Abstract: Advances in clinical medical imaging have brought about the routine production of vast numbers of medical images that need to be analyzed. As a result an enormous amount of computer vision research effort has been targeted at achieving automated medical image analysis. Computed Tomography (CT) is highly accurate for diagnosing liver tumors. This study aimed to evaluate the potential role of the wavelet and the neural network in the differential diagnosis of liver tumors in CT images. The tumors considered in this study are hepatocellular carcinoma, cholangio carcinoma, hemangeoma and hepatoadenoma. Each suspicious tumor region was automatically extracted from the CT abdominal images and the textural information obtained was used to train the Probabilistic Neural Network (PNN) to classify the tumors. Results obtained were evaluated with the help of radiologists. The system differentiates the tumor with relatively high accuracy and is therefore clinically useful.
Abstract: In the last two decades radiofrequency ablation (RFA)
has been considered a promising medical procedure for the treatment
of primary and secondary malignancies. However, the needle-based
electrodes so far developed for this kind of treatment are not suitable
for the thermal ablation of tumors located in hollow organs like
esophagus, colon or bile duct. In this work a tubular electrode
solution is presented. Numerical and experimental analyses were
performed to characterize the volume of the lesion induced. Results
show that this kind of electrode is a feasible solution and numerical
simulation might provide a tool for planning RFA procedure with
some accuracy.
Abstract: The use of the oncologic index ISTER allows for a more effective planning of the radiotherapic facilities in the hospitals. Any change in the radiotherapy treatment, due to unexpected stops, may be adapted by recalculating the doses to the new treatment duration while keeping the optimal prognosis. The results obtained in a simulation model on millions of patients allow the definition of optimal success probability algorithms.
Abstract: NFκB activation plays a crucial role in anti-apoptotic responses in response to the apoptotic signaling during tumor necrosis factor (TNFa) stimulation in Multiple Myeloma (MM). Although several drugs have been found effective for the treatment of MM by mainly inhibiting NFκB pathway, there are no any quantitative or qualitative results of comparison assessment on inhibition effect between different single drugs or drug combinations. Computational modeling is becoming increasingly indispensable for applied biological research mainly because it can provide strong quantitative predicting power. In this study, a novel computational pathway modeling approach is employed to comparably assess the inhibition effects of specific single drugs and drug combinations on the NFκB pathway in MM, especially the prediction of synergistic drug combinations.
Abstract: The overall penumbra is usually defined as the
distance, p20–80, separating the 20% and 80% of the dose on the beam axis at the depth of interest. This overall penumbra accounts
also for the fact that some photons emitted by the distal parts of the source are only partially attenuated by the collimator. Medulloblastoma is the most common type of childhood brain tumor
and often spreads to the spine. Current guidelines call for surgery to remove as much of the tumor as possible, followed by radiation of the brain and spinal cord, and finally treatment with chemotherapy.
The purpose of this paper was to present results on an Uniformity of dose distribution in radiation fields surrounding the spine using film
dosimetry and comparison with 3D treatment planning software.
Abstract: The major objective of this paper is to introduce a new method to select genes from DNA microarray data. As criterion to select genes we suggest to measure the local changes in the correlation graph of each gene and to select those genes whose local changes are largest. More precisely, we calculate the correlation networks from DNA microarray data of cervical cancer whereas each network represents a tissue of a certain tumor stage and each node in the network represents a gene. From these networks we extract one tree for each gene by a local decomposition of the correlation network. The interpretation of a tree is that it represents the n-nearest neighbor genes on the n-th level of a tree, measured by the Dijkstra distance, and, hence, gives the local embedding of a gene within the correlation network. For the obtained trees we measure the pairwise similarity between trees rooted by the same gene from normal to cancerous tissues. This evaluates the modification of the tree topology due to tumor progression. Finally, we rank the obtained similarity values from all tissue comparisons and select the top ranked genes. For these genes the local neighborhood in the correlation networks changes most between normal and cancerous tissues. As a result we find that the top ranked genes are candidates suspected to be involved in tumor growth. This indicates that our method captures essential information from the underlying DNA microarray data of cervical cancer.
Abstract: Diagnosis can be achieved by building a model of a
certain organ under surveillance and comparing it with the real time
physiological measurements taken from the patient. This paper deals
with the presentation of the benefits of using Data Mining techniques
in the computer-aided diagnosis (CAD), focusing on the cancer
detection, in order to help doctors to make optimal decisions quickly
and accurately. In the field of the noninvasive diagnosis techniques,
the endoscopic ultrasound elastography (EUSE) is a recent elasticity
imaging technique, allowing characterizing the difference between
malignant and benign tumors. Digitalizing and summarizing the main
EUSE sample movies features in a vector form concern with the use
of the exploratory data analysis (EDA). Neural networks are then
trained on the corresponding EUSE sample movies vector input in
such a way that these intelligent systems are able to offer a very
precise and objective diagnosis, discriminating between benign and
malignant tumors. A concrete application of these Data Mining
techniques illustrates the suitability and the reliability of this
methodology in CAD.
