ABSTRACT
OBJECTIVE@#To propose a probabilistic neural network classification method optimized by simulated annealing algorithm (SA-PNN) to discriminate lung cancer and adjacent normal tissues based on permittivity.@*METHODS@#The permittivity of lung tumors and the adjacent normal tissues was measured by an open-ended coaxial probe, and the statistical dependency (SD) algorithm was used for frequency screening.The permittivity associated with the selected frequency points was taken as the characteristic variable, and SA-PNN was used to discriminate lung cancer and the adjacent normal tissues.@*RESULTS@#Three frequency points, namely 984 MHz, 2724 MHz and 2723 MHz, were selected by SD algorithm.SA-PNN was used to discriminate 200 samples with the permittivity at the 3 frequency points as the characteristic variable.After 10-fold cross-validation, the final discrimination accuracy was 92.50%, the sensitivity was 90.65%, and the specificity was 94.62%.@*CONCLUSIONS@#Compared with the traditional probabilistic neural network, BP neural network, RBF neural network and the classification discriminant analysis function (Classify) in MATLAB, the proposed SA-PNN has higher accuracy, sensitivity and specificity for discriminating lung cancer and the adjacent normal tissues based on permittivity.
Subject(s)
Humans , Algorithms , Lung Neoplasms/diagnosis , Neural Networks, Computer , Sensitivity and SpecificityABSTRACT
Purpose: High Dose Rate (HDR) remote afterloading brachytherapy machine and advanced treatment planning system have made it possible to make variations in individual dwell times across a catheter according to tumour density and for sparing normal structures. New inverse planning technique such as Inverse Planning Simulated Annealing (IPSA) has also been introduced. But very few institutions are venturing towards volume based IPSA optimised intracavitary brachytherapy. This study focuses on dwell time deviation constraint (DTDC) feature of IPSA based optimization which restricts the large variation of dwell time across the catheter. Methods and Material: For this retrospective study we have generated IPSA optimised intracavitary brachytherapy plans for 20 cancer cervix applications. The initial DTDC value of each IPSA plan was kept 0.0. Later on gradual increment was made in DTDC values in step of 0.2. Plan modulation index (M) defined by Ryan L. Smith et al was used for characterising the variation of dwell time modulation with respect to gradual increase in DTDC parameter. Results: Plan modulation index gradually decreases with increasing value of DTDC from 0.0 to 1.0. There was the 83% decrease in M value from IPSA of DTDC 0.0 to fully constrained IPSA of DTDC1.0. There is reduction of 8.26% and 6.95% for D2cc values of rectum and bladder respectively for DTDC 1.0 compared to DTDC 0.0. Conclusions: One of the benefits of applying DTDC constrained in IPSA plan is that, it removes local hot spots. It's another advantage is the reduction in rectum and bladder dose.
ABSTRACT
ObjectiveTo study the relationship between tumor siza,aource intensita,arescription dose and source dwell time in the after-loading treatment plaa,and to establish a method that can be used for rapid quality control of after-loading plans.Methods The all of gynecological cancer patients treated in this hospital were selected:84 cases of all three tubes of Fletcher applicator,58 cases of uterine alone and 39 cases of vaginal applicator.Each patient was scanned with CT before treatment.Contouring the target and organs at risa,ahe treatment plan was optimized using IPSA.Record the source strengta,arescription dosa,aource dwell tima,and tumor volume of the prescribed dose for each case.Calculate CI values and Rv.The kvalue analyzes the CI distribution characteristics and the correlation with the Rv value.In addition,46 cases of gynecologic tumor patients were used to verify the method.Results The fitting index of the after-loading scheme of the three applicators showed a normal distribution.The mean value of the Fletcher applicator CI was 0.720±0.067,the k value was 1 394,Rvalue was 0.894.The mean value of the uterine alone CI was 0.697±0.076,the k value was 1 428,R=0.940,the mean value of the vaginal applicator CI was 0.742± 0.067,the k value was 1 362,and R=0.909.Conclusions Using this methoa,at can quickly assess whether the planned target voluma,aadiation source intensita,arescription dose and treatment time matca,and find the cause of deviation based on the feedback results to ensure that the after-loading treatment plan can be quickla,accuratela,and efficiently implemented according to clinical requirements.
