|
|
|
 |
Search published articles |
 |
|
Showing 7 results for Abdolmaleki
P. Abdolmaleki, M. Yarmohammadi, M. Gity,
Volume 1, Issue 4 (3-2004)
Abstract
Background: We designed an algorithmic model based on the logistic regression analysis and a non-algorithmic model based on the Artificial Neural Network (ANN). Materials and methods: The ability of these models was compared together in clinical application to differentiate malignant from benign breast tumors in a study group of 161 patients' records. Each patient’s record consisted of 6 subjective features extracted from MRI appearance. These findings were encoded as features for an ANN as well as a logistic regression model (LRM) to predict biopsy outcome. After both models had been trained perfectly on samples (n=100), the validation samples (n=61) were presented to the trained network as well as the established LRMs. Finally, the diagnostic performance of models were compared to that of the radiologist in terms of sensitivity, specificity and accuracy, using receiver operating characteristic curve (ROC) analysis. Results: The average output of the ANN yielded a perfect sensitivity (98%) and high accuracy (90%) similar to that one of an expert radiologist (96% and 92%) while specificity was smaller than that (67% verses 80%). The output of the LRM using significant features showed improvement in specificity from 60% for the LRM using all features to 93% for the reduced logistic regression model, keeping the accuracy around 90%. Conclusion: Results show that ANN and LRM prove the relationship between extracted morphological features and biopsy results. Using statistically significant variables reduced LRM outperformed of ANN with remarkable specificity while keeping high sensitivity is achieved. Iran . J. Radiat. Res., 2004 1(4): 217-228
P. Abdolmaleki, M. Mokhtari Dizaji, M.r. Vahead, M. Gity,
Volume 2, Issue 1 (6-2004)
Abstract
Background: Logistic discriminant method was applied to differentiate malignant from benign in a group of patients with proved breast lesions on the basis of ultrasonic parameters. Materials and Methods: Our database include 273 patients' ultrasonographic pictures consisting of 14 quantitative variables. The measured variables were ultrasound propagation velocity, acoustic impedence and attenuation coefficient at 10 MHz in breast lesions at 20, 25, 30 and 35 º C temperature, physicsl density and age. This database was randomly divided into the estimation of 201 and validation of 72 samples. The estimation samples were used to build the logistic
discriminant model, and validation samples were used to validate the performance. Finally,
important criteria such as sensitivity, specificity, accuracy and area under the receiver operating characteristic curve (ROC) were evaluated. Results: Our results showed that the logistic discriminant method was able to classify correctly 67 out of 72 cases presented in the validation sample. The results indicate a remarkable
diagnostic accuracy of 93%. Conclusion: A logistic discriminantor approach is capable of predicting the probability of malignancy of breast cancer. Features extracted from ultrasonic measurement on ultrasound imaging is used in this approach. Iran . J. Radiat. Res., 2004 2 (1): 27-34
P. Abdolmaleki, H. Abrishami-Moghddam, M. Gity, M. Mokhtari-Dizaji, A. Mostafa,
Volume 3, Issue 3 (12-2005)
Abstract
ABSTRACT Background: A computer aided diagnosis system was established using the wavelet transform and neural network to differentiate malignant from benign in a group of patients with histo-pathologically proved breast lesions based on the data derived independently from time-intensity profile. Materials and Methods: The performance of the artificial neural network (ANN) was evaluated using a database with 105 patients' records each of which consisted of 8 quantitative parameters mostly derived from time-intensity profile using wavelet transform. These findings were encoded as features for a three-layered neural network to predict the outcome of biopsy. The network was trained and tested using the jackknife method and its performance was then compared to that of the radiologists in terms of sensitivity, specificity and accuracy using receiver operating characteristic curve (ROC) analysis. Results: The network was able to classify correctly the 84 original cases and yielded a comparable diagnostic accuracy (80%), compared to that of the radiologist (85%) by performing a constructive association between extracted quantitative data and corresponding pathological results (r=0.63, p<0.001). Conclusion: An ANN supported by wavelet transform can be trained to differentiate malignant from benign breast tumors with a reasonable degree of accuracy.
N. Sarayegord Afshari, F. Abbasisiar, Dr. P. Abdolmaleki, M. Ghiassi Nejad,
Volume 7, Issue 3 (12-2009)
Abstract
Background: Since 40K is the most important
natural radionuclide in the environment, its
concentration was measured for all milk and milk
powder samples consumed in Tehran-Iran. Milk was
chosen, since because it is a reliable indicator of the
general population intake of certain radionuclide, and
many environmental programs have been applied for
its safety. Materials and Methods: Measurements
was done using a CANBERRA gamma spectrometer
Model No. S100. Forty one milk and milk powder
samples were choosen for the gamma spectroscopy
analysis. Results: The average activity concentrations
for 40K in the samples were calculated, 31.0 ± 6.1
and 17.1 ± 3.3 Bq.kg-1, in milk and milk powder
respectively. These data correspond to the effective
dose of 14 μSv.year-1 for adults and in the range of
6.4-15.9 μSv.day-1 for children. Conclusion: Considering
the obtained data from liquid milk samples, an
almost uniform distribution of 40K can also be
obtained. Furthermore, the calculated effective doses
were too low to induce important health hazards
however, the data useful for monitoring. Iran. J. Radiat.