Abstract: Tumour suppressors are key participants in the
prevention of cancer. Regulation of their expression through
miRNAs is important for comprehensive translation inhibition of
tumour suppressors and elucidation of carcinogenesis mechanisms.
We studies the possibility of 1521 miRNAs to bind with 873 mRNAs
of human tumour suppressors using RNAHybrid 2.1 and ERNAhybrid
programmes. Only 978 miRNAs were found to be
translational regulators of 812 mRNAs, and 61 mRNAs did not have
any miRNA binding sites. Additionally, 45.9% of all miRNA binding
sites were located in coding sequences (CDSs), 33.8% were located
in 3' untranslated region (UTR), and 20.3% were located in the
5'UTR. MiRNAs binding with more than 50 target mRNAs and
mRNAs binding with several miRNAs were selected. Hsa-miR-5096
had 15 perfectly complementary binding sites with mRNAs of 14
tumour suppressors. These newly indentified miRNA binding sites
can be used in the development of medicines (anti-sense therapies)
for cancer treatment.
Abstract: Early breast cancer detection is an emerging field of
research as it can save the women infected by malignant tumors.
Microwave breast imaging is based on the electrical property contrast
between healthy and malignant tumor. This contrast can be detected
by use of microwave energy with an array of antennas that illuminate
the breast through coupling medium and by measuring the scattered
fields. In this paper, author has been presented the design and
simulation results of the bowtie antenna. This bowtie antenna is
designed for the detection of breast cancer detection.
Abstract: A series of microarray experiments produces observations
of differential expression for thousands of genes across multiple
conditions.
Principal component analysis(PCA) has been widely used in
multivariate data analysis to reduce the dimensionality of the data in
order to simplify subsequent analysis and allow for summarization of
the data in a parsimonious manner. PCA, which can be implemented
via a singular value decomposition(SVD), is useful for analysis of
microarray data.
For application of PCA using SVD we use the DNA microarray
data for the small round blue cell tumors(SRBCT) of childhood
by Khan et al.(2001). To decide the number of components which
account for sufficient amount of information we draw scree plot.
Biplot, a graphic display associated with PCA, reveals important
features that exhibit relationship between variables and also the
relationship of variables with observations.
Abstract: This paper presents a novel approach to finding a
priori interesting regions in mammograms. In order to delineate those
regions of interest (ROI-s) in mammograms, which appear to be
prominent, a topographic representation called the iso-level contour
map consisting of iso-level contours at multiple intensity levels and
region segmentation based-thresholding have been proposed. The
simulation results indicate that the computed boundary gives the
detection rate of 99.5% accuracy.
Abstract: MicroRNAs (miRNAs) are a class of non-coding
RNAs that hybridize to mRNAs and induce either translation
repression or mRNA cleavage. Recently, it has been reported that
miRNAs could possibly play an important role in human diseases. By
integrating miRNA target genes, cancer genes, miRNA and mRNA
expression profiles information, a database is developed to link
miRNAs to cancer target genes. The database provides experimentally
verified human miRNA target genes information, including oncogenes
and tumor suppressor genes. In addition, fragile sites information for
miRNAs, and the strength of the correlation of miRNA and its target
mRNA expression level for nine tissue types are computed, which
serve as an indicator for suggesting miRNAs could play a role in
human cancer. The database is freely accessible at
http://ppi.bioinfo.asia.edu.tw/mirna_target/index.html.
Abstract: The progress of concentrations of particular heavy metals was assessed in chosen localities in region Moravia, the Czech Republic, from 2007 to 2009. Particular metals were observed in localities with various types and characterization of zone. Pb, Ni, As and Cd were emphasized as a result of their toxicity and potential adverse health effect to the exposed population. The progress of metal concentrations and their health effects in the most polluted localities were examined. According to the results, the air pollution limit values were not exceeded. Based on the health risk assessment, the probability of developing tumorous diseases is acceptable, except for the increased probability of cancer risk from long-term exposure to As.
Abstract: The main objective of this paper is to provide an efficient tool for delineating brain tumors in three-dimensional magnetic resonance images and set up compression-transmit schemes to distribute result to the remote doctor. To achieve this goal, we use basically a level-sets approach to delineating brain tumors in threedimensional. Then introduce a new compression and transmission plan of 3D brain structures based for the meshes simplification, adapted for time to the specific needs of the telemedicine and to the capacities restricted by wireless network communication. We present here the main stages of our system, and preliminary results which are very encouraging for clinical practice.
Abstract: pH-sensitive drug targeting using nanoparticles for
cancer chemotherapy have been spotlighted in recent decades. Graft
copolymer composed of poly (L-histidine) (PHS) and dextran
(DexPHS) was synthesized and pH-sensitive nanoparticles were
fabricated for pH-responsive drug delivery of doxorubicin (DOX).
