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 evaluate the effect of upregulation of HuR gene on the radiosensitivity of esophageal squamous cell carcinoma cell Kyse450. Methods:The HuR gene of Kyse450 cells was upregulated by lentivirus. At the same time, X-ray irradiation at a dose of 6 Gy was selected as the intervention condition. Western blot and qPCR were used to detect the expression levels of protein and RNA after Kyse450 transfection, respectively. CCK8 kit was employed to determine the cell proliferation rate. Clone formation assay was adopted to evaluate the ability of cell clone formation. Wound healing experiment and the Transwell test were performed to detect changes in cell migration. Results:CCK8 assay showed that the proliferation ability of cells was enhanced after upregulation of HuR gene, and this enhancement trend was more obvious after radiation. The plate cloning experiment showed that with the increase of radiation dose, the clone formation rates were decreased in both groups, but the clone formation rate in the overexpression group was higher than that in the control group. Wound healing experiment and Transwell test demonstrated that the wound healing rate and migration ability in the overexpression group were higher than those in the control group, and the difference was more significant after radiotherapy. Western blot showed that the levels of MMP9 and MMP2 at 24 h after radiotherapy in the overexpression group were higher than those in the control group. Conclusion:The upregulation of HuR can enhance the proliferation, cloning, migration capabilities and decrease the radiosensitivity of esophageal squamous cell carcinoma cells.
ABSTRACT
Objective To investigate the effect of nutritional intervention upon the clinical efficacy of chemoradiotherapy in patients diagnosed with esophageal carcinoma. Methods A total of 46 patients who were diagnosed with esophageal cancer in Anhui Cancer Hospital from November 2016 to August 2017 were enrolled in this prospective study. All patients were randomly and evenly divided into the nutritional intervention (NI) and routine treatment (RT) groups. The changes in body mass index (BMI),PG-SGA, serum albumin ( ALB), hemoglobin ( HB), white blood cell ( WBC) and other objective nutritional parameters and the incidence of chemoradiotherapy-induced complications were recorded before and after chemoradiotherapy. Results Prior to chemoradiotherapy,age,sex,BMI,ALB,PLT and clinical staging did not significantly differ between two groups (all P>0. 05).In the NI group,the BMI was (21.52±2. 67) after chemoradiotherapy,significantly higher than (21.13±2. 73) before radiotherapy (P= 0. 000).Moreover,the PG-SGA score after chemoradiotherapy was significantly lower compared with that before chemoradiotherapy (P= 0. 000).In the RT group,the BMI,Hb,ALB,PLT and WBC after chemoradiotherapy were significantly lower than those before radiotherapy, and thePG-SGA score was worse after chemoradiotherapy ( all P<0. 05).In the NI group, the incidence of grade 3 myelosuppression was 4. 34％, significantly lower than 8. 68％ in the RT group ( P= 0. 000 ). Conclusions Patients with esophageal cancer treated with chemoradiotherapy have a high nutritional risk. Nutritional intervention can improve the nutritional status, reduce the incidence of chemoradiotherapy-induced complications,and probably improve the quality of life and clinical prognosis.
ABSTRACT
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.