Construction of a prediction model for lung cancer combined with chronic obstructive pulmonary disease by combining CT imaging features with clinical features and evaluation of its efficacy / 中华放射学杂志

Objective:To assess the effectiveness of a model created using clinical features and preoperative chest CT imaging features in predicting the chronic obstructive pulmonary disease (COPD) among patients diagnosed with lung cancer.Methods:A retrospective analysis was conducted on clinical (age, gender, smoking history, smoking index, etc.) and imaging (lesion size, location, density, lobulation sign, etc.) data from 444 lung cancer patients confirmed by pathology at the Second Affiliated Hospital of Naval Medical University between June 2014 and March 2021. These patients were randomly divided into a training set (310 patients) and an internal test set (134 patients) using a 7∶3 ratio through the random function in Python. Based on the results of pulmonary function tests, the patients were further categorized into two groups: lung cancer combined with COPD and lung cancer non-COPD. Initially, univariate analysis was performed to identify statistically significant differences in clinical characteristics between the two groups. The variables showing significance were then included in the logistic regression analysis to determine the independent factors predicting lung cancer combined with COPD, thereby constructing the clinical model. The image features underwent a filtering process using the minimum absolute value convergence and selection operator. The reliability of these features was assessed through leave-P groups-out cross-validation repeated five times. Subsequently, a radiological model was developed. Finally, a combined model was established by combining the radiological signature with the clinical features. Receiver operating characteristic (ROC) curves and decision curve analysis (DCA) curves were plotted to evaluate the predictive capability and clinical applicability of the model. The area under the curve (AUC) for each model in predicting lung cancer combined with COPD was compared using the DeLong test.Results:In the training set, there were 182 cases in the lung cancer combined with COPD group and 128 cases in the lung cancer non-COPD group. The combined model demonstrated an AUC of 0.89 for predicting lung cancer combined with COPD, while the clinical model achieved an AUC of 0.82 and the radiological model had an AUC of 0.85. In the test set, there were 78 cases in the lung cancer combined with COPD group and 56 cases in the lung cancer non-COPD group. The combined model yielded an AUC of 0.85 for predicting lung cancer combined with COPD, compared to 0.77 for the clinical model and 0.83 for the radiological model. The difference in AUC between the radiological model and the clinical model was not statistically significant ( Z=1.40, P=0.163). However, there were statistically significant differences in the AUC values between the combined model and the clinical model ( Z=-4.01, P=0.010), as well as between the combined model and the radiological model ( Z=-2.57, P<0.001). DCA showed the maximum net benifit of the combined model. Conclusion:The developed synthetic diagnostic combined model, incorporating both radiological signature and clinical features, demonstrates the ability to predict COPD in patients with lung cancer.

Value of CT pulmonary vascular quantitative parameters in diagnosis of chronic obstructive pulmonary disease patients and high-risk groups / 中华放射学杂志

Objective:To explore the diagnostic value of CT pulmonary vascular quantitative parameters in patients with chronic obstructive pulmonary disease (COPD) and high-risk groups.Methods:A retrospective study of 1 126 patients who underwent chest CT examination and pulmonary function test in Shanghai Tongji Hospital from January 2015 to August 2020. According to lung function, they were divided into COPD group (471 cases), high-risk group (454 cases), and normal control group (201 cases). Pulmonary vascular parameters on chest CT, including the total number of vessels (N total), the number cross-sectional area of vessels under 5 mm 2 (N CSA<5), lung surface area (LSA), number of pulmonary blood vessels per unit lung surface area (N total/LSA) and the total area of vessels (VA total) at a 9, 15, 21 mm depth from the pleural surface, and the total blood vessel volume (TBV), blood vessel volume under 5 mm 2 and 10 mm 2(BV5 and BV10) were measured quantitatively. Kruskal-Wallis H test was used to compare the differences of quantitative parameters of pulmonary vascular in the three groups; Spearman rank test was used to analyze the correlation between CT pulmonary vascular parameters and pulmonary function. Results:There were significant differences in N total/LSA at a 9, 15, 21 mm depth from the pleural surface among three groups ( P<0.05). There were significant differences in N CSA<5, N total at a 9 mm depth from the pleural surface among three groups ( P<0.05). There were significant differences in LSA at a 9 mm depth from the pleural surface, N CSA<5, N total, LSA, VA total at a 15, 21 mm depth from the pleural surface and TBV, BV5 and BV10 among three groups ( P<0.05). In high-risk group, there were positive correlation between N total/LSA, VA total at a 9 mm depth from the pleural surface and some pulmonary function parameters ( r=0.095-0.139, P<0.05). N CSA<5, N total, LSA, N total/LSA, TBV, BV5 and BV10 at different depth from pleural surface were negatively correlated with some pulmonary function parameters ( r=-0.110--0.215, P<0.05). In COPD group, number of vessels at a 9 mm depth from the pleural surface was positively correlated with the diffusion capacity for carbon monoxide of the lung single breath ( r=0.105, 0.103, P<0.05). In addition to N total/LSA were positively correlated with lung function parameters ( r=0.181-0.324, P<0.05), the remaining pulmonary vascular parameters were negatively correlated with some pulmonary function parameters ( r=-0.092--0.431, P<0.05). Conclusion:Quantitative chest CT imaging are able to effectively evaluate pulmonary vascular changes in COPD patients and high-risk groups, and the quantitative parameters of pulmonary vascular CT may distinguish COPD from high-risk groups, providing a novel means for early diagnosis of COPD and prediction of high-risk groups.

