Objective To observe the efficacy of deep learning(DL)model based on PET/CT and its combination with Cox proportional hazard model for predicting progressive disease(PD)of lung invasive adenocarcinoma within 5 years after surgery.Methods The clinical,PET/CT and 5-year follow-up data of 250 patients with lung invasive adenocarcinoma were retrospectively analyzed.According to PD or not,the patients were divided into the PD group(n=71)and non-PD group(n=179).The basic data and PET/CT findings were compared between groups,among which the quantitative variables being significant different between groups were transformed to categorical variables using receiver operating characteristic(ROC)curve and corresponding cut-off value.Multivariant Cox proportional hazard model was used to select independent predicting factors of PD of lung invasive adenocarcinoma within 5 years after surgery.The patients were divided into training,validation and test sets at the ratio of 6∶2∶2,and PET/CT data in training set and validation set were used to train model and tuning parameters to build the PET/CT DL model,and the combination model was built in serial connection of DL model and the predictive factors.In test set,the efficacy of each model for predicting PD of lung invasive adenocarcinoma within 5 years after surgery was assessed and compared using the area under the curve(AUC).Results Patients'gender and smoking status,as well as the long diameter,SUVmax and SUVmean of lesions measured on PET images,the long diameter,short diameter and type of lesions showed on CT were statistically different between groups(all P＜0.05).Smoking(HR=1.787[1.053,3.031],P=0.031)and lesion SUVmax＞4.15(HR=5.249[1.062,25.945],P=0.042)were both predictors of PD of lung invasive adenocarcinoma within 5 years after surgery.In test set,the AUC of PET/CT DL model for predicting PD was 0.847,of the combination model was 0.890,of the latter was higher than of the former(P=0.036).Conclusion DL model based on PET/CT had high efficacy for predicting PD of lung invasive adenocarcinoma within 5 years after surgery.Combining with Cox proportional hazard model could further improve its predicting efficacy.

Objective Based on hemodynamic analysis, to investigate the cause of distal re-entry tear in Stanford type B aortic dissection after thoracic endovascular aortic repair (TEVAR).Methods A patient with type B aortic dissection was reexamined regularly with computed tomography angiography (CTA) at 1st month, 6th month, 12th month and 24th month after TEVAR. Based on the CTA images in each period, three-dimensional (3D) aorta models were reconstructed to perform morphological analysis and hemodynamic simulation.Results Compared with the diameter at 1st month after TEVAR, the diameter of true lumen at 12 months after TEVAR increased by 1.8 times and the global distortion of aorta increased by 16.67%. At postoperative 1st, 6th and 12th month, the maximum blood velocities at the new entry tear in systole were 69.6%, 33.7% and 92.1% higher than the average ones at distal landing zone, and the maximum wall shear stresses (WSSs) were 2.52, 2.32 and 3.52 times of the average WSSs respectively. In addition, the maximum time-averaged WSS (TAWSS) at 1st, 6th and 12th month after TEVAR were 1.88, 2.53 and 3.62 times of the mean TAWSS respectively.ConclusionsThe morphology of the aorta remodeled after TEVAR, and a sudden change in the diameter of true lumen occurred at distal anchoring zone and continued to increase. As a result, the blood flow velocity in this area accelerated, and the intima was continuously exposed to high WSS, leading to the redissection.

Objective To investigate the radiological features of invasive adenocarcinoma presenting as pGGN.Methods The pathological,clinical and imaging data of 45 pGGN lesions in 40 patients (9 males,31 females;average age (56.31 ± 3.44) years) with pulmonary adenocarcinoma in Tumor Hospital Affiliated to Harbin Medical University from November 2010 to April 2016 were analyzed retrospectively.All patients were confirmed by pathological diagnosis.x2 test and two-sample t test were used.ROC curve analysis was also used to evaluate the optimal cut-off points of lesion size and mass for diagnosing invasive adenocarcinoma.Results There were 20 patients with adenocarcinoma of situ (AIS) and minimally invasive adenocarcinoma (MIA) in group 1 (23 pGGN lesions),while another 20 patients with invasive adenocarcinoma in group 2 (22 pGGN lesions).The vascular convergence sign between 2 groups was statistically significant (13/23 in group 1 and 19/22 in group 2;x2 =4.874,P＜0.05).Statistically differences in the lesion size ((13.83±4.49) mm in group 1 and (20.32±5.97) mm in group 2) and in the lesion mass ((0.36± 0.34) g in group 1 and (0.98±0.44) g in group 2) were found between 2 groups (t values:4.131,5.355;both P＜0.01).ROC curve analysis showed that the optimal cut-off points of the size and the mass were 17.3 mm and 0.69 g respectively,with the sensitivities of 73％ (16/22) and 77％ (17/22),and the specificities of 87％(20/23) and 91％(21/23).Conclusion The size,mass,and vascular convergence sign are helpful to detect invasive adenocarcinoma present as pGGN.

