Objective To establish a mouse model of H1N1 influenza wind-heat syndrome by combining climate intervention with influenza virus nasal drops.Methods Seventy-two BALB/c mice were divided randomly into nine groups:a Control group,wind-heat(FR)groups(FR-3Day,FR-5Day),and Model groups(1LD-3Day,2LD-3Day,3LD-3Day,1LD-5Day,2LD-5Day,2LD-5Day,3LD-5Day)(n=8 mice per group).Mice in the Control group were housed in a normal environment,while mice in the FR and Model groups were kept in wind-heat conditions for 7 d.Mice in the Model groups received nasal PR8 influenza virus infection on the 8th day,and mice in the Control and FR heat groups received equal amounts of physiological saline nasal drops.After virus challenge,each group was housed in a normal environment and samples were taken on days 3 and 5.The appearance of the mice was observed and recorded and the lung index,routine blood parameters,lung tissue pathology,serum interleukin(IL)-6 levels,and virus titers were detected in each group based on their behavioral status,stools,and body temperature.Results After 7 d of wind-heat intervention,mice in the FR groups showed no significant abnormalities in terms of appearance,stools,body temperature,routine blood parameters,or lung tissue pathology compared with the Control group.The appearance,lung index,red blood cell count,hemoglobin,hematocrit,pathological result,and body temperature in the Model groups worsened progressively with increasing time and toxin dosage,while the neutrophil percentage,lymphocyte percentage,virus titer,and serum IL-6 levels peaked on day 3 after viral attack,for the same viral dose,and then decreased slightly on day 5.Conclusions PR8 nasal drops and 7 d of wind-heat climate intervention can be used to establish a mouse model of influenza wind-heat syndrome.

Objective:To investigate the effect of CT-derived fractional flow reserve (CT-FFR) measurement sites on the values and the diagnostic performance, and to determine the optimal measurement site for CT-FFR using invasive FFR as the reference standard.Methods:This study was part of the CT-FFR CHINA clinical trial. Patients with suspected coronary artery disease who were scheduled for invasive coronary angiography (ICA) were prospectively recruited from five clinical centers across the country from November 2018 to March 2020. Each enrolled patient underwent coronary CT angiography (CCTA), CT-FFR, ICA, and invasive pressure wire-based FFR assessments sequentially within one week. Four groups of CT-FFR values were obtained on each enrolled target vessels according to different CT-FFR measurement locations: 1, 2, 3 cm distal to the target lesion, and terminal vessel groups. Spearman and Bland-Altman analyses were used to explore the correlation and consistency of CT-FFR values and FFR values at different measurement sites. The measurement deviation of CT-FFR was also compared. Diagnostic accuracy and performance of CT-FFR, including sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC), in discriminating myocardial ischemia were analyzed across all measurement site groups on a per-vessel level, using FFR as the reference standard.Results:A total of 289 patients with 345 target lesion vessels were included. According to CCTA, there were 51 target vessels (14.8%) with<50% stenosis, 106 vessels (30.7%) with 50%-69% stenosis, and 188 vessels (54.5%) with stenosis≥70%. At per-vessel level, CT-FFR and FFR values at each measurement position group were highly positively correlated: 1 cm distal to target lesion group, r=0.734 ( P<0.001); 2 cm distal to target lesion group, r=0.732 ( P<0.001); 3 cm distal to target lesion group, r=0.737 ( P<0.001); terminal vessel group was 0.719 ( P<0.001). At per-vessel level, CT-FFR and FFR values of all measurement sites were in good agreement (Bland-Altman analysis results): 1 cm distal to target lesion group, 0.014 (95% LoA 0.002-0.026); 2 cm distal to target lesion group, 0.026 (95% LoA 0.015-0.038); 3 cm distal to target lesion group, 0.040 (95% LoA 0.039-0.051); terminal vessel group, 0.075 (95% LoA 0.064-0.087). And at per-vessel level, the accuracy of diagnosing myocardial ischemia with CT-FFR at 1 cm was highest [84.6% (95% CI 80.4%-88.3%)], and the lowest accuracy in the terminal vessel group [67.0% (95% CI 61.7%-72.0%)]. However, there was no significant difference in the diagnostic accuracy of CT-FFR at 1 cm, 2 cm [80.6% (95% CI 76.1%-84.6%)] and 3 cm [77.5% (95% CI 72.6%-81.7%)]. AUC of CT-FFR at 1 cm distal to the lesion were both highest for global level and moderately stenosis (50%-69%) lesions [0.85 (95% CI 0.81-0.89), 0.84 (95% CI 0.77-0.90)]. And the differences were statistically significant among the four measurement location groups (all P<0.05). Conclusions:The deviation of CT-FFR increases with measurement site distance distal to target lesions. One centimeter distal to the target lesion is the optimal measurement site, and the CT-FFR value here shows the highest diagnostic performance for myocardial ischemic lesions, especially for moderate stenosis.