A survey report on the application status of artificial intelligence in medical imaging in China / 中华放射学杂志

Objective:To explore the current status of the artificial intelligence (AI) developments in medical imaging in China, and to provide data for the development of AI.Methods:In May 2022, the Radiology Branch of the Chinese Medical Association and the China Medical Imaging AI Industry-University-Research Innovation Alliance jointly launched a nationwide survey on the application status and development needs of medical imaging AI in China in the form of a questionnaire. This survey was carried out for different groups of people, focusing on the clinical applications of medical imaging AI, enterprise development, and educational needs in colleges and universities, with the descriptive statistical analysis performed.Results:China′s medical imaging AI has made great progress in clinical applications, in enterprise developments, as well as in the education and teaching areas. In terms of clinical application, 90.8% (5 765/6 347) of the survey respondents had a preliminary understanding of AI. There were 62.1% (3 798/6 119) doctors confirmed the applications medical imaging AI products in their departments. AI products were applied in the whole process of medical imaging examination, especially in assistance of the diagnosis. The application of pulmonary nodules screening accounted for 89.5% (3 401/3 798) of all medical imaging AIs. The main factors restricting the rapid development of medical imaging AI included lack of experts [47.3% (3 002/6 347)], poor data quality [45.7% (2 898/6 347)] and imperfect function of the products [40.4% (2 566/6 347)]; in terms of enterprises, there were 65.4% enterprises with a scale of less than 100 employees (17/26), and 34.6% with a scale of more than 100 employees (9/26). The main group of the customers were the hospitals above the second level, accounting for about 92.3% (24/26); in terms of education, the number and quality of AI courses, practical operations and lectures currently carried out by schools vary between different levels. The AI courses for graduated students accounted for about 22.5% (86/381), which were the largest in number; while the proportion of AI courses for junior college students, undergraduates and regular trainees were less than 15%. More than 60% of the students thought it necessary for schools to establish AI courses. Among all the students, the master′s and doctoral candidates had the greatest demand for additional AI courses [84.8% (323/381)].Conclusions:The development and popularization of medical imaging AI in China continues to prosper, with opportunities and challenges coexisting. It is necessary to adhere to the orientation of clinical needs, and to realize the coordinated development of clinical application, enterprise development, as well as education and teaching.

The value of CT features in predicting visceral pleural invasion in clinical stage ⅠA peripheral lung adenocarcinoma under the pleura / 中华放射学杂志

