A MEDICAL INFORMATION SYSTEM BASED ON ORACLE
TECHNOLOGIES
Liana Stanescu, Dumitru Dan Burdescu, Cosmin Stoica Spahiu, Anca Ion
Faculty of Automation, Computers and Electronics, University of Craiova, Romania
Cristian Guran
BATM Systems, Craiova, Romania
Keywords: Medical information system, content-based image query, color histogram, texture, shape, medical imagery.
Abstract: The paper presents an information system based on Oracle technologies (Oracle Database, Oracle
interMedia and Oracle JDeveloper) dedicated for managing and querying medical multimedia databases.
The database contains images related to the internal medicine area. This on-line application allows creation
of complex medical files of patients that can be viewed and updated both by internist and general
practitioner. The main functions of the application are: managing patients contact information,
examinations, imagery and content-based visual query using color, texture and shape characteristics. It can
be used in individual offices, laboratories or in the hospital clinics and departments. The application
provides security and confidentiality for patient’s data.
1 INTRODUCTION
The information systems that are used in many areas
(financial, government, education, medical, etc) are
dealing nowadays with an increased demand for
managing efficiently not only the traditional
information, but also the multimedia content. The
management of multimedia data has a series of
unique aspects because multimedia objects are large,
relatively unstructured and in a variety of formats.
The indexing of the multimedia content is necessary
in order to have an efficient search.
One of the areas where both alphanumerical
information and multimedia data (images, video) is
necessary is the medical domain. For establishing
the diagnosis and treating the patients, the specialist
completes medical records with treatment, analyses
and other investigations, most of them of imagistic
nature. A big part of the medical devices uses the
DICOM standard, the result being a file with a
standard structure including alphanumeric
information, images or video data.
One of the database systems that provide
extended capabilities for managing multimedia
content is Oracle Database with Oracle interMedia.
This system was chosen to implement the medical
information software that is presented in this paper.
Oracle interMedia is part of the Oracle Database
11g, being thus possible the managing of multimedia
content (image, audio, video) in an integrated
fashion with the traditional information. Oracle
interMedia component extends to the multimedia
content the possibility offered by Oracle Database to
manage data in an efficient, secure and precise way
(Oracle 2007, Chigrik, 2007).
The paper presents a medical information system
based on Oracle that has as main scope to manage
both traditional information and images. It is also
studied the speed and quality of the content-based
visual query process that is done using Oracle
interMedia. This type of query needs to select an
image representing the query image and to find all
the similar images in the database taking into
account the color, texture and shape characteristics
(Del Bimbo, 2001, Faloutsos, 2005, Khoshafian,
1996, Smith, 1997). The tests were effectuated on a
database with 540 medical images from the digestive
tract representing patients having the next diagnoses:
ulcer, colitis, polyps, ulcerous tumor and
esophagitis.
417
Stanescu L., Dan Burdescu D., Stoica Spahiu C., Ion A. and Guran C. (2008).
A MEDICAL INFORMATION SYSTEM BASED ON ORACLE TECHNOLOGIES.
In Proceedings of the Tenth International Conference on Enterprise Information Systems - DISI, pages 417-420
DOI: 10.5220/0001679604170420
Copyright
c
 SciTePress

2 THE INFORMATION SYSTEM
DESCRIPTION
2.1 Necessity
Internal medicine can be considered as basics for
many specialties and needs large amounts of
paraclinical explorations performed by different
devices that generates visual and numerical data
(radiology, echography, endoscopies, tomography,
electrocardiogram, MRI, histological cups etc.) used
for diagnosis and for follow-up of treatment or
evolution. Numerical information is given by
functional and biological assays while various
imagistic devices provide image data. That is why
internal medicine departments usually accumulates
huge quantities of medical data, including thousands
of image files, millions of numerical values and
thousands of written reports. As a result, a complex
application to manage and query a database
containing information and images from medical
domain is needed.
Oracle has been chosen because of the qualities
and the functions that it provides. The application
was developed under Oracle Jdeveloper. It provides
a completely integrated Java environment for
development, implementation and execution of the
multilevel Internet applications. JDeveloper gives
the possibility to build applications integrated with
the Oracle Databases servers. The Java applications
can be executed on all the 3 levels of the Internet
Computing architecture: client, application server
and databases server (Oracle Application
Development Framework, 2006).
2.2 The Database Structure
Applying the normalization process (Elmasri, 1994),
the database proposed for this on-line application
will be described further on. The database contains a
number of tables created when installing the
application. The tables contain a series of codes that
makes easier the work of updating patient
information and the investigations. These tables are:
medical units, users groups and users.