Objective:To summarize the clinicopathological features, evolving trends in treatment and surgical approaches, and survival outcomes of patients who underwent D2 radical gastrectomy for gastric cancer in Shanxi Provincial Cancer Hospital over the past 11 years with the goal of providing a reference for the clinical practice of gastric cancer in this region.Methods:A retrospective observational study was conducted to analyze the clinicopathological data of patients who underwent D2 radical gastrectomy for pathologically confirmed gastric malignancy at the Department of Gastrointestinal Surgery, Shanxi Provincial Cancer Hospital from January, 2013 to December, 2023. Exclusion criteria consisted of: (1) residual gastric cancer or recurrent gastric cancer after surgery; (2) emergency gastric cancer resection due to bleeding, perforation, obstruction, or other causes; (3) comorbidity with other primary malignant tumors; (4) severe preoperative cardiopulmonary insufficiency or hepatic and renal insufficiency who cannot tolerate radical surgery; and (5) inconsistent main diagnosis information across the medical record system, pathological system, and gastric cancer-specific database. Patients were divided into three groups based on treatment methods: the surgery-only group, the perioperative chemotherapy group, and the adjuvant chemotherapy group. Endpoints included: (1) baseline patient characteristics; (2) trends in tumor location and pathological features; (3) evolution of treatment modalities; and (4) survival outcomes.Results:A total of 15,644 patients were included in the analysis, with 12,591 males and 3,053 females, the male-to-female gender ration was approximately 4∶1; the mean age was (61.2±9.5) years. The tumor sites were mainly concentrated in the esophagogastric junction (EGJ) (57.4%), followed by the antrum (25.9%). The incidence of EGJ cancer initially rose and then declined. However, gastric antrum tumors remained stable, and gastric body tumors showed a slow upward trend after 2020, accounting for 16.7%. In terms of pathological types, poorly differentiated carcinoma was the most prevalent, accounting for 55.9%, followed by moderately differentiated carcinoma (24.2%), mucinous adenocarcinoma (or signet ring cell carcinoma,14.1%), neuroendocrine carcinoma (4.8%), and well-differentiated carcinoma (0.9%). The proportion of poorly differentiated adenocarcinoma showed a significant upward trend overall as well, peaking at 65.6% in 2022 and decreasing to 57.5% in 2023. Mucinous adenocarcinoma (or signet ring cell carcinoma) exhibited fluctuations with a first increase followed by a decrease: it peaked at 17.3% in 2018, dropped sharply to 8.4% in 2022, and rose back to 13.8% in 2023. The proportions of well-differentiated adenocarcinoma, moderately differentiated adenocarcinoma, and neuroendocrine tumors remained stable year by year. In terms of pathological staging, the overall proportions of gastric cancer at Stage 0, Stage I, Stage II, Stage III, and Stage IVa were 0.5%, 17.3%, 25.1%, 54.9%, and 2.3%, respectively. For Stage III, its proportion was 74.6% in 2013, which decreased to 46.4% by 2023. Stages I and II gastric cancer showed an upward trend, with their proportions rising from 10.2% and 12.1% in 2013 to nearly 21.0% and 29.6% in 2023, respectively. Between 2013 and 2023, the proportion of patients who received surgery alone continued to decrease, with this proportion dropping to 34.7% in 2023. In contrast, the number of patients who received adjuvant chemotherapy increased year by year, reaching 54.2% in 2023. Since 2017, the application of perioperative chemotherapy has gradually increased, rising to 11.1% in 2023. Immunotherapy showed an almost synchronous growth trend with perioperative chemotherapy. However, targeted therapy exhibited a downward trend after a period of growth. There were 10,704 cases of open surgery (68.4%), 4,744 cases of laparoscopic surgery (30.3%), and 193 cases of transthoracic surgery (1.2%). Pathological margin positivity was observed in 443 cases (2.8%), and the volume of gastric cancer surgeries gradually increased, peaked in 2021 before subsequently decreasing gradually. However, the volume of laparoscopic surgeries did not decrease; instead, it showed an upward trend. The main resection method for EGJ tumors was total gastrectomy, accounting for 78.5% of the total, followed by proximal gastrectomy, which accounted for 21.5%. After total gastrectomy, esophagojejunal Roux-en-Y anastomosis was the primary anastomotic method, and for proximal gastrectomy, the main anastomotic method was esophagogastric anastomosis, which accounted for 68.0% of the total. For distal gastrectomy, Billroth II anastomosis was the most common anastomotic technique, accounting for 92.7% of these procedures. The overall incidence of postoperative complications was 14.5% (2,264/15,644), among which the incidence of severe complications (grades III-IV) was 4.5% (706/15,644). The entire cohort was followed up with for (47.1±36.8) months, and the 1-year, 3-year, and 5-year overall survival rates were 86.4%, 65.9%, and 58.1%, respectively. For patients with stage 0, I, II, III, and IV gastric adenocarcinoma, the 1-year overall survival rates were 95.7%, 98.0%, 89.4%, 81.0%, and 49.1%, respectively; the 3-year overall survival rates were 92.1%, 94.6%, 81.9%, 51.4%, and 14.7%, respectively; and the 5-year overall survival rates were 89.4%, 91.7%, 75.1%, 41.5%, and 10.0%, respectively. For patients with stage I, II, III, and IV gastric neuroendocrine carcinoma, the 1-year overall survival rates were 96.7%, 91.1%, 73.8%, and 52.6%, respectively; the 3-year overall survival rates were 87.2%, 69.6%, 46.1%, and 32.1%, respectively; and the 5-year overall survival rates were 87.2%, 62.2%, 36.7%, and 32.1%, respectively.Conclusions:Gastric cancer in Shanxi Province is characterized by a male predominance, a high prevalence of tumors at the esophagogastric junction, a large proportion of poorly differentiated adenocarcinoma, and presentation at advanced stages (predominantly Stage III). The detection rate of early gastric cancer has been increasing year by year, the volume of laparoscopic surgeries has been on the rise annually, and the treatment model has shifted from single surgery to comprehensive treatment.