Nanoparticles of DexPHS showed pH-sensitive changes in particle
sizes and drug release behavior, i.e. particle sizes and drug release rate
were increased at acidic pH, indicating that DexPHS nanoparticles
have pH-sensitive drug delivery potentials. Antitumor activity of
DOX-incorporated DexPHS nanoparticles were studied using CT26
colorectal carcinoma cells. Results indicated that fluorescence
intensity was higher at acidic pH than basic pH. These results
indicated that DexPHS nanoparticles have pH-responsive drug
targeting.
Abstract: The p53 tumor suppressor gene plays two important
roles in genomic stability: blocking cell proliferation after DNA
damage until it has been repaired, and starting apoptosis if the
damage is too critical. Codon 72 exon4 polymorphism (Arg72Pro) of
the P53 gene has been implicated in cancer risk. Various studies have
been done to investigate the status of p53 at codon 72 for arginine
(Arg) and proline (Pro) alleles in different populations and also the
association of this codon 72 polymorphism with various tumors. Our
objective was to investigate the possible association between P53
Arg72Pro polymorphism and susceptibility to colorectal cancer
among Isfahan and Chaharmahal Va Bakhtiari (a part of south west
of Iran) population. We investigated the status of p53 at codon 72 for
Arg/Arg, Arg/Pro and Pro/Pro allele polymorphisms in blood
samples from 145 colorectal cancer patients and 140 controls by
Nested-PCR of p53 exon 4 and digestion with BstUI restriction
enzyme and the DNA fragments were then resolved by
electrophoresis in 2% agarose gel. The Pro allele was 279 bp, while
the Arg allele was restricted into two fragments of 160 and 119 bp.
Among the 145 colorectal cancer cases 49 cases (33.79%) were
homozygous for the Arg72 allele (Arg/Arg), 18 cases (12.41%) were
homozygous for the Pro72 allele (Pro/Pro) and 78 cases (53.8%)
found in heterozygous (Arg/Pro).
In conclusion, it can be said that p53Arg/Arg genotype may be
correlated with possible increased risk of this kind of cancers in south
west of Iran.
Abstract: Since hyaluronic acid (HA) receptor such as CD44 is
over-expressed at sites of cancer cells, HA can be used as a targeting
vehicles for anti-cancer drugs. The aim of this study is to synthesize
block copolymer composed of hyaluronic acid and
poly(ε-caprolactone) (HAPCL) and to fabricate polymeric micelles for
anticancer drug targeting against CD44 receptor of tumor cells.
Chemical composition of HAPCL was confirmed using 1H NMR
spectroscopy. Doxorubicin (DOX) was incorporated into polymeric
micelles of HAPCL. The diameters of HAPHS polymeric micelles
were changed around 80nm and have spherical shapes. Targeting
potential was investigated using CD44-overexpressing. When
DOX-incorporated polymeric micelles was added to KB cells, they
revealed strong red fluorescence color while blocking of CD44
receptor by pretreatment of free HA resulted in reduced intensity,
indicating that HAPCL polymeric micelles have targetability against
CD44 receptor.
Abstract: The main goal in this paper is to quantify the quality of
different techniques for radiation treatment plans, a back-propagation
artificial neural network (ANN) combined with biomedicine theory
was used to model thirteen dosimetric parameters and to calculate
two dosimetric indices. The correlations between dosimetric indices
and quality of life were extracted as the features and used in the ANN
model to make decisions in the clinic. The simulation results show
that a trained multilayer back-propagation neural network model can
help a doctor accept or reject a plan efficiently. In addition, the
models are flexible and whenever a new treatment technique enters
the market, the feature variables simply need to be imported and the
model re-trained for it to be ready for use.
Abstract: Pattern recognition is the research area of Artificial Intelligence that studies the operation and design of systems that recognize patterns in the data. Important application areas are image analysis, character recognition, fingerprint classification, speech analysis, DNA sequence identification, man and machine diagnostics, person identification and industrial inspection. The interest in improving the classification systems of data analysis is independent from the context of applications. In fact, in many studies it is often the case to have to recognize and to distinguish groups of various objects, which requires the need for valid instruments capable to perform this task. The objective of this article is to show several methodologies of Artificial Intelligence for data classification applied to biomedical patterns. In particular, this work deals with the realization of a Computer-Aided Detection system (CADe) that is able to assist the radiologist in identifying types of mammary tumor lesions. As an additional biomedical application of the classification systems, we present a study conducted on blood samples which shows how these methods may help to distinguish between carriers of Thalassemia (or Mediterranean Anaemia) and healthy subjects.
Abstract: Accurate assessment of the primary tumor response to
treatment is important in the management of breast cancer. This
paper introduces a new set of treatment evaluation indicators for
breast cancer cases based on the computational process of three
known metrics, the Euclidian, Hamming and Levenshtein distances.
The distance principals are applied to pairs of mammograms and/or
echograms, recorded before and after treatment, determining a
reference point in judging the evolution amount of the studied
carcinoma. The obtained numerical results are indeed very
transparent and indicate not only the evolution or the involution of
the tumor under treatment, but also a quantitative measurement of the
benefit in using the selected method of treatment.