Objective:To investigate the value of CT features in predicting visceral pleural invasion (VPI) in clinical stage ⅠA peripheral lung adenocarcinoma under the pleura.Methods:The CT signs of 274 patients with clinical stage ⅠA peripheral lung adenocarcinoma under the pleura diagnosed in Changzheng Hospital of Naval Medical University from January 2015 to November 2021 were retrospectively analyzed. According to the ratio of 6∶4, 164 patients collected from January 2015 to August 2019 were used as the training group, and 110 patients collected from August 2019 to November 2021 were used as the validation group. The maximum diameter of the tumor (T), the maximum diameter of the consolidation part (C), and the minimum distance between the lesion and the pleura (DLP) were quantitatively measured, and the proportion of the consolidation part was calculated (C/T ratio, CTR). The CT signs of the tumor were analyzed, such as the relationship between the tumor and the pleura classification, the presence of a bridge tag sign, the location of the lesion, density type, shape, margin, boundary and so on. Variables with significant difference in the univariate analysis were entered into multivariate logistic regression analysis to explore predictors for VPI, and a binary logistic regression model was established. The predictive performance of the model was analyzed by receiver operating characteristic curve in the training and validation group.Results:There were 121 cases with VPI and 153 cases without VPI among the 274 patients with lung adenocarcinoma. There were 79 cases with VPI and 85 cases without VPI in the training group. Univariate analysis found that the maximum diameter of the consolidation part, CTR, density type, spiculation sign, vascular cluster sign, relationship of tumor and pleura and bridge tag sign between patients with VPI and those without VPI were significantly different in the training group( P<0.05). Multivariate logistic regression analysis found the relationship between tumor and pleura [taking type Ⅰ as reference, type Ⅱ (OR=6.662, 95%CI 2.364-18.571, P<0.001), type Ⅲ (OR=34.488, 95%CI 8.923-133.294, P<0.001)] and vascular cluster sign (OR=4.257, 95%CI 1.334-13.581, P=0.014) were independent risk factors for VPI in the training group. The sensitivity, specifcity, and area under curve (AUC) for the logistic model in the training group were 62.03%, 89.41% and 0.826, respectively, using the optimal cutoff value of 0.504. The validation group obtained an sensitivity, specifcity, and AUC of 92.86%, 47.06%, and 0.713, respectively, using the optimal cutoff value of 0.449. Conclusion:The relationship between the tumor and the pleura and the vascular cluster sign in the CT features can help to predict visceral pleural invasion in the clinical stage ⅠA peripheral lung adenocarcinoma under the pleura.

Prediction of pulmonary function test parameters by parameter response mapping parameters based on random forest regression model / 中华放射学杂志

Objective:To explore the predictive value of random forest regression model for pulmonary function test.Methods:From August 2018 to December 2019, 615 subjects who underwent screening for three major chest diseases in Shanghai Changzheng Hospital were analyzed retrospectively. According to the ratio of forced expiratory volume in the first second to forced vital capacity (FEV 1/FVC) and the percentage of forced expiratory volume in the first second to the predicted value (FEV 1%), the subjects were divided into normal group, high risk group and chronic obstructive pulmonary disease (COPD) group. The CT quantitative parameter of small airway was parameter response mapping (PRM) parameters, including lung volume, the volume of functional small airways disease (PRMV fSAD), the volume of emphysema (PRMV Emph), the volume of normal lung tissue (PRMV Normal), the volume of uncategorized lung tissue (PRMV Uncategorized) and the percentage of the latter four volumes to the whole lung (%). ANOVA or Kruskal Wallis H was used to test the differences of basic clinical characteristics (age, sex, height, body mass), pulmonary function parameters and small airway CT quantitative parameters among the three groups; Spearman test was used to evaluate the correlation between PRM parameters and pulmonary function parameters. Finally, a random forest regression model based on PRM combined with four basic clinical characteristics was constructed to predict lung function. Results:There were significant differences in the parameters of whole lung PRM among the three groups ( P<0.001). Quantitative CT parameters PRMV Emph, PRMV Emph%, and PRMV Normal% showed a moderate correlation with FEV 1/FVC ( P<0.001). Whole lung volume, PRMV Normal,PRMV Uncategorized and PRMV Uncategorized% were strongly or moderately positively correlated with FVC ( P<0.001), other PRM parameters were weakly or very weakly correlated with pulmonary function parameters. Based on the above parameters, a random forest model for predicting FEV 1/FVC and a random forest model for predicting FEV 1% were established. The random forest model for predicting FEV 1/FVC predicted FEV 1/FVC and actual value was R 2=0.864 in the training set and R 2=0.749 in the validation set. The random forest model for predicting FEV 1% predicted FEV 1% and the actual value in the training set was R 2=0.888, and the validation set was R 2=0.792. The sensitivity, specificity and accuracy of predicting FEV 1% random forest model for the classification of normal group from high-risk group were 0.85(34/40), 0.90(65/72) and 0.88(99/112), respectively; and the sensitivity, specificity and accuracy of predicting FEV 1/FVC random forest model for differentiating non COPD group from COPD group were 0.89(8/9), 1.00 (112/112) and 0.99(120/121), respectively. While the accuracy of two models combination for subclassification of COPD [global initiative for chronic obstructive lung disease (GOLD) Ⅰ, GOLDⅡ and GOLD Ⅲ+Ⅳ] was only 0.44. Conclusions:Small airway CT quantitative parameter PRM can distinguish the normal population, high-risk and COPD population. The comprehensive regression prediction model combined with clinical characteristics based on PRM parameter show good performance differentiating normal group from high risk group, and differentiating non-COPD group from COPD group. Therefore, one-stop CT scan can evaluate the functional small airway and PFT simultaneously.

