © 2011 http://www.ijser.org

International Journal of Scientific & Engineering Research Volume 2, Issue 10, Oct-2011 4

ISSN 2229-5518

Number and type of Images: LIDC have a collection of about 200 serial CT data.

Applications: This database serves as an important resource for researchers interested in developing improved methods for early detection and screening

for lung cancer.
Specifically, the LIDC initiative aims were to provide:

a reference database for the relative

evaluation of image processing or CAD
algorithms.

a flexible query system that will provide investigators the opportunity to evaluate a wide range of technical parameters that may be important for research applications.

Various universities that makes access to this database are Cornell University, University of California, Los Angeles, University of Chicago , University of Iowa, University of Michigan for medical research and teaching.
2.2 NATIONAL BIOMEDICAL IMAGING ARCHIVE (National Cancer Institute, USA):

Description: NBIA is a searchable repository of medical images that provides the biomedical research community, industry, and academia with access to image archives. to be used in the development and

validation of analytical software tools that support:

Lesion detection and classification

Accelerated diagnostic imaging decision

Quantitative imaging assessment of drug

response
NBIA provides access to imaging resources that will improve the use of imaging in today's biomedical research and practice by:

Increasing the efficiency and reproducibility

of imaging cancer detection and diagnosis

Ultimately enabling the development of imaging resources that will lead to improved clinical decision support.

Various database repository under NBIA are:

Database1: CT Colonography

The "CT Colonography" (CTC) image collection in
DICOM format.

Collection Statistics are as under :

Number of Images 941,774

Database2: FDG-PET Lymphoma

FDG-PET Lymphoma is a collection consisting of
Lymphoma cases using PET and CT modalities.
Number of Images 28,462

Database3: Head-Neck Cetuximab (RTOG 0522 and

ACRIN 4500)

IJSER © 2011 http://www.ijser.org

International Journal of Scientific & Engineering Research Volume 2, Issue 10, Oct-2011 5

ISSN 2229-5518

The Head-Neck Cetuximab collection in NBIA consists of image data from ACRIN 4500/RTOG 0522, which was randomized phase III Trial of Radiation Therapy and Chemotherapy for stage III and IV Head and Neck carcinomas. Data was provided to NBIA through two independent channels:

RTOG 0522: CT, Structures, RT Doses, RT

Plans sent from ITC

ACRIN 4500: Quantitative PET (PET/CT)

sent from ACRIN
Number of Images 202,320

Database4: IDRICONDUIT

Number of Images 416,004

Database5: I-SPY

The I-SPY collection is a demonstration project in which some images relating to the I-SPY breast cancer trial were collected and stored.

Number of Images 5,054

Applications: NBIA repository is used in the development and validation of analytical software tools that support:

Lesion detection and classification

Accelerated diagnostic imaging decision

Quantitative imaging assessment of drug response

2.3 NATIONAL CENTRE FOR RESEARCH RESOURCES:

Description: The resource of National Centre for

Research Resources are dedicated to the design of quantitative magnetic resonance (MR) acquisition and processing technology to assess tissue changes and alterations in function, metabolism, and physiology as the brain changes during neurodevelopment or neurodegeneration. Applications: To accomplish the needs of a large
community of clinicians and neuroscientists at
several institutions, this technology development came into existence.
National Centre for Research Resources is supported by NIH/NCRR grant P41 RR015241.
2.4 F.M. Kirby Research Centre for functional brain Imaging at Kennedy Krieger institute (Baltimore, Maryland):

Description: The datasets are publicly accessible, in order to promote search in medical image processing and analysis. Their primary databases

are possible through collaborative efforts in:

IJSER © 2011 http://www.ijser.org

International Journal of Scientific & Engineering Research Volume 2, Issue 10, Oct-2011 6

ISSN 2229-5518

1. Diffusion Tensor Imaging
2. Image Analysis of Functional Anatomy
3. Kirby 21: Multi-Modal MRI Reproducibility

a. DTI Datasets

This database is developed by the Laboratory of Brain Anatomical MRI, these datasets show DTI data and three-dimensional fiber trajectories:

Human Brain Atlas

These atlases were developed from coronal, sagittal, and axial slices. The CMRM also has a human atlas template, a mouse atlas,
a monkey atlas, and a CT-MRI atlas.

DTI Database

This human database contains raw and processed DTI data of the normal population. It is a public database, open to registered users. Its purpose is to facilitate research in DTI data processing and analysis, to study specific biological interests, or to be used as control data.