ABSTRACT
Objective To evaluate the effect of an inverse planning simulated annealing (IPSA) in the treatment of cervical cancer with combined intracavitary and interstitial three-dimensional brachytherapy.Methods A total of 60 patients with locally advanced cervical cancer who received both external beam radiotherapy and combined intracavitary and interstitial brachytherapy in our hospital from October 2016 to July 2018 were enrolled.Patients were divided into four groups with 15 patients each according to the number of needles applied (1,2,3,and 4 needles,respectively).Dosimetric distributions were optimized with both Graphical optimization (GRO) and IPSA.Paired t-test was applied to compare the dosimetric differences between plans optimized with GRO and IPSA.Results The Dg0 and V100 of IPSA plans were higher than those of GRO (t=-4.742,-4.823,P＜0.05),while the conformity index (CI) and conformal index (COIN) were slightly lower than those of GRO plans (t=9.642,8.783,P＜0.05).No significant difference in the V150,V200,V300 between IPSA and GRO (P＞0.05) was observed.There was also no significant difference in the D2cm3 of bladder and rectum between IPSA and GRO (P＞0.05).The difference of Dg0 between IPSA and GRO was increased as the number of implanted needles increased,which increased from 4 cGy to 14 cGy as the number of needle increased from 1 to 4.The difference of V100 between GRO and IPSA was also increased as the number of needle increased.Conclusions In the treatment of cervical cancer with combined intracavitary and interstitial threedimensional brachytherapy,IPSA plan could improve the target coverage(D90,V100)without increasing the dose to the OARs and high dose region in the target compared with GRO.With the numbers of needles increased,the advantage of IPSA increased in terms of target coverage.
ABSTRACT
Objective To compare and analyze the dosimetric discrepancy of combind intracavitary/interstitial brachytherapy using three different kinds of optimization method in locally advanced cervical cancer.Methods Totally 20 cases of locally advanced cervical cancer were selected and divided into three groups according to different optimization method which include manual optimization group (MO) based on graphical optimization,inverse planning simulated annealing (IPSA 1)based on simulated annealing optimization algorithm,IPSA 2 based on IPSA 1 with limitation on maximum dose of target.The dose volume histogram parameters of the targets (V200,V150,V100,D100,D90,HI) and the OARs(D0.1 cm3,D1 cm3 and D2 cm3) were analyzed.Results For CTV,compared with MO,there was no significantly statistical difference in D100between IPSA 1 and IPSA 2(P ＞ 0.05).However,V200,V150,V100 and HI for ISPA1 were better than for ISPA2 (t =-3.422-9.910,P ＜ 0.05).In addition,V100 and D100 in ISPA1 were better than in ISPA2 (t =7.238,5.032,P ＜0.05).For OARs,D0.1 cm3,D1 cm3 and D2 cm3 in rectum,bladder,sigmoid colon of both ISPA 1 and ISPA 2 were dramatically lower than those of MO (t =2.235 5.819,P ＜ 0.05),without significantly statistical difference found between ISPA1 and ISPA2.Conclusions For combined intracavitary/interstitial brachytherapy in locally advanced cervical cancer,all treatment plans based on three different kinds of optimization methods can meet the clinical need.Moreover,inverse optimization can ensure dose coverage over target and reduce maximum dose of rectum,bladder and sigmoid colon.
ABSTRACT
Aiming at the disadvantages of traditional direct aperture optimization (DAO) method, such as slow convergence rate, prone to stagnation and weak global searching ability, a gradient-based direct aperture optimization (GDAO) is proposed. In this work, two different optimization methods are used to optimize the shapes and the weights of the apertures. Firstly, in order to improve the validity of the aperture shapes optimization of each search, the traditional simulated annealing (SA) algorithm is improved, the gradient is introduced to the algorithm. The shapes of the apertures are optimized by the gradient based SA method. At the same time, the constraints between the leaves of multileaf collimator (MLC) have been fully considered, the optimized aperture shapes are meeting the requirements of clinical radiation therapy. After that, the weights of the apertures are optimized by the limited-memory BFGS for bound-constrained (L-BFGS-B) algorithm, which is simple in calculation, fast in convergence rate, and suitable for solving large scale constrained optimization. Compared with the traditional SA algorithm, the time cost of this program decreased by 15.90%; the minimum dose for the planning target volume was improved by 0.29%, the highest dose for the planning target volume was reduced by 0.45%; the highest dose for the bladder and rectum, which are the organs at risk, decreased by 0.25% and 0.09%, respectively. The results of experiment show that the new algorithm can produce highly efficient treatment planning a short time and can be used in clinical practice.