Lung cancer screening with low-dose CT: a study on risk factors and establishing the high-risk model for lung cancer / 中华放射学杂志

Objective To establish standards of high-risk populations for low-dose CT(LDCT)lung cancer screening projects by analyzing lung cancer risk factors. Methods LDCT was performed in 6 990 subjects undergoing physical examinations in Changzheng Hospital from September 2013 to September 2016, including 4 567 males and 2 423 females. Mineralization nodes, solid nodules, pure ground glass nodules and partial solid nodules were defined as positive results.All cases of lung cancer were confirmed by pathological examination. The morbidity and risk factors of lung cancer were analyzed using t-test, chi-square test and logistic regression analysis.And there were 13 risk factors involved,including age,sex, body mass index(BMI),smoking,the family history of lung cancer and other malignant tumors,the history of chronic bronchitis or chronic obstructive pulmonary disease,the history of pulmonary fibrosis,the history of tuberculosis, the history of other malignant tumors, the history of cardiovascular disease, the history of second hand smoke exposure,the history of exposure to radon and the history of exposure to asbestos.The cut point of risk factors was analyzed according to the receiver operating characteristic (ROC) curve. Results Sixty-nine cases of lung cancer and 85 malignant nodules were detected in this screening.There were 34 males and 35 females among the lung cancer patients and their age ranged from 24 to 88 years with an average age of(60±16)years.In all the factors involved in this study,sex(χ2=7.937),age(t=19.509,χ2=29.991) and cardiovascular disease (χ2=5.333) were proved to be the risk factors of lung cancer by single factor analysis.Logistic regression analysis showed that sex(OR=0.478,95%CI:0.297-0.769,P=0.002)and age(OR=1.024,95%CI:1.024-1.060,P=0.001)were independent risk factors of lung cancer.ROC analysis showed an area under the curve(AUC)of 0.62 for age,0.587 for age of males and 0.659 for age of females. According to ROC curves, people over 56.5 years old (sensitivity 55.1%, specificity 75.0%, accuracy 74.8%),males over 56.5 years old(sensitivity 52.9%,specificity 73.4%,accuracy 73.3%)and females over 57.5 years old(sensitivity 57.1%,specificity 80.5%,accuracy 80.1%)were high-risk groups.Conclusions In this study,sex and age were proved to be the risk factors of lung cancer.Males over 56.5 years old and females over 57.5 years old are more likely to suffer from lung cancer.However,this study is a single center study,so that other risk factors of lung cancer are not ruled out completely.

Multivariate analysis of CT features of visceral pleural invasion of peripheral non-small cell lung cancer with the largest diameter less than or equal to 3 cm / 实用放射学杂志

Objective To analyze the CT features of visceral pleural invasion of peripheral non-small cell lung cancer with the largest diameter less than or equal to 3 cm to improve the diagnostic accuracy.Methods The CT features of 249 patients with peripheral non-small cell lung cancer with the largest diameter less than or equal to 3 cm were analyzed retrospectively.Multivariate Logistic regression was performed to analyze the independent risk factors of the visceral pleural invasion.Results Visceral pleural invasion was observed in 61/249 of the cases.Gender,the largest diameter,type,spiculated sign,lobulated sign,DLP and relationship of nodule and visceral pleura between the two groups were significantly different (P＜0.05).Multivariate Logistic regression analysis showed that the largest diameter and spiculated sign of nodules were independent risk factors for visceral pleural invasion.Visceral pleural invasion was uncommon in TypeⅠ.The probability of the visceral pleural invasion in typeⅡ,typeⅢand typeⅣ was 0.023 times (95% CI:0.006-0.093),0.225 times (95% CI:0.078-0.648)and 0.645 times (95% CI:0.261-2.300)as much as that of type Ⅴ,respectively.Visceral pleural invasion was more likely to occur in Type V than other types (P＜0.05).Conclusion The largest diameter and spiculated sign are independent predictors for visceral pleural invasion in non-small cell lung cancer with the largest diameter less than or equal to 3 cm.Nodules closely adjacent to the pleura are more likely to invade the visceral pleural.