Developmental DTI Database

This database is still under construction.

b. Functional Anatomy Datasets

Developed by the Center for Imaging Science at Johns Hopkins University, these datasets show analyzed biological images.

c. Kirby 21: A Multi-Modal MRI Reproducibility Resource

This database consists of scan-rescan imaging
sessions on 21 healthy volunteers. All data have been

IJSER © 20 http://www.ijs

converted to NIFTI format and is publicly released.

Figure.2.1: An axial slice from the CMRM DTI Human Atlas.

Applications: This dataset is intended to be a resource for statisticians and imaging scientists to be able to quantify the reproducibility of their imaging

methods.
2.5 IMAGE SCIENCES INSTITUTES:

a. DRIVE: Digital Retinal Images for Vessel

Extraction

Description: The DRIVE database has been established to enable comparative studies on segmentation of blood vessels in retinal images. The images for the DRIVE database were obtained from a diabetic retinopathy screening program in The Netherlands. The screening population consisted of

400 diabetic subjects between 25-90 years of age.

Number of Images:

International Journal of Scientific & Engineering Research Volume 2, Issue 10, Oct-2011 7

ISSN 2229-5518

retinopathy
7 show signs of early diabetic retinopathy

Each image has been JPEG compressed. The set of 40 images has been divided into a training and a test set, both containing 20 images.

b. SCR database: Segmentation in Chest

Radiographs

Description: The automatic segmentation of anatomical structures in chest radiographs is of great importance for computer-aided diagnosis in these images. The SCR database has been established to facilitate comparative studies on segmentation of the lung fields, the heart and the clavicles in standard posterior-anterior chest radiographs.

Number of Images in the database:

coordinates of nodule, simple diagram of nodule location, degree of subtlety in visual detection of nodules

Applications: Useful for diagnostic training and testing

2.6 MEDPIX

Description: It is a free online Medical Image Database and Radiology Portal, provided by the Departments of Radiology and Biomedical Informatics, Uniformed Services University,

Bethesda, Maryland, USA. MedPix is a fully web- enabled cross-platform database, integrating images and textual information. The primary target audience includes physicians and nurses, allied health professionals, medical students, graduate nursing students and other post-graduate trainees. The content material is organized by disease location, pathology category, patient profiles, and by image classification and caption.

Current MedPix Inventory:

Number of Registered users

37973

Images with Captions and Meta-

54192

IJSER © 2011 http://www.ijser.org

International Journal of Scientific & Engineering Research Volume 2, Issue 10, Oct-2011 8

ISSN 2229-5518

2.8 CORNELL UNIVERSITY (New York City) :

SIMBA Home: VIA-ELCAP Public Access DICOM image data may be rapidly as well as directly downloaded in blocks of 10 cases.

Format of Image Data

DICOM

Repository

For lungs, heart, abdomen, liver, spine, etc

Applications: This database serves as an important resource for researchers interested in developing improved methods for early detection of diseases.

3. CONCLUSION

The Visible Human Dataset offers many additions to the original goal of a three-dimensional representation of a computer generated anatomical
2.7 McKESSON CORPORATION(MyPACS.net): Description: This database have relevant datasets for detecting ailments such as, Congenital, infection,
non-infectious inflammatory disease, Benign Mass Cyst, Neoplasm, Trauma, Normal/Variants, latrogenic, Metabolic, Hematological, Vascular and all chest problems.

Applications: this database is helpful for medical researchers and doctors to cure the above ailments and can curb the problem at right time.

model of the human body and to the general study of human anatomy. In this paper, we have presented a large repository of medical image datasets that offers the opportunity to perform relevant research and their use in various areas.

REFERENCES

[1]http://imaging.cancer.gov/programsandresources/ Informati

onSystems/LIDC

IJSER © 2011 http://www.ijser.org

International Journal of Scientific & Engineering Research Volume 2, Issue 10, Oct-2011 9

ISSN 2229-5518

[2]https://wiki.nci.nih.gov/display/CIP/NBIA+at+CBI IT+Ima

ge+Collections

[3] http://www.ncrr.nih.gov/
[4] http://mri.kennedykrieger.org/
[5] http://www.imago.uu.nl/
[6] http://www.isi.uu.nl/Portal/
[7]
http://rad.usuhs.edu/medpix/parent.php3?mode=def ault#to
[8] http://www.mypacs.net/repos/mpv3_repo/static/m/A bout/i

ndex.html

[9] http://www.mckesson.com/en_us/McKesson.com/
[10] http://www.cornell.edu/

IJSER © 2011 http://www.ijser.org