Objective:To summarize the clinicopathological features, evolving trends in treatment and surgical approaches, and survival outcomes of patients who underwent D2 radical gastrectomy for gastric cancer in Shanxi Provincial Cancer Hospital over the past 11 years with the goal of providing a reference for the clinical practice of gastric cancer in this region.Methods:A retrospective observational study was conducted to analyze the clinicopathological data of patients who underwent D2 radical gastrectomy for pathologically confirmed gastric malignancy at the Department of Gastrointestinal Surgery, Shanxi Provincial Cancer Hospital from January, 2013 to December, 2023. Exclusion criteria consisted of: (1) residual gastric cancer or recurrent gastric cancer after surgery; (2) emergency gastric cancer resection due to bleeding, perforation, obstruction, or other causes; (3) comorbidity with other primary malignant tumors; (4) severe preoperative cardiopulmonary insufficiency or hepatic and renal insufficiency who cannot tolerate radical surgery; and (5) inconsistent main diagnosis information across the medical record system, pathological system, and gastric cancer-specific database. Patients were divided into three groups based on treatment methods: the surgery-only group, the perioperative chemotherapy group, and the adjuvant chemotherapy group. Endpoints included: (1) baseline patient characteristics; (2) trends in tumor location and pathological features; (3) evolution of treatment modalities; and (4) survival outcomes.Results:A total of 15,644 patients were included in the analysis, with 12,591 males and 3,053 females, the male-to-female gender ration was approximately 4∶1; the mean age was (61.2±9.5) years. The tumor sites were mainly concentrated in the esophagogastric junction (EGJ) (57.4%), followed by the antrum (25.9%). The incidence of EGJ cancer initially rose and then declined. However, gastric antrum tumors remained stable, and gastric body tumors showed a slow upward trend after 2020, accounting for 16.7%. In terms of pathological types, poorly differentiated carcinoma was the most prevalent, accounting for 55.9%, followed by moderately differentiated carcinoma (24.2%), mucinous adenocarcinoma (or signet ring cell carcinoma,14.1%), neuroendocrine carcinoma (4.8%), and well-differentiated carcinoma (0.9%). The proportion of poorly differentiated adenocarcinoma showed a significant upward trend overall as well, peaking at 65.6% in 2022 and decreasing to 57.5% in 2023. Mucinous adenocarcinoma (or signet ring cell carcinoma) exhibited fluctuations with a first increase followed by a decrease: it peaked at 17.3% in 2018, dropped sharply to 8.4% in 2022, and rose back to 13.8% in 2023. The proportions of well-differentiated adenocarcinoma, moderately differentiated adenocarcinoma, and neuroendocrine tumors remained stable year by year. In terms of pathological staging, the overall proportions of gastric cancer at Stage 0, Stage I, Stage II, Stage III, and Stage IVa were 0.5%, 17.3%, 25.1%, 54.9%, and 2.3%, respectively. For Stage III, its proportion was 74.6% in 2013, which decreased to 46.4% by 2023. Stages