Diagnostic Value of Volume-Based Fluorine-18-Fluorodeoxyglucose PET/CT Parameters for Characterizing Thyroid Incidentaloma

OBJECTIVE: To assess clinical value of fluorine-18-fluorodeoxyglucose positron emission tomography/computed tomography (PET/CT) for differentiation of malignant from benign focal thyroid incidentaloma. MATERIALS AND METHODS: This retrospective study included 99 patients with focal thyroid incidentaloma of 5216 non-thyroid cancer patients that had undergone PET/CT. PET/CT semi-quantitative parameters, volume-based functional parameters, metabolic tumor volume (MTV), and total lesion glycolysis (TLG) of thyroid incidentaloma were assessed. Receiver-operating characteristic (ROC) analysis was conducted and areas under the curve (AUC) were compared by Hanley and McNeil test to evaluate usefulness of maximum standardized uptake value (SUVmax), MTV and TLG, as markers for differentiating malignant from benign thyroid incidentalomas. RESULTS: Of 99 thyroid incidentalomas, 64 (64.6%) were malignant and 35 (35.4%) were benign. Malignant thyroid incidentalomas were larger (1.8 cm vs. 1.3 cm, p = 0.006), and had higher SUVmax (11.3 vs. 4.8, p 0.05). A threshold TLG 4.0 of 2.475 had 81.3% sensitivity and 94.3% specificity for identifying malignant thyroid incidentalomas. CONCLUSION: Volume-based PET/CT parameters could potentially have clinical value in differential diagnosis of thyroid incidentaloma along with SUVmax.

Progress in research of relationship between ambient air PM2.5 and lung diseases / 中华流行病学杂志

Fine Particulate Matter (PM2.5-particles with an aerodynamic diameter ≤2.5 μm)can penetrate deeply into the lung,deposit in the alveoli,and consequently impair lung function.Both short term and long term exposures to PM2.5 are associated with the incidence of respiratory diseases (e.g.asthma,chronic obstructive pulmonary disease,lung cancer).This paper summarizes the effects of ambient air PM2.5 exposure on human respiratory system revealed by epidemiological studies.

Predictive value of quantitative CT features of pulmonary subsolid nodules in three different dimensions for the pathologic grade / 实用放射学杂志

Objective To investigate the predictive value of the whole nodule size and solid component size of lung adenocarcinoma manifesting as subsolid nodule(SSN) in three different dimensions for pathologic grade.Methods We evaluated retrospectively preoperative chest HRCT data of 125 patients with 127 SSNs surgically resected and pathologically conformed lung adenocarcinomas.All specimens were divided into two groups: a total of 69 SSNs in group A, including 22 AIS and 47 MIA;a total of 58 SSNs in group B, only including IAC.Computer aided diagnosis software were used to measure the one dimension maximum diameter of solid component with lung window setting(1D-SCLW),two dimension maximum diameter of solid component with lung window setting(2D-SCLW),one dimension maximum diameter of solid component with mediastinal window setting(1D-SCMW),two dimension maximum diameter of solid component with mediastinal window setting(2D-SCMW),one dimension maximum diameter of whole nodule with lung window setting (1D-WNLW), two dimension maximum diameter of whole nodule with lung window setting (2D-WNLW), and volume of solid component with threshold of-300 HU (SCT) of all SSNs.Results 1D-SCLW, 2D-SCLW,1D-SCMW,2D-SCMW,1D-WNLW,2D-WNLW and SCT of the group B were significantly larger than those of the group A(P=0.000).ROC analyses indicated that the diagnostic efficiency of SCT for the pathologic grade was the highest among 7 CT features(AUC=0.887, sensitivity:81%,specificity:93%);The cut-off values of 1D-SCLW,2D-SCLW,1D-SCMW,2D-SCMW,1D-WNLW, 2D-WNLW and SCT were 17.50 mm,14.75 mm,9.50 mm,7.75 mm,0.50 mm,1.25 mm and 139.00 mm3.Multiple Logistic regression analysis revealed that SCT was the independent predictor of pathologic grade(OR=4.978,95%CI=1.430-17.331,P=0.012).SCT of 139.00 mm3 or greater was a significant indicator of IAC.Conclusion Among the whole nodule size and solid component size of SSN in three different dimensions on preoperative HRCT, SCT is found to be the independent predictor of pathologic grade, which may provide reference for surgery.