Background and purpose:Gastric cancer impacts human health seriously. Accurate preoperative assessment of T staging and metastatic lymph nodes of gastric cancer was beneifcial to patients’ treatment options and their prognosis. The purpose of this study was to evaluate the diagnostic performance of diffusion-weighted magnetic resonance imaging for preoperative assessment of T staging and metastatic lymph nodes in patients with gastric cancer. Methods:This study selected 35 gastric cancer patients met the criteria for this prospective study. They all underwent gastric 3.0 T MRI+DWI imaging scan. These patients’ T stage and metastatic lymph nodes were evaluated before the surgery, with the reference of post-operative histopathological ifndings. Kappa consistency test was used to assess the consistency of T staging between the two methods. This study analyzed short axis diameter, long axis diameter and apparent diffusion coeffcient (ADC) values of lymph nodes, relative of muscle’s ADC (rADCm) values (rADCm=ADC values of lymph nodes/ADC values of right erector spinae), and relative of primary tumor’s ADC (rADCp) values (rADCp=ADC values of lymph nodes/ADC values of primary tumor) on MRI image. Independent samples test was used to assess the difference between metastatic lymph nodes and benign lymph nodes. The receiver operating characteristic(ROC) curve was generated to evaluate the accuracy of diffusion-weighted magnetic resonance imaging (MRI) for preoperative assessment of metastatic lymph nodes of gastric cancer.Results:The accuracy of diffusion-weighted MRI for T stages was 77.14%, 75% for T1, 100% for T2, 76.47% for T3 and 75.00% for T4 and respectively. There were statistically signiifcant differences in the long axis diameter, the short axis diameter, ADC value, rADCm and rADCp between metastatic lymph nodes and benign lymph nodes (P<0.05). The area under the ROC curve of rADCm was greater than thats of other criteria, so rADCm was the most signiifcant parameter. The best discriminative cut-off value of long axis, short axis, ADC value, rADCm value and rADCp value were 9.55 mm, 6.05 mm, 0.934×10-3mm2/s, 0.60 and 1.083, respectively. The sensitivity and speciifcity were 59.00% and 73.10%, 59.00% and 69.80%, 82.60% and 88.50%, 83.70% and 84.60%, 78.20% and 80.80%, respectively.Conclusion:Diffusion-weighted MRI has great signiifcance for preoperative assessment of T staging and metastatic lymph nodes of gastric cancer.

Objective To assess the clinical value of 18 F-FDG PET/CT for the patients with ascites of unknown causes.Methods A total of 106 patients with ascites undergoing 18 F-FDG PET/CT examination was retrospectively studied and 18F-FDG PET/CT imaging was interpreted by two ways.(1)PET/CT(localization):Diagnostic results of PET/CT depended on the degree of 18 F-FDG uptake in peritoneum with CT was trecoted as anatomical localization,and high 18F-FDG uptake in peritoneum was regarded as malignancy.(2)PET/CT(mor-phology):Morphological changes of peritoneum on CT imaging and the degree of 18 F-FDG uptake on PET ima-ging were simultaneously considered when interpreting the diagnostic results of PET/CT.Results In the differen-tial diagnosis of ascites of unknown cause,the sensitivity,specificity and accuracy of PET/CT( localization) were 90.2%,71.1%and 82.1%,respectively.These values of PET/CT(morphology)were 95.1%,93.3% and 94. 3%,and 85.2%of malignant ascites were found primary lesion.The specificity and accuracy of PET/CT( mor-phology)were higher than those of PET/CT(localization)(P=0.002,P<0.001).Statistical difference was not found in both sensitivities.Conclusion PET/CT( morphology) had higher clinical value than PET/CT( localiza-tion) in the differential diagnosis of ascites with unknown cause,and had important significance in detecting pri-mary cause of malignant ascites.

OBJECTIVETo explore the correlation between metabolic tumour volume (MTV) and microvessel density (MVD) and blood-borne metastasis in colorectal carcinoma.

METHODSThirty-six patients with CRC conformed by pathology underwent PET-CT examination before operation. SUVmax and MTV were obtained by PET VCRA software. The blood vessels were identified with CD34 immunohistochemical staining, and the MVD was recorded. The correlation between SUVmax and MTV with histological differentiation, T stage, MVD and blood-borne metastasis was analyzed.