The data confidentiality is ensured by user name
and password that are provided separately for each
unit. In order to increase the data security, the
password is encrypted. Each doctor has access to
information regarding his own patients, but he can
share some data that can be seen by other specialists.
He can also access both statistical and scientific data
regarding all patients in database but in this case the
identification data about patients is hidden and the
ID number, name and address are blinded. At
information management level, anonimizing all
information concerning clinical data ensures
confidentiality; diagnosis, paraclinical information,
treatments are also blinded and only statistical data
can be viewed. On the other hand, the office
secretary can see personal information about patients
and referring doctors, but no diagnosis and treatment
elements are accessible. Other tables are:
- Diagnosis table.
- Analyses table codifies paraclinical and
biological data.
- Clinical examination table.
- Patient groups table.
The following tables are the most important in
the database because they store information about
patients, examinations, investigations and results:
- Patients table is used for storing information
about patient’s visits: personal ID number,
name, doctor, county, city, address, phone/fax
number, email and program – if any.
- A patient might have several examinations, for
each of them storing in the Consulting Table,
the diagnosis, date and treatment. Each
examination might contain one or several
clinical examinations (it is stored code,
description, a series of analyses identified by
code and obtained value).
- Images table stores information about still
images that were obtained from a patient
during his whole disease history.
This table has two special fields in order to store
the images and to realize the content based visual
query: image, having ORDSYS.ORDIMAGE type
and image_sign, having the ORDSYS.
ORDIMAGESIGNATURE type. InterMedia uses
objects to describe multimedia databases:
ORDAudio for audio data; ORDImage static
images; ORDVideo for video sequences and
ORDDoc for heterogeneous data (Oracle, 2007). At
the insertion in the database of the multimedia data
using interMedia, the metadata for still images is
automatically extracted (Oracle, 2007).
2.3 The Main Functions
2.3.1 Patient’s Information Management
This function is one of the main functions in the
application, and the information about patients has
the following organization:
ICEIS 2008 - International Conference on Enterprise Information Systems
418

a) Contact information
This option refers to the information for patient
identification: personal ID number, name, address,
phone, fax, email, category and National License
Number of the examining doctor.
b) Examinations
The management of this information is
implemented in a window that contains several
secondary windows. The first secondary window
contains a record for each patient examination with
the following information: examination date,
diagnosis and results of the visit (solved/unsolved).
This window is associated with four secondary ones,
having the following functions:
1. Collecting data from clinical examination.
2. Collecting numerical data from laboratories.
3. Storing, as descriptive text, the results of
various investigations.
4. Storing treatment recommendations and
prescriptions resulting from diagnosis.
c) Imagery
This option gives access to all the functions of
the application concerning the imagistic data for a
specific patient and provided by different devices
(echograph, endoscope, MRI, CT, etc). For storing
in the database, these images can be loaded from
saved files or can be imported directly from medical
devices using a real time acquisition system.
Viewing an image stored in the database implies not
only displaying the image, but also viewing the
metadata attached to it. Oracle Multimedia provides
a set of server-based manipulation functions: scaling
and cropping, arbitrary rotation, flip, mirror, gamma
correction, contrast enhancement, re-quantization
and alpha channel (Oracle, 2007). A part of these
processing functions used for enhancing the image,
were also implemented in this system.
2.3.2 Content-Based Image Query
The directions of the medical field where content-
based visual queries methods can be used are well
known (Müller et al, 2005, Lehmann et al, 2006). As
a result, we implemented in the application content-
based visual query methods using color and texture
characteristics. Generally speaking, there are two
methods to find images:
- Using information that was manually
introduced in tables
- Using the images characteristics that are
automatically extracted
InterMedia gives the possibility to combine
these 2 possibilities: there are used text type data to
describe the semantic of the image, and
ORDImageSignature data type for content-based
queries that uses main attributes of the image.
The search criteria used by InterMedia are color,
texture and shape. Coordinates represent the
locations of these visual attributes inside the image.
These coordinates are not used independently to
recognize shapes, but along with one of these three
visual attributes. Once the image is inserted in the
database, it is analysed and stored as a
characteristics vector representing a compact
representation of the content. This vector is called
the image signature. The OrdImageSignature type
has methods for image comparison. The image
signature is extracted by segmenting the image
based on the color spots that compose the image.
In the content-based visual query process each
image from the database is compared with a query
image that can be another image from database, or
an external image.