Predictive value of whole nodule size and solid component size of pulmonary subsolid nodule with different window setting for the pathologic grade / 中华放射学杂志

Objective To investigate the predictive value of whole nodule size and solid component size of pulmonary subsolid nodules (SSNs)with different window setting on preoperative HRCT for pathologic grade in lung adenocarcinoma.Methods We retrospectively evaluated preoperative chest HRCT and pathological data of 125 patients with 127 surgically resected lung adenocarcinoma manifesting as SSNs.All specimens were divided into two groups:a total of 69 SSNs in group A,including 22 adenocarcinomas in situ (AIS) and 47 minimally invasive adenocarcinoma (MIA);a total of 58 SSNs in group B,including invasive adenocarcinoma (IAC).Observer 1 used computer aided diagnosis software to measure the volume of whole nodule with lung window setting (WNLW),volume of solid component with lung window setting (SCLW),volume of solid component with mediastinal window setting (SCMW) and volume of solid component with threshold of-300 HU(SCT) of all SSNs.Observer 2 randomly selected 50 SSNs and repeated all the measurements.The interobserver agreement regarding quantitative measurements were evaluated by using intraclass correlation coefficient(ICC).The differences of all quantitative features between two groups were evaluated by Mann-Whitney U test.All the quantitative features were evaluated by using univariate logistic regression analysis,significant quantitative features identified by univariate logistic regression analysis were included in the multivariate logistic regression and independent predictors of pathological grade were obtained.Receiver operating characteristic analysis was conducted for the independent predictive factors that exhibited statistically significant differences in the multivariate logistic regression.Results The interobserver agreement regarding quantitative features were excellent (ICC＞ 0.75).The WNLW,SCLW,SCMW and SCT of group B were significantly larger than those of group A (P＜ 0.001).The univariate logistic regression analysis indicated that WNLW,SCLW,SCMW and SCT were significant (P＜0.001),the multivariate logistic regression analysis indicated that SCT was the independent predictive factor (OR=1.013,95％CI:1.006—1.020,P＜0.001).When SCT larger than 139.00 mm3,SSN was significantly associated with IACs (AUC=0.887,sensitivity=81％,specificity=93％).Conclusion SCT of SSNs on preoperative HRCT can be used to distinguish between AIS-MIA and IAC,which may provide information for choice of operation.

Bone suppression images improve radiologists'performance on detection of lung nodules on chest radiographs / 实用放射学杂志

Objective To evaluate the performance of bone suppression images on the detection of lung nodules in comparison with the radiologists'reading results.Methods There were 141 standard posteroanterior digital chest radiographs,which included 95 patients with a solitary nodule and 46 controls.In this observational study,4 observers,including 2 radiologists and 2 residents,in-dicated their confidence level regarding the presence of a nodule for each lung,first by use of standard images,then with the addition of bone suppression images.Receiver operating characteristic (ROC)curve analysis was used to evaluate the observers'performance. Results Average nodule size was (1.9±1)cm (range from 0.9 cm to 2.9 cm).The mean value of the area under the ROC curve (AUC)was significantly improved from 0.844 with use of standard images alone to 0.873 with use of bone suppression images (P<0.01).Conclusion The use of bone suppression images can improve radiologists'performance on detection of lung nodules on chest radiographs.