I and II gastric cancer showed an upward trend, with their proportions rising from 10.2% and 12.1% in 2013 to nearly 21.0% and 29.6% in 2023, respectively. Between 2013 and 2023, the proportion of patients who received surgery alone continued to decrease, with this proportion dropping to 34.7% in 2023. In contrast, the number of patients who received adjuvant chemotherapy increased year by year, reaching 54.2% in 2023. Since 2017, the application of perioperative chemotherapy has gradually increased, rising to 11.1% in 2023. Immunotherapy showed an almost synchronous growth trend with perioperative chemotherapy. However, targeted therapy exhibited a downward trend after a period of growth. There were 10,704 cases of open surgery (68.4%), 4,744 cases of laparoscopic surgery (30.3%), and 193 cases of transthoracic surgery (1.2%). Pathological margin positivity was observed in 443 cases (2.8%), and the volume of gastric cancer surgeries gradually increased, peaked in 2021 before subsequently decreasing gradually. However, the volume of laparoscopic surgeries did not decrease; instead, it showed an upward trend. The main resection method for EGJ tumors was total gastrectomy, accounting for 78.5% of the total, followed by proximal gastrectomy, which accounted for 21.5%. After total gastrectomy, esophagojejunal Roux-en-Y anastomosis was the primary anastomotic method, and for proximal gastrectomy, the main anastomotic method was esophagogastric anastomosis, which accounted for 68.0% of the total. For distal gastrectomy, Billroth II anastomosis was the most common anastomotic technique, accounting for 92.7% of these procedures. The overall incidence of postoperative complications was 14.5% (2,264/15,644), among which the incidence of severe complications (grades III-IV) was 4.5% (706/15,644). The entire cohort was followed up with for (47.1±36.8) months, and the 1-year, 3-year, and 5-year overall survival rates were 86.4%, 65.9%, and 58.1%, respectively. For patients with stage 0, I, II, III, and IV gastric adenocarcinoma, the 1-year overall survival rates were 95.7%, 98.0%, 89.4%, 81.0%, and 49.1%, respectively; the 3-year overall survival rates were 92.1%, 94.6%, 81.9%, 51.4%, and 14.7%, respectively; and the 5-year overall survival rates were 89.4%, 91.7%, 75.1%, 41.5%, and 10.0%, respectively. For patients with stage I, II, III, and IV gastric neuroendocrine carcinoma, the 1-year overall survival rates were 96.7%, 91.1%, 73.8%, and 52.6%, respectively; the 3-year overall survival rates were 87.2%, 69.6%, 46.1%, and 32.1%, respectively; and the 5-year overall survival rates were 87.2%, 62.2%, 36.7%, and 32.1%, respectively.Conclusions:Gastric cancer in Shanxi Province is characterized by a male predominance, a high prevalence of tumors at the esophagogastric junction, a large proportion of poorly differentiated adenocarcinoma, and presentation at advanced stages (predominantly Stage III). The detection rate of early gastric cancer has been increasing year by year, the volume of laparoscopic surgeries has been on the rise annually, and the treatment model has shifted from single surgery to comprehensive treatment.