RESULTSThe SUVmax, MTV and MVD in patients with blood-borne metastasis were 5.15 ± 5.41, (22.99 ± 18.63) cm³ and 14.17 ± 3.63, and were 10.65 ± 3.79, (16.95 ± 11.82) cm³ and 11.27 ± 3.69, respectively, in patients with non-blood-borne metastasis. The differences of SUVmax, MTV and MVD between blood-borne metastasis and non-blood-borne metastasis patients were statistically significant (all P > 0.05). Pearson correlation analysis found that there was no linear correlation between SUVmax and MVD, and the SUVmax was not statistically significant between high and low MVD groups (t = 0.919, P = 0.364). But there was a linear correlation between MTV and MVD (r = 0.621, P = 0.000), and the MTV was statistically significant between high and low MVD groups (t = 3.567, P = 0.001). The receiver-operating characteristic curves showed that MTV could be used to predict blood-borne metastasis of CRC, and the best cutoff value for MTV was 14.975 cm³, and the sensitivity, specificity, negative predictive value and positive predictive value were 85.7%, 54.5%, 72.3% and 64.2%, respectively. There were no significant relationships between SUVmax, MTV, MVD, blood-borne metastasis and histological differentiation (P > 0.05). With the increased T stage, the MTV, MVD and the probability of blood-borne metastasis were also increased (all P < 0.05).

CONCLUSIONSThere are correlations between MTV and MVD and blood-borne metastasis in CRC. The risk of blood-borne metastasis in patients with MTV > 14.975 cm³ is higher, and needs to take more effective intervention.

Colorectal Neoplasms ; blood supply ; diagnostic imaging ; pathology ; Fluorodeoxyglucose F18 ; Humans ; Microvessels ; pathology ; Multimodal Imaging ; Neoplasm Staging ; Neoplastic Cells, Circulating ; Positron-Emission Tomography ; ROC Curve ; Radiopharmaceuticals ; Sensitivity and Specificity ; Tomography, X-Ray Computed

Objective To explore the correlation between metabolic tumour volume ( MTV ) and microvessel density ( MVD ) and blood?borne metastasis in colorectal carcinoma. Methods Thirty?six patients with CRC conformed by pathology underwent PET?CT examination before operation. SUVmax and MTV were obtained by PET VCRA software. The blood vessels were identified with CD34 immunohistochemical staining, and the MVD was recorded. The correlation between SUVmax and MTV with histological differentiation, T stage, MVD and blood?borne metastasis was analyzed. Results The SUVmax, MTV and MVD in patients with blood?borne metastasis were 5.15±5.41, (22.99±18.63) cm3 and 14.17± 3.63, and were 10.65±3.79, (16.95±11.82)cm3 and 11.27±3.69, respectively, in patients with non?blood?borne metastasis. The differences of SUVmax, MTV and MVD between blood?borne metastasis and non?blood?borne metastasis patients were statistically significant( all P>0.05) . Pearson correlation analysis found that there was no linear correlation between SUVmax and MVD, and the SUVmax was not statistically significant between high and low MVD groups (t=0.919,P=0.364). But there was a linear correlation between MTV and MVD (r=0.621,P=0.000),and the MTV was statistically significant between high and low MVD groups ( t=3.567, P=0.001) . The receiver?operating characteristic curves showed that MTV could be used to predict blood?borne metastasis of CRC, and the best cutoff value for MTV was 14.975 cm3, and the sensitivity, specificity, negative predictive value and positive predictive value were 85. 7%, 54. 5%, 72.3% and 64. 2%, respectively. There were no significant relationships between SUVmax, MTV, MVD, blood?borne metastasis and histological differentiation (P>0.05). With the increased T stage, the MTV, MVD and the probability of blood?borne metastasis were also increased ( all P<0.05) . Conclusions There are correlations between MTV and MVD and blood?borne metastasis in CRC. The risk of blood?borne metastasis in patients with MTV>14.975 cm3 is higher, and needs to take more effective intervention.