ABSTRACT
Objective To investigate the dosimetric difference between inverse planning simulated annealing(IPSA)and manual optimized plan for isodose line in interstitial brachytherapy for locally advanced cervical cancer and to provide a better optimization method for clinical application. Methods A total of 104 patients with cervical cancer were enrolled in this study. They received pelvic external beam radiotherapy and interstitial brachytherapy in five fractions. Both IPSA and manual optimized plan for isodose line were used to optimize the dose in each fraction. Dose volume parameters of the two plans were compared to analyze the dosimetric outcome by paired t-test. Results There were no significant differences in mean D 90and D 100for high-risk clinical target volume(HR-CTV)and D 90for intermediate-risk clinical target volume(IR-CTV)between the two groups(P>0.05). The IPSA group had a significantly higher D 100for IR-CTV than the manual optimized group(58.36±2.06 Gy vs. 53.99±2.17 Gy, P=0.025). For organs at risk,the IPSA group had a significantly lower mean rectum D 2ccand a significantly higher bladder D 2ccthan the manual optimized group(68.53± 2.85 Gy vs. 71.77± 1.79 Gy, P=0.002;80.49± 3.36 Gy vs. 78.71± 2.64 Gy,P=0.034). There was no significant difference in sigmoid D 2ccbetween the two groups(P>0.05). The IPSA group had significantly higher relative dose homogeneity index(HI)and conformity index (CI)of radiation dose for target volume than the manual optimized group(P<0.05), and there was no significant difference in overdose volume index(OI)between the two groups(P= 0. 1 0 7).Conclusions Compared with manual optimized plan for isodose line, IPSA can improve the dose distribution of tumor tissue,reduce mean rectum D 2cc,and increase CI and HI,so it is a preferable optimized treatment planning method in clinical application.
ABSTRACT
Objective To establish a computer-aided diagnosis (CAD) model for the classification and diagnosis of systemic lupus erythematosus (SLE) complicated with renal involvement,and to provide a new method for the timely detection and diagnosis of the disease.Methods Simulated annealing(SA) algorithm was used to optimize the penalty coefficient C and kernel function parameter g of the support vector machines(SVM) algorithm before an SA-SVM classifier model was established and was applied to the intelligent assistant diagnosis of SLE.Results Unlike the single SVM classifier,this method never fell into local optimum,and improved the classification accuracy of a classifier.The classification accuracy for SLE with renal involvement was as high as 98.72％.Conclusion The experimental results show that this classification model is well applicable to the intelligent diagnosis of SLE with renal involvement.
ABSTRACT
This paper is aimed to study the clustering method for Chinese medicine (CM) medical cases. The traditional K-means clustering algorithm had shortcomings such as dependence of results on the selection of initial value, trapping in local optimum when processing prescriptions form CM medical cases. Therefore, a new clustering method based on the collaboration of firefly algorithm and simulated annealing algorithm was proposed. This algorithm dynamically determined the iteration of firefly algorithm and simulates sampling of annealing algorithm by fitness changes, and increased the diversity of swarm through expansion of the scope of the sudden jump, thereby effectively avoiding premature problem. The results from confirmatory experiments for CM medical cases suggested that, comparing with traditional K-means clustering algorithms, this method was greatly improved in the individual diversity and the obtained clustering results, the computing results from this method had a certain reference value for cluster analysis on CM prescriptions.
Subject(s)
Algorithms , Cluster Analysis , Databases as Topic , Drug Prescriptions , Drugs, Chinese Herbal , Pharmacology , Reproducibility of ResultsABSTRACT
Objective To compare the differences and characteristics of the dose distribution of the two optimization methods in the three dimensional brachytherapy,and provide the basis for clinieal treatment.Methods Excel 2007 was used to generate random number.And a total of 21 patients of cervical cancer were selected from those who have completed the treatment.Inverse simulated annealing optimization (IPSA) plans were designed for graphical optimization (GO) plans.The dose volume histogram (DVH) parameters of the targets (V100％,V150％) and the organs (D1 cm3,D2cm3) of the two methods were analyzed.Results The targets dose of both plans could meet the prescription requirements.There was no statistically significant difference in the dose parameters of all targets (P ＞ 0.05).The closes of D1 cm3 and D2cm3 in the bladder of IPSA plan were significantly lower than that of the GO plan (t =3.596,3.490,P ＜ 0.05).There was no statistically significant difference in the dose parameters of rectum (P ＞ 0.05).Conclusions For cervix brachytherapy,the GO and IPSA have no effect on targets dose,but IPSA optimization can reduce the maximum dose of bladder.
ABSTRACT
Dysregulation of P70 ribosomal S6 kinase (P70S6K) has been observed in many cancers; therefore, the design of new molecules targeting p70S6K of paramount importance in cancer therapy. The current study employed a group-based quantitative structure-activity relationship (GQSAR) to develop global QSAR models capable of predicting the bioactivity of P70S6K inhibitors. A wide variety of chemical structures and biological activities (half maximal inhibitory concentration) of P70S6K inhibitors were collected from the binding database website. Compounds were classified into various chemical groups and then fragmented into R1, R2, and R3 fragments based on certain pharmacophoric features required for ligand-target biointeractions. Different two-dimensional fragment-based descriptors were calculated for each fragment. The dataset was then divided into a training set (n=40) and a test set (n=10) using a sphere exclusion algorithm. Multiple linear regressions coupled with simulated annealing or stepwise regression resulted in model A (r2=0.92) and model B (r2=0.87), respectively. Leave-one-out validation showed that models A and B have internal predictive abilities of 72% and 61%, respectively. External validation indicated that both models are robust, with squared cross-correlation coefficients of the training set (pred-r2) of 0.87 and 0.89, respectively. The developed GQSAR models indicate that fragment R3 plays a key role in activity variation (65%) with sound contribution of five-membered rings (5 chain count), aromatic carbons (SaaaCE-index), and aromatic nitrogens (SaaNcount). In contrast, fragments R1 and R2 together contribute 35% of activity variation, suggesting that sulfur atoms (Sulfur count) and hydrophobic threemembered rings (chi3 chain) at R1 are preferable for inhibitory activity.