Objective To explore the value of combining apparent diffusion coefficient(ADC)heterogeneity with morphological indicators in assessing the pathological grading of non-muscle invasive bladder cancer(NMIBC).Methods The MRI images of 86 patients confirmed with NMIBC by surgical pathology were analyzed retrospectively.All patients underwent T2WI,diffusion weighted ima-ging(DWI),and dynamic contrast enhancement(DCE)examinations.Two radiologists independently measured tumor largest diam-eter(LD),actual tumor-wall contact length(ACTCL),ADCmean,ADCmin,and ADCmax values.ADC heterogeneity was calculated using the formula(ADCmax-ADCmin)/ADCmean.Differences in quantitative parameters between low-and high-grade NMIBC were compared using the Mann-Whitney U test,while differences in qualitative parameters were compared using the chi-square test.Univariate and multivariate logistic regression analyses were used to identify independent predictors of high-grade NMIBC,and receiver operating characteristic(ROC)curves were drawn to evaluate the performance of ADC heterogeneity combined with morphological indicators in assessing high-grade NMIBC.Results ADC heterogeneity and ACTCL were independent predictors for preoperative assessment of NMIBC pathological grading.The area under the curve(AUC)of ADC heterogeneity and ACTCL in assessing high-grade NMIBC were 0.843 and 0.744,respectively.The combined AUC was 0.902.The difference was statistically significant(P<0.05).Conclusion The combination of ADC heterogeneity with ACTCL can effectively improve the efficiency of preoperative assessment of NMIBC pathological grading,and providing more precise clinical decision-making and prognosis monitoring.

Objective To establish a mouse model of H1N1 influenza wind-heat syndrome by combining climate intervention with influenza virus nasal drops.Methods Seventy-two BALB/c mice were divided randomly into nine groups:a Control group,wind-heat(FR)groups(FR-3Day,FR-5Day),and Model groups(1LD-3Day,2LD-3Day,3LD-3Day,1LD-5Day,2LD-5Day,2LD-5Day,3LD-5Day)(n=8 mice per group).Mice in the Control group were housed in a normal environment,while mice in the FR and Model groups were kept in wind-heat conditions for 7 d.Mice in the Model groups received nasal PR8 influenza virus infection on the 8th day,and mice in the Control and FR heat groups received equal amounts of physiological saline nasal drops.After virus challenge,each group was housed in a normal environment and samples were taken on days 3 and 5.The appearance of the mice was observed and recorded and the lung index,routine blood parameters,lung tissue pathology,serum interleukin(IL)-6 levels,and virus titers were detected in each group based on their behavioral status,stools,and body temperature.Results After 7 d of wind-heat intervention,mice in the FR groups showed no significant abnormalities in terms of appearance,stools,body temperature,routine blood parameters,or lung tissue pathology compared with the Control group.The appearance,lung index,red blood cell count,hemoglobin,hematocrit,pathological result,and body temperature in the Model groups worsened progressively with increasing time and toxin dosage,while the neutrophil percentage,lymphocyte percentage,virus titer,and serum IL-6 levels peaked on day 3 after viral attack,for the same viral dose,and then decreased slightly on day 5.Conclusions PR8 nasal drops and 7 d of wind-heat climate intervention can be used to establish a mouse model of influenza wind-heat syndrome.