Multi-slice CT features and pathological correlation of peripheral lung cancer associated with thin-walled airspace / 中华放射学杂志

Objective To evaluate multi-slice CT (MSCT) features and pathological basis of lung cancer containing thin-walled airspace. Methods Thirty?five cases of pathologically confirmed lung cancer containing thin-walled airspace were retrospectively analysed with regard to clinical data, pathological types and MSCT features between 2012 and 2015.There were 35 cases(25 adenocarcinoma, 9 squamous carcinoma, 1 spindle cell tumor) in total. MSCT features were compared between the lesions with or without solid component .Fisher exact test was used for the statistical analysis. For dynamic follow-up CT scans, the lesion dynamic change was evaluated .Correlations between the pathological section and CT images of the 11 cases were analysed. Results These features accounted for more than 60% of all MSCT signs in 35 cases, including round shape in 28 cases(80.0%),lobulation in 32 cases(91.4%),multiple cysts in 27 cases(77.1%), irregular inner wall in 33 cases(94.3%)and septum in airspace in 31 cases(88.6%). Shape, spiculation, bronchus cut-off, blood vessel and bronchus passing through the airspace, and ground-glass opacity were significantly different between the lesions with or without solid component(P<0.05).The frequency of spiculation(11 cases) and bronchus cut-off(12 cases) in mixed solid lesions was higher than that in lesions without solid component(1 case, respectively).The frequency of irregular shape(6 cases),blood vessel passing through the airspace(12 cases),ground-glass opacity(13 cases)and bronchus passing through the airspace(7 cases) in lesions without solid were higher than that in solid mixed lesions(1, 1, 5, 3 cases respectively).The pathological basis of the formation of thin-walled airspace was obvious central necrosis in solid lesions and emphysematous change due to the tumor cells diffused along the inner airspace wall and the alveolar wall destruction.Five lesions were with progressive wall thickening and increased size of the airspace,and two lesions were with decreased size of the airspace and enlarged nodules in followed CT.One case of lung cancer with thin-walled airspace evolved from ground glass nodule. Conclusions The CT manifestation of lung cancer containing thin-walled airspace was characteristic.The pathological basis of the thin-walled airspace was various.

CT findings of abnormal bronchovascular bundle in peripheral small cell lung cancer / 实用放射学杂志

Objective To investigate CT findings of abnormal bronchovascular bundle in patients with peripheral small cell lung cancer (SCLC).Methods The CT findings of abnormal bronchovascular bundle in 78 peripheral SCLC patients confirmed by pathology were retrospectively reviewed.Abnormal bronchovascular bundle of peripheral SCLC was divided into three types:type Ⅰ (thickening of the bronchovascular bundle),type Ⅱ (string beads of bronchovascular bundle) and type Ⅲ (bronchial cast with bronchus cut-off).Results 41 of 78 patients had abnormal bronchovascular bundle,in which 26 cases were in type Ⅰ,10 in type Ⅱ,5 in type Ⅲ.Except for 1 case with no mediastinal lymph node metastasis among 41 cases with abnormal bronchovascular bundle,all other 40 cases had mediastinal lymph node metastasis.Conclusion The abnormal bronchovascular bundle could reflect the biologic character of SCLC.Abnormal bronchovascular bundle is associated with advanced patients.

Subtype discrimination of lung adenocarcinoma manifesting as ground glass nodule based on radiomics / 中华放射学杂志

Objective To develop and validate the radiomics nomogram on the discrimination of lung invasive adenocarcinoma from'non-invasive'lesion manifesting as ground glass nodule(GGN)and compare it with morphological features and quantitative imaging. Methods One hundred and sixty pathologically confirmed lung adenocarcinomas from November 2011 to December 2014 were included as primary cohort. Seventy-six lung adenocarcinomas from November 2014 to December 2015 were set as an independent validation cohort. Lasso regression analysis was used for feature selection and radiomics signature building. Radiomics score was calculated by the linear fusion of selected features. Multivariable logistic regression analysis was performed to develop models. The prediction performances were evaluated with ROC analysis and AUC,and the different prediction performance between different models and mean CT value were compared with Delong test. The generalization ability was evaluated with the leave-one-out cross-validation method. The performance of the nomogram was evaluated in terms of its calibration. The Hosmer-Lemeshow test was used to evaluate the significance between the predictive and observe values.Results Four hundred and eighty-five 3D features were extracted and reduced to 2 features as the most important discriminators to build the radiomics signatures. The individualized prediction model was developed with age, radiomics signature, spiculation and pleural indentation, which had the best discrimination performance(AUC=0.934)in comparison with other models and mean CT value(P<0.05)and showed better performance compared with the clinical model(AUC=0.743,P<0.001).The radiomics-based nomogram demonstrated good calibration in the primary and validation cohort, and showed improved differential diagnosis performance with an AUC of 0.956 in the independent validation cohort. Conclusion Individualized prediction model incorporating with age, radiomics signature, spiculation and pleural indentation, presenting with radiomics nomogram, could differentiate IAC from'non-invasive'lesion manifesting as GGN with the best performance in comparison with morphological features and quantitative imaging.

