ABSTRACT
Objective:To propose a deep learning network model 2D-PE-GAN to automatically delineate the target area of nasopharyngeal carcinoma and improve the efficiency of target area delineation.Methods:The model adopted the architecture of generative adversarial networks which used a UNet similar structure as the generator, and 2D-PE-block was added after each layer of convolution operation of the generator to improve the accuracy of delineation. The experimental data included CT images from 130 cases of nasopharyngeal carcinoma. The images were preprocessed before model training. In addition, three models of UNet, GAN, and GAN with an attention mechanism were compared, and Dice similarity coefficient, Hausdorff distance, accuracy, Matthews correlation coefficient, Jaccard distance were employed to evaluate network performance.Results:Compared with UNet, GAN and GAN with the attention mechanism, the average Dice similarity coefficient of 2D-PE-GAN network segmentation of CTV was increased by 26%, 4% and 2%. The average Dice similarity coefficient of GTV segmentation was increased by 21%, 4%, 2%, respectively. Compared with the GAN network with the attention mechanism, the parameters and time of 2D-PE-GAN were reduced by 0.16% and 18%, respectively.Conclusions:Compared with the above three networks, 2D-PE-GAN network can increase the segmentation accuracy of nasopharyngeal carcinoma target area delineation. At the same time, compared with the attention mechanism with similar reasons, 2D-PE-GAN network can reduce the occupation of computing resources when the segmentation accuracy is not much different.
ABSTRACT
Objective:To develop a dose prediction-based quantitative evaluation method of the quality of radiotherapy plans, and to verify the clinical feasibility and clinical value of the method .Methods:The 3D U-Netwas trained using the radiotherapy plans of 45 rectal cancer cases that were formulated by physicists with more than five years of radiotherapy experience. After obtaining 3D dose distribution using 3D U-Net prediction, this study established the plan quality metrics of intensity modulated radiotherapy(IMRT) rectal cancer radiotherapy plans using dose-volume histogram(DVH) indexes of dose prediction. Then, the initial scores of rectal cancer radiotherapy plans were determined.Taking the predicted dose as the optimization goal, the radiotherapy plans were optimized and scored again. The clinical significance of this scoring method was verified by comparing the scores and dosimetric parameters of the 15 rectal cancer cases before and after optimization.Results:The radiotherapy plans before and after optimization all met the clinical dose requirements. The total scores were(77.21±9.74) before optimization, and (88.78±4.92) after optimization. Therefore, the optimized radiotherapy planswon increased scores with a statistically significant difference( t=-4.105, P<0.05). Compared to the plans before optimization, the optimized plans show decreased Dmax of all organs at risk to different extents. Moreover, the Dmax, V107%, and HI of PTV and the Dmax of the bladder decreased in the optimized plans, with statistically significant differences ( t=2.346-5.771, P<0.05). There was no statistically significant difference in other indexes before and after optimization ( P>0.05).The quality of the optimized plans were improved to a certain extent. Conclusions:This study proposed a dose prediction-based quantitative evaluation method of the quality of radiotherapy plans. It can be used for the effective personalized elevation of the quality of radiotherapy plans, which is beneficial to effectively compare and review the quality of clinical plans determined by different physicists and provide personalized dose indicators. Moreover, it can provide great guidance for the formulation of clinical therapy plans.
ABSTRACT
Objective:To develope a self-adjustable automatic planning method of intensity modulated radiotherapy based on predicted dose, in order to enhance the robustness of automatic planning.Methods:After the patients′ dose by 3D U-Res-Net_B network was predicted, the current dose was calculated based on the last iteration result, then the predicted dose was combined to calculate the target dose and optimized. With all iterations completed or exit conditions satisfied, final treatment plannings would be acquired. A total of 30 cases of rectal cancer were tested to verify the effectiveness of the algorithm.Results:The mean value of planning target volumes′ V100% was (95.03±0.91)% for clinical plans, close to (94.67±1.96)% for automatical plans( P>0.05), and better than (92.90±2.13)% for predicted dose with the statisically significant difference ( t=29.0, P<0.05). Automatic planning′s indexes such as V35 of small intestines, V40 of bladders and V20 - V40 of femoral heads were lower than predicted and clinical ones, with the statisically significant difference( t=4.5-118.0, P<0.05). Discrepancy in other indexes of organs at risk was not statistically significantly different( P>0.05). Conclusions:This method made automatic planning processes more robust and more adaptive to difficult clinical situations.