In the retrieval process it is assigned a weight to
each visual attribute. The similarity between two
images is calculated for each attribute as a distance
(score) between images. The score of the whole
image is a number between 0 (there is no difference)
– 100 (maximum possible difference). It represents
the sum of all the scores, taking into consideration
the attributes’ weights. In the retrieval process it is
used a threshold value. If the sum is smaller than the
specified threshold value, the images are considered
to be similar, otherwise not.
To execute this process, the user must select an
image from the database and activate the Compare
Signature button. In the new window, the user has
the possibility to setup the parameters needed for the
retrieval (color, texture, shape and location). In
figure 1, the window that implements all the
operations described above is presented.
Figure 1: The window for content-based visual query.
A MEDICAL INFORMATION SYSTEM BASED ON ORACLE TECHNOLOGIES
419

3 EXPERIMENTS AND RESULTS
The experiments were performed in the following
conditions. It was created a database with 540 color
images from the digestive area. The images were
taken from patients having the following diagnoses:
polyps, ulcer, esophagites, colitis and ulcerous
tumor. For each patient there are more images of the
same ill area, made from different angles.
In order to execute the query procedure the
following steps are necessary:
• a query image is chosen
• the similarity between the query image and
every target image from the database is
computed
• the images are displayed in ascending order of
the computed distance
Table 1: Experimental results.
For each query, the relevant images have been
established. Each of the relevant images has become
in its turn a query image, and the final results for a
query are an average of these individual results.
These experiments have considered the color and
texture attributes of the medical images, each of
them having equal weights (0.5). The motivation of
this choice is bound by the nature of medical images
from digestive area with different diagnosis that
generates changes both in color and texture of the ill
tissue. In this case the shape parameter is less
important. The experimental results are summarized
in table 1.
4 CONCLUSIONS AND FUTURE
WORK
This paper presents the main functions of an
information system based on the newest Oracle
technology (Oracle Database, interMedia and
Jdeveloper). A special attention is provided to study
the content-based visual query process using Oracle
interMedia. There have been presented the
experimental results of this process that used a
database with 540 medical images from the digestive
tract. The queries are based on two attributes: color
and texture. The results are satisfactory and
motivates next studies in the following directions:
• The experiments will include a database with
much more medical images
• There will be tested more combinations for
color and texture weights, taking into
consideration the doctors recommendations:
there are cases where the variations in color
represent a sign of a ill tissue and cases where
changes in texture are important
• It will be analyzed the quality of the content-
based visual query process when there are
used images from different parts of the body,
not only from digestive area.
REFERENCES
Chigrik, A., 2007. SQL Server 2000 vs Oracle 9i.
http://www.mssqlcity.com/Articles/Compare/sql_server_v
s_oracle.htm
Del Bimbo, A., 2001. Visual Information Retrieval,
Morgan Kaufmann Publishers. San Francisco USA.
Faloutsos, C., 2005. Searching Multimedia Databases by
Content. Springer.
Khoshafian, S., Baker, A.B., 1996. Multimedia and
Imaging Databases, Morgan Kaufmann Publishers.
Inc. San Francisco California
Muller, H., Rosset, A., Garcia, A., Vallee, J.P.,
Geissbuhler, A., 2005. Benefits of Content-based
Visual Data Access. In Radiology. Radio Graphics.
25:849-858
Oracle, 2007. Oracle InterMedia: Managing Multimedia
Content.
http://www.oracle.com/technology/products/intermedi
a/pdf/10gr2_collateral/imedia_twp_10gr2.pdf
Smith, J.R., 1997. Integrated Spatial and Feature Image
Systems: Retrieval, Compression and Analysis, Ph.D.
thesis, Graduate School of Arts and Sciences.
Columbia University.
Elmasri R, Navathe S.B., 1994. Fundamentals of
Database Systems, Addison - Wesley Publishing
Company, second edition
Oracle Apllication Development Framework, 2006.
http://download.oracle.com/otn_hosted_doc/jdeveloper/10
13/adfdevguide.pdf
Lehmann, T.M., Deselaers, T., Schubert, H., Güld, M.O.,
Thies, C., Fischer. B., Spitzer, K., 2006.
IRMA - a content-based approach to Image Retrieval
in Medical Applications. In: Khosrow-Pour M (ed):
Emerging Trends and Challenges in Information
Technology Management. Proceedings of the 2006
Information Resources Management Association
International Conference, pp. 911--912
Query Nr. of
relevant
images
Nr. of relevant
images retrieved in
the first 5
Polyps 208 4
Colitis 88 4
Ulcer 140 4
Ulcerous Tumor 40 3
Esophagitis 64 3
ICEIS 2008 - International Conference on Enterprise Information Systems
420