Objective Based on the mathematical models established in Department of Thoracic Surgery of Peking University People's Hospital for predicting malignant probability for solitary pulmonary nodules ( SPN),another continuous 145 patients with SPN were assessed to verify the accuracy of the model comparing with foreign models (Mayo model and VA model).Methods A retrospective cohort study in our institution included 145 patients with definite pathological diagnosis of SPN from Oct 2009 to Aug 2011,72 males and 73 females,average age (59.4 ± 12.2 ) years old.Clinical data included age,gender,course of disease,symptoms,history and quantity of smoking,time of smoking cessation,history of tumor,family history of tumor,tumor site,diameter,calcification,speculation,border,lobulation,traction of pleural,vascular convergence sign,and cavity.These raw data were incorporated into our model,Mayo model and VA model,the probability of malignant in every patient was calculated separately according to methods described before.The sensitivity and specificity of these 3 models were evaluated then.Afterwards,calibration of the 3 models was assessed by the Hosmer-Lemeshow (H-L) test.Discrimination was tested by calculating the area under curve ( AUC ) after the receiver operating characteristic (ROC) curve was drawn.Results 32.4％ (47 in 145 patients) of the nodules were malignant,and 67.6％ (98 in 145 patients) were benign in this group.Verified the accuracy of our model with sensitivity of 94.9％,specificity of 66.0％,positive predictive value of 85.3％ and negative predictive value of 86.1％.The H-L test showed good fitting in all models ( P ＞0.05 ).The AUC for our model was 0.874 ±0.035,and 0.784 ± 0.041 in Mayo model (P =0.004 compared to our model),0.754 ± 0.041 in VA model (P =0.002 compare to our model).And,there was not significant statistical difference between Mayo model and VA model (P ＞0.05 ).Our model has the best precision indexed by AUC,which were statistically significant differential compared with Mayo model and VA model.Conclusion The model established by our center has superior value than foreign counterparts in predicting the probability of malignant or benign in patients with SPN.

Objective:To estimate the probability of N2 lymph node metastasis and to assist physicians in making diagnosis and treatment decisions.Methods:We reviewed the medical records of 739 patients with computed tomography-defined stage Ⅰ non-small cell lung cancer ( NSCLC ) that had an exact tumor-node-metastasis stage after surgery.A random subset of three fourths of the patients ( n =554 ) were selected to develop the prediction model.Logistic regression analysis of the clinical characteristics was used to estimate the independent predictors of N2 lymph node metastasis.A prediction model was then built and externally validated by the remaining one fourth ( n=185 ) patients which made up the validation data set.The model was also compared with 2 previously described models.Results:We iden-tified 4 independent predictors of N2 disease:a younger age, larger tumor size, central tumor location, and adenocarcinoma or adenosquamous carcinoma pathology.The model showed good calibration ( Hos-mer-Lemeshow test:P=0.923) with an area under the receiver operating characteristic curve (AUC) of 0.748 (95%confidence interval, 0.710-0.784) .When validated with all the patients of group B, the AUC of our model was 0.781 (95% CI: 0.715 -0.839) and the VA model was 0.677 (95% CI:0.604-0.744) (P =0.04).When validated with T1 patients of group B, the AUC of our model was 0.837 (95%CI:0.760 -0.897) and Fudan model was 0.766 (95% CI: 0.681 -0.837) (P <0.01) .Conclusion:Our prediction model estimated the pretest probability of N2 disease in computed tomography-defined stageⅠNSCLC and was more accurate than the existing models.Use of our model can be of assistance when making clinical decisions about invasive or expensive mediastinal staging procedures.

Objective To determine the value of endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) for staging of lung cancer. Methods The study was retrospective, a total of 52 patients underwent EBUSTBNA for known or suspected lung cancer. All patients were detected enlarged mediastinal lymph nodes on CT scan ( ≥ 1.0cm). Results Of the 52 patients, 41 patients were found with N2 or N3 disease on EBUS-TBNA. 11 patients with negative EBUS-TBNA underwent thoracoscopy or thoracotomy for pulmonary resection and mediastinal lymph node dissection, 9 patients were confirmed N0 by pathology, whereas 2 patients had metastatic lymph node. The diagnostic sensitivity, specificity, accuracy, positive predictive value and negative predictive value of EBUS-TBNA for the mediastinal staging of lung cancer were 95.3%, 100%, 96.2%, 100%, and 81.8%, respectively. The procedure was uneventful, and there were no postoperative complications. Conclusion EBUS-TBNA is an effective and safe technique for mediastinal staging in lung cancer patients.

Objective To evaluated the role of endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) in the diagnosis of mediastinal lesions around the trachea.MethodsThe study was retrospective, between September 2009 to July 2010, 34 consecutive patients with enlarged mediastinal lymph nodes or mediastinal masses of unknown origin underwent EBUS-TBNA.Patients in whom EBUS-TBNA was nondiagnostic subsequently underwent surgical biopsy or a minimum of 6 months clinical and radiologic follow-up.ResultsOf the 34 patients, EBUS-TBNA achieved definitive diagnosis in 28 patients (82.4％), 10 were diagnosed as malignancies, 18 were diagnosed as benign.The sensitivity, specificity,and accuracy of EBUS-TBNA in distinguishing benign from malignant mediastinal lesions were 90.9％, 100％, and 97.1％,respectively.EBUS was well tolerated by all of the patients with no complications.ConclusionEBUS-TBNA of mediastinal lesions around the trachea is a minimally invasive safe diagnostic technique with high yield.