ABSTRACT
Objective:To develop a deep learning model for predicting three-dimensional (3D) voxel-wise dose distributions for intensity-modulated radiotherapy (IMRT).Methods:A total of 110 postoperative rectal cancer cases treated by IMRT were considered in the study, of which 90 cases were randomly selected as the training-validating set and the remaining as the testing set. A 3D deep learning model named 3D U-Res-Net was constructed to predict 3D dose distributions. Three types of 3D matrices from CT images, structure sets and beam configurations were fed into the independent input channel, respectively, and the 3D matrix of IMRT dose distributions was taken as the output to train the 3D model. The obtained 3D model was used to predict new 3D dose distributions. The predicted accuracy was evaluated in two aspects: the average dose prediction bias and mean absolute errors (MAEs)of all voxels within the body, the dice similarity coefficients (DSCs), Hausdorff distance(HD 95) and mean surface distance (MSD) of different isodose surfaces were used to address the spatial correspondence between predicted and clinical delivered 3D dose distributions; the dosimetric index (DI) including homogeneity index, conformity index, V50, V45 for PTV and OARs between predicted and clinical truth were statistically analyzed with the paired-samples t test. Results:For the 20 testing cases, the average prediction bias ranged from -2.12% to 2.88%, and the MAEs varied from 2.55% to 5.75%. The DSCs value was above 0.9 for all isodose surfaces, the average MSD ranged from 0.21 cm to 0.45 cm, and the average HD 95 varied from 0.61 cm to 1.54 cm. There was no statistically significant difference for all DIs, except for bladder Dmean. Conclusions:This study developed a deep learning model based on 3D U-Res-Net by considering beam configurations input and achieved an accurate 3D voxel-wise dose prediction for rectal cancer treated by IMRT.
ABSTRACT
Objective To evaluate the feasibility of utilizing dose-volume histogram (DVH) prediction models of organs at risk (OARs) to deliver automatic treatment planning of prostate cancer.Methods The training set included 30 cases randomly selected from a database of 42 cases of prostate cancer receiving treatment planning.The bladder and rectum were divided into sub-volumes (Ai) of 3 mm in layer thickness according to the spatial distance from the boundary of planning target volume (PTV).A skewed normal Gaussian function was adopted to fit the differential DVH of Ai,and a precise mathematical model was built after optimization.Using the embedded C++ subroutine of Pinnacle scripa,ahe volume of each Ai of the remaining validation set for 12 patients was obtained to predict the DVH parameters of these OARa,ahich were used as the objective functions to create personalized Pinnacle script.Finalla,automatic plans were generated using the script.The dosimetric differences among the original clinical plannina,aredicted value and the automatic treatment planning were statistically compared with paired t-test.Results DVH residual analysis demonstrated that predictive volume fraction of the bladder and rectum above 6 000 cGy were lower than those of the original clinical planning.The automatic treatment planning significantly reduced the V70,V60,V50 of the bladder and the V70 and V60 of the rectum than the original clinical planning (all P＜0.05),the coverage and conformal index (CI) of PTV remained unchangea,and the homogeneity index (HI) was slightly decreased with no statistical significance (P＞ 0.05).Conclusion The automatic treatment planning of the prostate cancer based on the DVH prediction models can reduce the irradiation dose of OARs and improve the treatment planning efficiency.
ABSTRACT
For the past several decades, the infectious disease profile in China has been shifting with rapid developments in social and economic aspects, environment, quality of food, water, housing, and public health infrastructure. Notably, 5 notifiable infectious diseases have been almost eradicated, and the incidence of 18 additional notifiable infectious diseases has been significantly reduced. Unexpectedly, the incidence of over 10 notifiable infectious diseases, including HIV, brucellosis, syphilis, and dengue fever, has been increasing. Nevertheless, frequent infectious disease outbreaks/events have been reported almost every year, and imported infectious diseases have increased since 2015. New pathogens and over 100 new genotypes or serotypes of known pathogens have been identified. Some infectious diseases seem to be exacerbated by various factors, including rapid urbanization, large numbers of migrant workers, changes in climate, ecology, and policies, such as returning farmland to forests. This review summarizes the current experiences and lessons from China in managing emerging and re-emerging infectious diseases, especially the effects of ecology, climate, and behavior, which should have merits in helping other countries to control and prevent infectious diseases.
Subject(s)
Humans , Behavior , China , Epidemiology , Climate , Communicable Diseases , Classification , Epidemiology , Communicable Diseases, Emerging , Epidemiology , Disease Outbreaks , Ecology , Forecasting , IncidenceABSTRACT
Objective To investigate the significance of computed tomography(CT)and 3.0 T magnetic resonance imaging(MRI)in intensity-modulated radiotherapy(IMRT)for esophageal carcinoma. Methods Thirty-five patients newly diagnosed with esophageal carcinoma who received radical radiotherapy in our hospital from November 2013 to April 2015 were enrolled as subjects. Target volume was delineated on the CT images and MRI images(T2-weighted and diffusion-weighted fusion images). The MRI-and CT-based IMRT plans were designed using the same dose prescription and dose constraints for organs at risk(OAR). The target volume,prescribed dose,and doses for OAR were compared between the two plans. Results In the two plans, dose distribution and planning parameters met the clinical requirement. The length of lesion,gross tumor volume (GTV),and planning target volume(PTV)defined by 3.0 T MRI were significantly smaller than those defined by CT(P=0.00,0.03,0.03). There were no significant differences in the D 2%,D 98%,D 50%,homogeneity index,or conformity index for primary GTV(PGTV)and PTV-PGTV between the two plans(all P>0.05). Compared with the CT-based plan,the 3.0 T MRI-based plan had a significantly smaller mean dose to the lungs and an insignificantly smaller actual dose to the lungs(P=0.00;P>0.05).There were no significant differences in maximum doses tolerated by the spinal cord or heart between the two plans. Conclusions In terms of target volume delineation and dosimetric parameters, both CT-and 3.0 T MRI-based plans meet the clinical requirement. The 3.0 T MRI-based plan may provide potential benefits for some OAR due to a smaller target volume compared with the CT-based plan.