Objective:To investigate the effect of CT-derived fractional flow reserve (CT-FFR) measurement sites on the values and the diagnostic performance, and to determine the optimal measurement site for CT-FFR using invasive FFR as the reference standard.Methods:This study was part of the CT-FFR CHINA clinical trial. Patients with suspected coronary artery disease who were scheduled for invasive coronary angiography (ICA) were prospectively recruited from five clinical centers across the country from November 2018 to March 2020. Each enrolled patient underwent coronary CT angiography (CCTA), CT-FFR, ICA, and invasive pressure wire-based FFR assessments sequentially within one week. Four groups of CT-FFR values were obtained on each enrolled target vessels according to different CT-FFR measurement locations: 1, 2, 3 cm distal to the target lesion, and terminal vessel groups. Spearman and Bland-Altman analyses were used to explore the correlation and consistency of CT-FFR values and FFR values at different measurement sites. The measurement deviation of CT-FFR was also compared. Diagnostic accuracy and performance of CT-FFR, including sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC), in discriminating myocardial ischemia were analyzed across all measurement site groups on a per-vessel level, using FFR as the reference standard.Results:A total of 289 patients with 345 target lesion vessels were included. According to CCTA, there were 51 target vessels (14.8%) with<50% stenosis, 106 vessels (30.7%) with 50%-69% stenosis, and 188 vessels (54.5%) with stenosis≥70%. At per-vessel level, CT-FFR and FFR values at each measurement position group were highly positively correlated: 1 cm distal to target lesion group, r=0.734 ( P<0.001); 2 cm distal to target lesion group, r=0.732 ( P<0.001); 3 cm distal to target lesion group, r=0.737 ( P<0.001); terminal vessel group was 0.719 ( P<0.001). At per-vessel level, CT-FFR and FFR values of all measurement sites were in good agreement (Bland-Altman analysis results): 1 cm distal to target lesion group, 0.014 (95% LoA 0.002-0.026); 2 cm distal to target lesion group, 0.026 (95% LoA 0.015-0.038); 3 cm distal to target lesion group, 0.040 (95% LoA 0.039-0.051); terminal vessel group, 0.075 (95% LoA 0.064-0.087). And at per-vessel level, the accuracy of diagnosing myocardial ischemia with CT-FFR at 1 cm was highest [84.6% (95% CI 80.4%-88.3%)], and the lowest accuracy in the terminal vessel group [67.0% (95% CI 61.7%-72.0%)]. However, there was no significant difference in the diagnostic accuracy of CT-FFR at 1 cm, 2 cm [80.6% (95% CI 76.1%-84.6%)] and 3 cm [77.5% (95% CI 72.6%-81.7%)]. AUC of CT-FFR at 1 cm distal to the lesion were both highest for global level and moderately stenosis (50%-69%) lesions [0.85 (95% CI 0.81-0.89), 0.84 (95% CI 0.77-0.90)]. And the differences were statistically significant among the four measurement location groups (all P<0.05). Conclusions:The deviation of CT-FFR increases with measurement site distance distal to target lesions. One centimeter distal to the target lesion is the optimal measurement site, and the CT-FFR value here shows the highest diagnostic performance for myocardial ischemic lesions, especially for moderate stenosis.