Objective To review the experience d EBUS-TBNA for staging of lung cancer and the value in diagnosing thoracic diseases in our single center.Methods The data of 343 patients who underwent EBUS-TBNA from September 2009 to August 2011 in our institution were retrospectively reviewed.There were 219 males and 124 females with an average age of (59.4 ± 13.6 ) years.Based on their primary indication,patyients were divided into three categories:group A:with known or strongly suspected lung cancer and enlarged mediastinal lymph nodes on chest radiographic examination ( short axis ≥ 1.0cm) ; group B:with enlarged mediastinal lymph nodes or mediastinal masses of unknown origin; and group C:with pulmonary parenchymal mass located close to the central airways.Results The average short axis diameter of the thoracic lesions was ( 1.94 ± 1.01 ) cm ( range from 0.5 to 8.0cm),and 2.66 punctures were performed per lesion.In group A ( n =208 ),151 patients were confirmed to have mediestinal lymph nodes metastasis while 51 showed negative results.Four patients were diagnosed as tuberculosis and two were confirmed to be stage Ⅱ sarcoidosis.37 in the 51 patients with negative EBUS-TBNA underwent thoracoscopic or thoracotomy for pulmonary resection and mediastinal lymph node dissection.Postoperative pathology confirmed that 32 patients did not have lymph nodes metastases.The diagnostic sensitivity,specificity,accuracy,positive predictive and negative predictive of EBUS-TBNA for the mediastiral staging of lung cancer were 96.8％ (151/156),100.0％ (32/32),97.3％ ( 183/188 ),100％ ( 151/151 ) and 86.5％ (32/37),respectively.In group B ( n =94),22 patients had malignancy and 72 had benign diseases.Thirteen patients received operative validation in the 23 cases which were diagnosed as proliferative lymph nodes by EBUS-TBNA,and by further operation two and three patients were confirmed as malignancy and other benign diseases respectively.The sensitivity,negative predictive value ( NPV ) and accuracy of EBUS-TBNA in distinguishing malignant mediastinal diseases was 88.0％ (22/25)、100％ (73/73) 、95.9％ (70/73)and 97.9％ (92/94),respectively.In group C( n =41 ),malignant diagnosis was achieved in 33 patients,while 4 patients confirmed as malignancy by further operations in the other 8 negative cases.The diagnostic sensitivity and accuracy of EBUS-TBNA for the diagnosis of unknown pulmonary parenchymal mass were 89.2％ (33/37) and 90.2％ (37/41),respectively.All the procedures were uneventful and no complication occurred.Conclusion EBUS-TBNA is a highly effective and safe procedure in the diagnosis of thoracic diseases and staging.of lung cancer.

Objective To determine the value of endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) for the diagnosis of intrapulmonary tumors located adjacent to the central airway.MethodsThe study was retrospective,from September 2009 to September 2011,33 patients with pulmonary masses located close to the central airways suspected to be lung cancer were accessed by EBUS-TBNA.Conventional bronchoscopic biopsy before EBUSTBNA was nondiagnostic in all cases.If EBUS-TBNA did not result in a formal pathological diagnosis of malignancy,patients were subsequently referred for a surgical procedure.ResultsOf the 33 patients,EBUS-TBNA confirmed lung cancer in 29 cases (4 small cell lung cancer,25 non-small cell lung cancer).Four patients were not confirmed by EBUS-TBNA,3 cases were diagnosed as squamous cell carcinoma by thoracoscoopy or thoracotomy,the other one was a pulmonary inflammatory lesion diagnosed by thoracoscopy.The sensitivity,specificity,accuracy,negative predictive value and positive predictive value of EBUS-TBNA for the diagnosis of intrapulmonary lesions was 90.2％,100％,90.9％,25％,and 100％,respectively.The procedure was uneventful,and there were no complications.ConclusionEBUS-TBNA is an effective tool with a high yield for the diagnosis of intrapulmonary lesions located adjacent to the central airway.