ABSTRACT
Objective To investigate the role of miR?193a?3p in the radioresistance of esophageal squamous cell carcinoma ( ESCC) . Methods MTT assay was used to identify the cell lines with the highest radiosensitivity and radioresistance in four esophageal cancer cell lines exposed to irradiation of 6 MV X?ray. Stem?loop quantitative real?time PCR was used to measure the expression levels of miR?193a?3p, miR?155, and miR?22?3P in the two cell lines. Further studies were performed on miR?193a?3p because of the substantial difference in its expression between the two cell lines. The mimic (3PM) and antagomiR (3PA) of miR?193a?3p as well as siRNA ( si?LOXL4) were synthesized and transfected into cells to elevate and inhibit miR?193a?3p expression. MTT assay and flow cytometry were used to evaluate the effects of miR?193a?3p and its downstream gene LOXL4 on radiosensitivity. Results KYSE510 and KYSE410 were characterized as cell lines with the highest radiosensitivity and radioresistance, respectively. miR?193a?3p had a substantially larger difference in expression between the two cell lines than miR?155 or miR?22?3P (1. 00 ∶ 21. 00). Transfection of 3PM resulted in elevated expression of miR?193a?3p in KYSE510, which had a significantly lower radiosensitivity and a significantly reduced apoptosis ratio by 11. 01% compared with the control group ( P<0. 05) . KYSE410 transfected with 3PA had a significantly higher radiosensitivity ( P<0. 05) . The expression of LOXL4, a downstream gene of miR?193a?3p, was negatively correlated with miR?193a?3p expression. Transfection with si?LOXL4 inhibited the expression of LOXL4, which resulted in a significantly lower radiosensitivity and a significantly reduced apoptosis ratio by 7. 07% compared with the control group ( P<0. 05) . Conclusions miR?193a?3p promotes the radioresistance of esophageal cancer cells probably by regulation of LOXL4.
ABSTRACT
Astrocytes play a major role in the reactive processes in response to neuronal injuries in the brain. Excessive gliosis is detrimental and can contribute to neuronal damage. CD81 (TAPA), a member of the tetraspanin family of proteins, is upregulated by astrocytes after traumatic injury to the rat central nervous system (CNS). To further understand the role of CD81 in the inhibition of astrocytes, we analyzed the effects of a CD81 antibody, on cultured rat astrocytes. The results indicated that the effect worked in a dose-dependent manner with certain dosage range. It, however, reached a dosage equilibrium at a high dosage. Furthermore, anti-CD81 antibody remarkably inhibited the proliferation of astrocytes after incubation with astrocytes for different periods of time and the effect presented a time-dependent fashion. However, anti-CD81 antibody substantially inhibited the proliferation of astrocytes at low density and middle density but slightly inhibited the proliferation of astrocytes at high density, suggesting that the effect was positively correlated with the proliferative ability of astrocytes. Finally, the cell cycle of astrocytes exposured to anti-CD81 antibody was arrested in S phase at the initial stage and at G(0)/G(1) phase over time. These findings indicated that CD81 exert significant inhibitory effect, dose-dependently and time-dependently, on the proliferation of astrocytes and the effect is positively correlated with the proliferative capability of astrocytes.
ABSTRACT
Objective To investigate the effect of anti-CD81(antibodys against CD81) on the proliferation of astrocytes. Methods Purified astrocytes from newborn rats' cerebral cortex were divided into 6 groups and added with anti-CD81 different concentrations(0,0.1,0.5,1,5,10?mg/L).The activity of astrocytes was tested by methyl thiazolyl terazolium(MTT).Three significative groups were chosen based on MTT result and added with anti-CD81 of different concentrations(0,0.5,5mg/L).After administration for 24 hours,the cell cycle of the astrocytes was measured by flow cytometer.The corresponding data were analyzed with SPSS statistical software. Results 1.By MTT,the average optical density(AOD) values of astrocytes were reduced after administration with anti-CD81 of different concentrations for 24 hours,that is,the number of astrocytes was reduced,which indicated anti-CD81 inhibited the proliferation of astrocytes and the effect showed a dose-dependent pattern.2.By cell cycle analysis,a progressive dose-dependent decrease was found in the index of cells in G-0/G-1 phase and an increase in S phase.Such as,the index of cells in G-0/G-1 phase,was 82.73 in 0,is 82.16 in 0.5?mg/L,was 78.58 in 5?mg/L.Conclusion Anti-CD81 inhibits the proliferation of astrocytes and the number of astrocytes is reduced.Further more,the index of cells decreases in G-0/G-1 phase and increases in phase S after administration with anti-CD81.This study shows that anti-CD81 doesn't restrain the cells from G-1 phase to S phase but the cells are arrested in S phase.