ABSTRACT
Objective To evaluate the clinical value of the afterloading brachytherapy inverse intensity-modulated radiotherapy of gynecological tumor.Methods Twenty patients with cervical cancer,were randomly divided into A and B groups,10 cases for each group.Group A received the afterloading brachytherapy inverse intensity-modulated radiotherapy.Group B received the three-dimensional comformal afterloading brachytherapy.The target volume dose distribution,organs at risk (rectum,bladder),shortterm curative effect and radioactive complications were analyzed on both groups.Results The dose homogeneity index of the target volume of group A was 52.43-± 0.45,better than that of group B (46.37 ± 1.45) (t =0.92,P ＜ 0.05).The maximum dose of rectum and bladder of group A were about 37％,35％,less than that of group B (t =1.34,1.39,P ＜ 0.05).The 75％ prescription dose irradiated volume of rectum and bladder of group A were about only 1/2 of group B (t =1.23,1.13,P ＜ 0.05).The local control rate of 96％ for group A was better than 93％ for group B (t =1.25,P ＜ 0.05).Conclusions Afterloading brachytherapy inverse intensity-modulated radiotherapy technique could be better than the three-dimensional comformal afterloading brachytherapy.It should be recommended for gynecological tumor.
ABSTRACT
A two dimensional colloidal suspension subject to a periodic substrate evolves into a colloidal molecular crystal under situationsofstrongconfinement. Wefocusonthelongrangeorientationalordertherebyemerging, inthegroundstate. We study by simulations the situations where in each trap lies a pair of identical colloids, or alternatively a pair of oppositelychargedmacroions. We consider square or triangular geometries for the periodic confinement, together with less symmetric distorted lattices.
Uma suspensão bidimensional coloidal sujeita a um substrato periódico evolui para um cristal coloidal molecular em situações de forte confinamento. Nós focamos na ordem de orientação emergindo a partir do estado fundamental. Fazendo uso de simulações, estudamos as situações onde em cada armadilha reside um par de colóides idênticos ou, alternativamente, um par de macro-íons de cargas opostas. Consideramos geometrias quadradas ou triangulares para o confinamento periódico com arranjos simétricos com menor distorção.
ABSTRACT
Um mapa genético é um diagrama onde são representados os genes com suas respectivas posições no cromossomo. Eles são essenciais para o procedimento de localização de genes envolvidos no controle genético de caracteres quantitativos ou no controle de outros caracteres de interesse econômico. No presente trabalho avalia-se, via simulação computacional de dados, a eficiência dos algoritmos simulated annealing, delineação rápida em cadeia e ramos e conexões, para a construção de mapas genéticos. Nas condições avaliadas, o algoritmo ramos e conexões foi o mais rápido, sendo que tanto este, quanto a delineação rápida em cadeia apresentaram 100 por cento de eficiência. A eficiência do simulated annealing para ordenação de marcadores variou com o número de marcadores, para 5 e 10 foi de 100 por cento, para 15 99,8 por cento e com 20 marcadores a eficiência obtida foi de 99,2 por cento.
The efficiency of Simulated Annealing (SA), Rapid Chain Delineation (RCD) and Branch and Bounds (BB) algorithms was evaluated by a Monte Carlo method. Regarding the conditions appraised the Branch and Bounds showed to be the fastest among them. Both RCD and BB were 100 percent efficient. The efficiency of SA depends on the length of the linkage group to be ordered. For 5 and 10 the efficiency was 100 percent, for 15 it was 99.8 percent and for 20 it was 99.2 percent.
ABSTRACT
Analysis of gene deletions is a fundamental approach for investigating gene function. We evaluated an algorithm that uses classification techniques to predict the phenotypic effects of gene deletions in yeast. We used a modified simulated annealing algorithm for feature selection and weighting. The selected features with high weights were phylogenetic conservation scores for bacteria, fungi (excluding Ascomycota), Ascomycota (excluding Saccharomyces cerevisiae), plants, and mammals, degree of paralogy, and number of protein-protein interactions. Classification was performed by weighted k-nearest neighbor and with support vector machine algorithms. To demonstrate how this approach might complement existing experimental procedures, we applied our algorithm to predict essential genes and genes causing morphological alterations in yeast.