Objective To assess the value of multi-modal image-guided transrectal ultrasonography in the diagnosis of prostatic nodules in elderly patients.Methods Sixty-four elderly patients suspected of prostate cancer (PCA) were enrolled from December 2015 to December 2016.Sixty-four patients with 72 nodules underwent transrectal ultrasound (TRUS),contrast-enhanced transrectal ultrasound (CETRUS) and transrectal real-time tissue elastography (TRTE).A combination of systematic biopsy and suspicious sitetargeted biopsy was conducted.The accuracies of different detection methods for prostate cancer were assessed against the gold standard of histological examination of prostate biopsy samples.Results Among the 72 nodules,31 were prostatic hyperplasia,5 were chronic prostatitis,35 were prostatic cancer,and one was prostatic lymphoma.There were significant differences in enhancement strength,enhancement time fast-in and degree of elasticity on TRTE and CETRUS between the malignant and benign groups (x2 =28.794,10.889,52.898;P =0.000,0.001,0.000,respectively).When the 35 PCA nodules were divided into two subgroups based on the Gleason score,there were statistically significant differences in enhancement strength,homogeneity of enhancement,and enhancement time fast-in and fast-out between them (x2=6.073,12.315,4.717,18.093;P =0.048,0.001,0.030,0.000,respectively).The combination of CETRUS and TRTE in diagnosing prostate nodules produced a sensitivity of 83.3 ％,a specificity of 86.1 ％,an accuracy of 84.7 ％,a positive predictive value of 85.7％,and a negative predictive rate of 83.8％,better than either method alone.Conclusions Multi-modal image-guided transrectal ultrasonography has an advantage in providing information on the perfusion and elasticity of prostate nodules in the elderly patients and thus has important clinical value for the diagnosis of prostate nodules.

Objective To evaluated the role of endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) in the diagnosis of thoracic sarcoidosis.Methods The study was retrospective,from September 2009 to June 2011,35 patients with suspected sarcoidosis,with enlarged hilar or mediastinal lymph nodes on computed tomography ( ≥1.0 cm),underwent EBUS-TBNA.Patients in whom EBUS-TBNA was nondiagnostic subsequently underwent surgical biopsy or a minimum of 6 months clinical and radiologic follow-up.Results EBUS-TBNA was performed on a total of 87 lymph node stations in 35 patients.Of the enlarged lymph nodes,64 (73.6％) were located in the mediastinal region and the remaining 23 ( 26.4％ ) around the hilar or interlobar area.A final diagnosis of sarcoidosis was made for 28 (80％) of the patients.In patients with a final diagnosis of sarcoidosis,EBUS-TBNA demonstrated noncaseating epithelioid cell granulomas in 25 ( 89.3％ ) of the patients.EBUS was well tolerated by all of the patients with no complications.Conclusion EBUS-TBNA is a safe procedure with a high yield for the diagnoses of thoracic sarcoidosis of stage Ⅰ or Ⅱ.

With the dramatically increasing detection rate of ground-glass nodules (GGN), exact understanding and treatment strategy of them has become the hottest issue currently. More and more studies have begun to explore the underlying mechanisms of their indolent characteristics and favorable prognosis from the perspectives of molecular evolution and immune microenvironment. GGN has different dominating gene mutations at different evolutional stages. The pure GGN has a lower tumor mutation burden and genomic instability, while a gradually evolutionary feature of genomic mutation along with the pathological progression can be observed. GGN has less infiltration of immune cells, and they are under the pressure of immune surveillance with weakened immune escape. With the increase of solid components, an inhibitory immune microenvironment is gradually established and immune escape is gradually enhanced, leading to rapid tumor growth. Further exploration of the molecular characteristics of GGN will help to more precisely distinguish these highly heterogeneous lesions, which could be helpful to make personalized treatment plans.

Objective:To examine the efficiacy of a machine learning diagnostic model specifically for solid nodules in multiple pulmonary nodules constructed by combining patient clinical information and CT features.Methods:Totally 446 solid nodules resected from 287 patients with multiple pulmonary nodules in Department of Thoracic Surgery, Peking University People′s Hospital from January 2010 to December 2018 were included. There were 117 males and 170 females, aging (61.4±9.9) yeras (range: 33 to 84 years). The nodules were randomly divided into training set (228 patients with 357 nodules) and test set (59 patients with 89 nodules) by a ratio of 4∶1. The extreme gradient boosting (XGBoost) algorithm was used to generate a predictive model (PKU-ML model) on the training set. The accuracy was verified on the test set and compared with previous published models. Finally, an independent single solid nodule set (155 patients, 95 males, aging (62.3±8.3) years (range: 37 to 77 years)) was used to evaluate the accuracy of the model for predictive value of single solid nodules. Area of receiver operating characteristic curve (AUC) was used to evaluate diagnostic values of models.Results:In the training set, the AUC of the PKU-ML model was 0.883 (95% CI: 0.849 to 0.917). In the test set, the performance of the PKU-ML model (AUC=0.838, 95% CI: 0.754 to 0.921) was better than the models designed for single pulmonary nodules (Brock model: AUC=0.709, 95% CI: 0.603 to 0.816, P=0.04; Mayo model: AUC=0.756, 95% CI: 0.656 to 0.856, P=0.01; VA model: AUC=0.674, 95% CI: 0.561 to 0.787, P<0.01), similar with PKUPH model (AUC=0.750, 95% CI: 0.649 to 0.851, P=0.07). In the independent single solid nodules set, the PKU-ML model also achieved good performance (AUC=0.786, 95% CI: 0.701 to 0.872). Conclusion:The machine learning based PKU-ML model can better predict the malignancy of solid nodules in multiple pulmonary nodules, and also achieved a good performance in predicting the malignancy of single solid pulmonary nodules compared to mathematical models.