Objective To explore the correlation between metabolic tumour volume ( MTV ) and microvessel density ( MVD ) and blood?borne metastasis in colorectal carcinoma. Methods Thirty?six patients with CRC conformed by pathology underwent PET?CT examination before operation. SUVmax and MTV were obtained by PET VCRA software. The blood vessels were identified with CD34 immunohistochemical staining, and the MVD was recorded. The correlation between SUVmax and MTV with histological differentiation, T stage, MVD and blood?borne metastasis was analyzed. Results The SUVmax, MTV and MVD in patients with blood?borne metastasis were 5.15±5.41, (22.99±18.63) cm3 and 14.17± 3.63, and were 10.65±3.79, (16.95±11.82)cm3 and 11.27±3.69, respectively, in patients with non?blood?borne metastasis. The differences of SUVmax, MTV and MVD between blood?borne metastasis and non?blood?borne metastasis patients were statistically significant( all P>0.05) . Pearson correlation analysis found that there was no linear correlation between SUVmax and MVD, and the SUVmax was not statistically significant between high and low MVD groups (t=0.919,P=0.364). But there was a linear correlation between MTV and MVD (r=0.621,P=0.000),and the MTV was statistically significant between high and low MVD groups ( t=3.567, P=0.001) . The receiver?operating characteristic curves showed that MTV could be used to predict blood?borne metastasis of CRC, and the best cutoff value for MTV was 14.975 cm3, and the sensitivity, specificity, negative predictive value and positive predictive value were 85. 7%, 54. 5%, 72.3% and 64. 2%, respectively. There were no significant relationships between SUVmax, MTV, MVD, blood?borne metastasis and histological differentiation (P>0.05). With the increased T stage, the MTV, MVD and the probability of blood?borne metastasis were also increased ( all P<0.05) . Conclusions There are correlations between MTV and MVD and blood?borne metastasis in CRC. The risk of blood?borne metastasis in patients with MTV>14.975 cm3 is higher, and needs to take more effective intervention.

Background and objective Mediastinal involvement in lung cancer is a highly significant prognostic fac-tor for survival, and accurate staging of the mediastinum will correctly identify patients who will benefit the most from surgery. Positron emission tomography/computed tomography (PET/CT) has become the standard imaging modality for the staging of patients with lung cancer. e aim of this study is to investigate 18-fluoro-2-deoxy-glucose (18F-FDG) PET/CT imaging in the detection of mediastinal disease in lung cancer. Methods A total of 72 patients newly diagnosed with non-small cell lung cancer (NSCLC) who underwent preoperative whole-body 18F-FDG PET/CT were retrospectively included. All patients underwent radical surgery and mediastinal lymph node dissection. Mediastinal disease was histologically confirmed in 45 of 413 lymph nodes. PET/CT doctors analyzed patients’ visual images and evaluated lymph node’s short axis, lymph node’s maxi-mum standardized uptake value (SUVmax), node/aorta density ratio, node/aorta SUV ratio, and other parameters using the histopathological results as the reference standard. e optimal cutovalue for each ratio was determined by receiver operator characteristic curve analysis. Results Using a threshold of 0.9 for density ratio and 1.2 for SUV ratio yielded high accuracy for the detection of mediastinal disease. e lymph node’s short axis, lymph node’s SUVmax, density ratio, and SUV ratio of integrated PET/CT for the accuracy of diagnosing mediastinal lymph node was 95.2%. e diagnostic accuracy of mediastinal lymph node with conventional PET/CT was 89.8%, whereas that of PET/CT comprehensive analysis was 90.8%. Conclusion Node/aorta density ratio and SUV ratio may be complimentary to conventional visual interpretation and SUVmax measure-ment. e use of lymph node’s short axis, lymph node’s SUVmax, and both ratios in combination is beer than either conven-tional PET/CT analysis or PET/CT comprehensive analysis in the assessment of mediastinal disease in NSCLC patients.

Objective To explore the diagnostic performance and the distributive characteristics of me-diastinal lymph nodes in lung tumor with PET/CT examination .Methods Thirty-three cases of preoperative whole-body 18 F-FDG PET/CT examination revealed pulmonary lesions ,a radical surgery and lymph node dis-section patients were included in this study .PET/CT doctors read the image of PET/CT and recorded the lymph node short diameter,CT value,SUVmax,and analysed the patient′s visual graphics.The application of PET/CT a-nalysis was used for diagnosis of the mediastinal lymph nodes ,and compared with the pathological findings .Re-sul ts The diagnostic accuracy of mediastinal lymph nodes with the conventional CT method alone was 84 .1%, with the conventional PET method alone was 82.8%,with the conventional PET/CT analysis was 91.7%,with the PET/CT comprehensive analysis was 95.2%;Five benign lymph nodes were mis -diagnosed.In this study, there were eight cases of lung cancer with mediastinal or hilar lymph node metastasis ,all of the lymph nodes loca-ted in the right lung ,and in which five cases were in the inner zone .Conclusion The PET/CT comprehensive a-nalysis of lymph node performs better than either the CT method alone or the PET method alone (χ2 =9.10,P<0.05);The lesions in the inner zone are more prone to occur mediastinal lymph node metastasis .