Res., 2009 7 (3): 159-164
M.r. Deevband, P. Abdolmaleki, M.r. Kardan, H.r. Khosravi, M. Taheri, F. Nazeri, N. Ahmadi,
Volume 9, Issue 2 (9-2011)
Abstract
Background: The Poly-Allyl Diglycol Carbonate
(PADC) detector is of particular interest for
development of a fast neutron dosimeter. Fast
neutrons interact with the constituents of the CR-39
detector and produce H, C and O recoils, as well as
(n, α) reaction. These neutron- induced charged
particles contribute towards the response of CR-39
detectors. Material and Methods: Electrochemical
etching was used to enlarge track diameter which
was made by low energy recoil protons. Before
electrochemical etching, a chemical etching was
performed for 1 hour. The responses were also
calculated by Monte Carlo simulations, using MCNPX
code in different energy bins considering H, C and O
recoils. The total registered efficiency and partial
contributions of the efficiency, due to interactions
with each constituent of CR-39, were calculated.
Results: The optimized condition of etchant was
obtained to be 6N KOH 15kV.cm-1, and 6 hours
etching time. The obtained results show that track
efficiency of CR-39 was a function of incident neutron
energy. The tracks caused by O and C recoil nuclei
were negligible for neutron energies lower than 1
MeV. At neutron energies lower than 1 MeV, only
recoil protons would have sufficient energy to leave
visible tracks. But, O and C recoils had important
contributions in overall response of PADC at neutron
energies of few MeV. Conclusion: The efficiency of a
CR-39 based dosemeter could be calculated by
MCNPX code and the results were in a good agreement
with experimental results in energy range of
241Am – Be bare source and 241Am-Be was softened
with a spherical polyethylene moderator of radius of
20 cm. Iran. J. Radiat. Res., 2011 9(2): 95-102
E. Heshmati, Dr. H. Mozdarani, P. Abdolmaleki, K. Khoshaman,
Volume 10, Issue 1 (6-2012)
Abstract
Background: Gemcitabine (2′, 2′-difluoro-2′-
deoxycytidine, an analogue of deoxycytidine) is a
relatively new drug with wide range of anti-cancer
activity. In this study, radiosensitizing effects of
gemcitabine was investigated on HeLa and MRC5
human originated cell lines under both chronically
hypoxic and normoxic conditions using the
micronucleus (MN) assay. Materials and Methods:
For induction of chronic hypoxia, the cell culture
flasks were saturated with N2 gas. To evaluate the
radiosensitizing effects, in the presence of the
non-genotoxic concentration (1ng/ml) of gemcitabine,
cells were exposed to different doses (0.5, 1, 2 Gy) of
X-ray in both chronically hypoxic and normoxic
conditions. Results: Results showed that there was
no significant difference in MN induction under
chronically hypoxic and normoxic condition when
using 1 ng/ml gemcitabine alone, however in the
absence of drug, MN induction was significantly
different in irradiated cells (P<0.01). Radiosensitizing
effects of gemcitabine in chronic hypoxic condition
was greater than normoxic condition in both cell lines
(P<0.01), although more pronounced in HeLa cells.
Conclusions: Radiosensitizing effects and greater
dose modifying factor of gemcitabine under depleted
oxygen condition is not clearly understood. It might be
due to depletion of deoxynocleotides pools via
inhibition of ribonucleotide reductase and
mismatched nucleosides incorporation into DNA after
radiation exposure. Iran. J. Radiat. Res., 2012 10(1):
11-18
S. Bijari, A. Jahanbakhshi, Ph.d P. Abdolmaleki,
Volume 21, Issue 2 (4-2023)
Abstract
Background: Glioma is the most common type of tumor in the nervous system. Glioma grading remains challenging despite advancements in diagnostic and treatment systems. Preoperative classification is essential to determining optimal treatment and prognosis for gliomas. This study aimed to use magnetic resonance imaging (MRI) to develop accurate nomogram models for glioma grading. Materials and Methods: Eighty-three patients who had undergone a glioma biopsy from June 2017 to November 2021 were retrospectively collected. Two multiparametric MRIs were acquired: T2-weighted and T1-weighted gadolinium contrast-enhanced of 83 glioma patients from one medical institution. Using the open-source python package PyRadiomics, 107 radiomics features were identified for each sequence MRI. We analyzed the probabilities of low-grade gliomas (LGG) and high-grade gliomas (HGG) using logistic regression and the least absolute shrinkage and selection operator regression (LASSO). We identified seven features affecting LGG and HGG differentiated using the lasso algorithm. Next, logistic regression analysis was performed to build a classification model, and five features were obtained. Nomograms were created to predict the incidence of HGG and LLG. To evaluate the prediction performance of the models, receiver operating characteristic (ROC) curves were plotted, and the area under the curve (AUC), sensitivity, specificity, and accuracy were calculated. Results: For multivariate logistic regression models, according to the best-selected features based on MRI images and clinical data, five parameters were independent predictors of LGG from HGG (P<0.001). The highest prediction performance in terms of AUC, sensitivity, specificity, and accuracy was 0.97, 89.19%, 91.11%, and 90.24%, respectively. Conclusion: The radiomics nomogram models created from quantitative images and clinical data performed well in differentiating LGG from HGG.
|
|
