Electronic nose technology for detecting lung cancer patients in an Egyptian population = (Titelsatznr. 59425)

[ MARC ]
000 -LEADER
fixed length control field 08157nam a22002417a 4500
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 181226s2016 ua a|||g bm|| 00| 0 eng d
040 ## - CATALOGING SOURCE
Transcribing agency SOUL
041 ## - LANGUAGE CODE
Language code of text/sound track or separate title ara
Language code of original eng
082 04 - DEWEY DECIMAL CLASSIFICATION NUMBER
Edition number 21
Classification number 612.014
Item number E F
100 1# - MAIN ENTRY--PERSONAL NAME
9 (RLIN) 4817
Personal name Abdel Mohdy, Taher Saeed.
245 10 - TITLE STATEMENT
Title Electronic nose technology for detecting lung cancer patients in an Egyptian population =
Remainder of title استخدام تقنية الأنف إلكترونى فى اكتشاف مرضى سرطان الرئة فى مجموعة من المصريين \
Statement of responsibility, etc. Taher Saeed Abdel Mohdy ; Supervised by Ehab Ibrahim Abdou Mohamed, Hanaa Ahmed Shafiq.
246 03 - VARYING FORM OF TITLE
Title proper/short title استخدام تقنية الأنف إلكترونى فى اكتشاف مرضى سرطان الرئة فى مجموعة من المصريين
260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT)
Place of publication, distribution, etc. Alexandria :
Name of publisher, distributor, etc. Alexandria University.Medical Research Institute.Department of Medical Biophysics.
Date of publication, distribution, etc. 2016..
300 ## - PHYSICAL DESCRIPTION
Extent 96 p. :
Other physical details ill. ;
Dimensions 27 cm +
Accompanying material 1 CD.
500 ## - GENERAL NOTE
General note Thesis(M.S.)-Alexandria University.Medical Research Institute.Department of Medical Biophysics.
504 ## - BIBLIOGRAPHY, ETC. NOTE
Bibliography, etc Includes bibliographical references, index
520 ## - SUMMARY, ETC.
Summary, etc. the Arab league countries nationals, of which 13,826 cases (79.7%) were males and 2,806
(20.3%) were females. The majority of cases were reported in Arab countries in North
Africa such as Egypt (20.6%). LC is the one of the most causes of death in the global
population. The disease has become an epidemic as LC death rates have risen dramatically
over the last century. Worldwide, there are estimated to be 1.8 million new cases in 2012
(12.9 of the total). It was a rare disease at the start of the 20th century, but being vulnerable
to new causes and an increasing life span combined to make LC the most common cancer
in the world for several decades.
(6)
Patients with LC present with: persistent cough, dyspnea, wheeze, hemoptysis
(coughing up blood for several days in succession), chest or shoulder pain and discomfort.
Adding that, more than half of all patients diagnosed with lung cancer present with
advanced disease at the time of diagnosis. The main diagnostic procedures for lung cancer
are chest radiography, chest computed tomography (CT)/ PET scan, sputum cytology or
pleural fluid cytology and bronchoscopy. Biopsy for histopathological evaluation is the
gold standard technique for diagnosing lung cancer.
(64)
In the past, screening chest X-rays had been evaluated in the effort of early detection
of LC in high-risk patients, but no decline in mortality rates has been achieved. Screening
low dose CT had been evaluated because of its higher sensitivity; nevertheless, CT may
produce false positive results (For each true positive scan, there are about 19 false positive
scans), which increase the number of unnecessary invasive diagnostic procedures needed
to verify the CT findings. Sputum cytology screening test had not been found to be of
diagnostic relevance as well and with no proven effect of screening on mortality rates,
there is concern that screening may cause over-diagnosis, unnecessary anxiety, radiation
exposure and expense. In order to increase the chances of a successful treatment and
prevent the consequences of the disease, LC must be diagnosed as early as possible.
(64)
There is a need to develop rapid, cheap, convenient, and accurate tests for the diagnosis of
infectious diseases, to initiate rapid pathogen detection and subsequent specific treatment.
An Electronic Nose is a device use to perceive odors or flavors, likewise the human
olfactory system, as a global fingerprint which consists of three essential elements: an
array of olfactory receptor cells situated in the roof of the nasal cavity, the olfactory bulb
which is situated just above the nasal cavity; and the brain, in an e-nose there are three
components; a) a sampling conditioning unit, which delivers the odor volatiles from the
headspace above the sample; b) a test chamber in which the sensor array is based; and c) a
processing unit which analyzes the sensor responses for pattern recognition.
(56)
An Artificial Neural Network (ANN) is an information processing paradigm that is