Objective To explore the value of combining apparent diffusion coefficient(ADC)heterogeneity with morphological indicators in assessing the pathological grading of non-muscle invasive bladder cancer(NMIBC).Methods The MRI images of 86 patients confirmed with NMIBC by surgical pathology were analyzed retrospectively.All patients underwent T2WI,diffusion weighted ima-ging(DWI),and dynamic contrast enhancement(DCE)examinations.Two radiologists independently measured tumor largest diam-eter(LD),actual tumor-wall contact length(ACTCL),ADCmean,ADCmin,and ADCmax values.ADC heterogeneity was calculated using the formula(ADCmax-ADCmin)/ADCmean.Differences in quantitative parameters between low-and high-grade NMIBC were compared using the Mann-Whitney U test,while differences in qualitative parameters were compared using the chi-square test.Univariate and multivariate logistic regression analyses were used to identify independent predictors of high-grade NMIBC,and receiver operating characteristic(ROC)curves were drawn to evaluate the performance of ADC heterogeneity combined with morphological indicators in assessing high-grade NMIBC.Results ADC heterogeneity and ACTCL were independent predictors for preoperative assessment of NMIBC pathological grading.The area under the curve(AUC)of ADC heterogeneity and ACTCL in assessing high-grade NMIBC were 0.843 and 0.744,respectively.The combined AUC was 0.902.The difference was statistically significant(P<0.05).Conclusion The combination of ADC heterogeneity with ACTCL can effectively improve the efficiency of preoperative assessment of NMIBC pathological grading,and providing more precise clinical decision-making and prognosis monitoring.

Objective:To propose a model that could improve image quality of cone-beam computed tomography(CBCT),which based on region-discriminative generative adversarial networks(GAN),in radiotherapy for cervical cancer,so as to meet the requirements of self-adaptive radiotherapy for image quality.Methods:We employed a region-discriminative strategy and a generative adversarial networks idea to construct a model of improving CBCT image quality that could focus on local details of the images of radiotherapy for cervical cancer,which discriminator could improve the quality of generating local details of images.This model of image quality was applied to CBCT images of radiotherapy for cervical cancer.And then,the effects of processing image were evaluated through quantitative indicators and visualization.Results:Both texture clarity and contrast were significantly enhanced after CBCT image quality was improved.The signal to noise ratio of peak value of images was increased by 47.2%,and the indicator of similarity of structure was enhanced to>0.838.Compared with other model,both visualization and indicators can appear better efficiency of model.Compared with Unet network and CycleGAN network,the similarities of structure were respectively increased by 11.88% and 19.54%,and the signal to noise ratios were respectively increased by 19.75% and 25.99%.Conclusion:The GAN bases on region-discrimination can significantly improve the quality of generating integral and detailed CBCT image of radiotherapy for cervical cancer,which can provide new technical pathway for image quality of CBCT with low dose,and can play an important role for improving safety and effectiveness of radiotherapy.It has importantly clinical value for formulating and executing radiotherapy plan.

Objective:To develop a machine learning algorithm based on habitat imaging(HI),which can be used in the grading of gliomas by using multimodal magnetic resonance imaging(MRI),so as to construct the model of support vector machine(SVM)and the visualized heterogeneous regions of gliomas.Methods:A total of 335 glioma patients were collected from the 2019 brain tumor segmentation(BraTS)challenge competition of World Health Organization(WHO),which included 259 cases with high-grade gliomas(HGG)and 76 cases with low-grade gliomas(LGG).Subregions were divided based on HI technology.The PyRadiomics open-source package was used to extract the image features of region of interest(ROI),and to screen the features that stronger correlated with the high and low-grade gliomas.An SVM model was used to classify and predict the screened feature data.The heterogeneity of gliomas in images was analyzed through visualized characterization.The efficacy of glioma grading was assessed by using the area under curve(AUC)of the receiver operating characteristic(ROC)curve.Results:The AUC of test set exceeded 90%.The average accuracy of the performance indicators of test set was(92.74±2.88)%,and the average sensitivity was(93.90±2.10)%,and the average specificity was(90.36±4.59)%,and the average F1 score was(95.24±0.66)%when the tumors were divided into six habitat regions.The SVM model could showed important sub-regions in glioma grading in three-dimensional space.Conclusion:The study method based on HI has significant advantages in glioma grading,which can effectively realize visualized heterogeneity of tumor and construct model of the heterogeneity of tumor.