inspired by the way biological nervous systems, such as the brain, process information.
The key element of this paradigm is the novel structure of the information processing
system. It is composed of a large number of highly interconnected processing elements
(neurons) working in unison to solve specific problems. ANNs, like people, learn by
example. An ANN is configured for a specific application, such as pattern recognition or
data classification, through a learning process. Learning in biological systems involves
adjustments to the synaptic connections that exist between the neurons. Neural networks,
with their remarkable ability to derive meaning from complicated or imprecise data, can be
used to extract patterns and detect trends that are too complex to be noticed by either
humans or other computer techniques. A trained neural network can be thought of as an
”expert” in the category of information it had been given to analyze. This expert can then
be used to provide projections given new situations of interest.
(49)
In the present study we applied the E-Nose technology to measure qualitative odor
differences of blood, breath, urine from HC participants and LC patients, biopsy samples
from histopathologically proven Egyptian patients with LC to estimate the data using an
ANN for the classification of all participants and analysis of output results and diagnosis.
The results of the blood, breath, urine and biopsy samples of the all study groups
were analyzed by the portable E-Nose PEN3 as qualitative analysis and sensor response
patterns of the E-Nose were processed by using the Winmuster software package (Version
1.6.2.2, Airsense Analytics GmbH, Schwerin, Germany) for multidimensional plots and
further analysis using PCA and LDA classification among LC patients and HC
participants.
A clear distinction between both groups is evident in Figure (30) A through C for the
same biological samples when plotted together, where both principal components #1 and
#2 show that variance in signals are 95.46, 82.01, and 91.66%, respectively, which means
that E-Nose was capable of identifying samples from each group with less false-positive
LC or false-negative HC results. This lends to support the fact that VOCs found in the
blood, breath, urine of LC patients are significantly different from those for HC
participants.
A clear distinction between both groups is evident in Figure (33) A through C for the
same biological samples when plotted together, where both Linear discriminant #1 and #2
show that variance in signals are 32.29, 38.86 and 41.22 % respectively, which means that
E-Nose was capable of identifying samples from each group with less false-positive HC or
false-negative LC results. This also lends to support the fact that the VOCs found in the
blood, breath, and urine of LC patients are significantly different from those for HC
participants.
Matlab Neural Network Pattern Recognition Toolbox version (R2015a) is used to
predict and classify and recognize patterns. The confusion matrix, ROC, and performance
plot of the results are displayed, the correct predictions together with the percentage of
output correct classification, which reached almost 100% for all group samples, with less
misclassification. Based on these features, the predictive accuracy, sensitivity, specificity
of the proposed diagnosis model of the ANN reached a good percentage with less false
positive and less false negative results. That is accurately identified LC Patients from HC
participants with great precision, for all measured blood, urine, and breath samples.
546 ## - LANGUAGE NOTE
Language note English Text and abstracts in Arabic and English.
650 40 - SUBJECT ADDED ENTRY--TOPICAL TERM
9 (RLIN) 4818
Topical term or geographic name as entry element Medical Biophysics.
700 1# - ADDED ENTRY--PERSONAL NAME
9 (RLIN) 4819
Personal name Mohamed, Ehab Ibrahim Abdou
Relator term supervisor
710 2# - ADDED ENTRY--CORPORATE NAME
Corporate name or jurisdiction name as entry element Alexandria University.
Subordinate unit Medical Research Institute.
-- Department of Medical Biophysics.
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme
Koha item type Theses
Item part Faculty of Medicine كلية الطب
Exemplare
Withdrawn status Lost status Source of classification or shelving scheme Damaged status Not for loan Permanent location Current location Shelving location Date acquired Full call number Barcode Date last seen Price effective from Koha item type
          6october 6october 1208 2019-01-02 612.014 E F SOULE208TH0769 2021-08-25 2019-01-02 Theses
www.soul.o6u.edu.eg

E-Mail: soul@o6u.edu.eg
Address: October 6 city – Central Axis – Next to El Hosary mosque.
Tell: (+202) 38376382
Fax: (+202) 38376280



Developed and implemented by ILC EG