A preliminary investigation on pulmonary subsolid nodule detection using deep learning methods from chest X-rays / 中华放射学杂志

Objective To evaluate the effectiveness of deep learning methods to detect subsolid nodules from chest X-ray images.Methods The building,training,and testing of the deep learning model were performed using the research platform developed by Infervision,China.The training dataset consisted of 1 965 chest X-ray images, which contained 85 labeled subsolid nodules and 1 880 solid nodules. Eighty-five subsolid nodules were confirmed by corresponding CT exams. We labeled each X-ray image using the corresponding reconstructed coronal slice from the CT exam as the gold standard,and trained the deep learning model using alternate training.After the training,the model was tested on a different dataset containing 56 subsolid nodules,which were also confirmed by corresponding coronal slices from CT exams. The model results were compared with an experienced radiologist in terms of sensitivity,specificity,and test time. Results Out of the testing dataset that contained 56 subsolid nodules, the deep learning model marked 72 nodules,which consisted of 39 true positives(TP)and 33 false positives(FP).The model took 17 seconds.The human radiologist marked 39 nodules,with 31 TP and 8 FP.The radiologist took 50 minutes and 24 seconds. Conclusions Subsolid nodules are prone to mis-diagnosis by human radiologists. The proposed deep learning model was able to effectively identify subsolid nodules from X-ray images.

Preliminary application of quantitative assessment of emphysema using CT in subjective evaluation of normal population / 实用放射学杂志

Objective To explore the application value of quantitative assessment of emphysema using CT in CT subjective evaluation of normal population,and compare the quantitative parameters of emphysema among groups.Methods A total of 1 231 volunteers with negative results of subjective assessment in low dose CT screening were included in this study.The threshold of emphysema was set at -950 HU,and the total lung volume(TLV),total emphysema volume(TEV),emphysema index(EI)and 15th percentile lung density(PD15)were quantified.The presence of emphysema was defined by an EI higher than or equal to 5%.The volunteers were divided into different groups by gender and age,and the quantitative parameters were compared among different groups.Results A total of 102 cases of emphysema were detected in 1 231 volunteers,with a detection rate of 8.29%,with 76 male volunteers,accounting for 9.93%,and 26 female volunteers,accounting for 5.58%,respectively.There were statistically significant differences in TLV,TEV, EI and PD15 between genders and age groups,with TLV,TEV,EI higher and PD15 lower in male(P<0.001)and with TEV and EI higher in older than 60 years old group(P<0.001).Conclusion Quantitative assessment of emphysema using CT exhibites relatively high clinical value in CT subjective evaluation of normal population.There are statistically significant differences in the quantitative parameters of emphysema among different groups.

Low-radiation-dose CT:quantitative research for lung volume using iterative model reconstruction / 实用放射学杂志

Objective To investigate the impact of quantitative measurement for lung volume using iterative model reconstruction (IMR),hybrid iterative reconstruction (iDose4 )and filtered back projection (FBP),and to compare the image noise between different reconstruction methods.Methods 70 subjects were performed with low-dose chest CT scan (Philips Brilliance 256 iCT),and the original data were reconstructed with IMR (algorithm:Routine,SharpPlus,Soft Tissue,level:1 - 3 ),iDose4 and FBP respectively.We set less than -950 HU as emphysema threshold,calculated the total lung volume (TLV),total emphysema volume (TEV),emphysema index (EI)and objective image noise (OIN),and then compared the quantitative parameters and OIN between different groups.Results All parameters showed a significantly statistical difference (P =0.000)except TLV (P =1.000).The TEV and EI are significant higher in IMR-S group than in other groups.The OIN in IMR-S-L1 group was the highest,and the FBP group was the second-highest.OIN in iDose4 group was lower than that in IMR-S groups but higher than that in IMR-R and IMR-ST group.Conclusion SharpPlus algorithm of IMR will affect the quantitative measurement of lung volume under low-radiation-dose condition,and the OIN in IMR-S groups is obvious.Therefore SharpPlus algorithm is not recommended for quantitative analysis of lung volume.The Routine and Soft Tissue algorithm will not affect the quantitative measurement,and can distinctly reduce the OIN compared with idose4 and FBP.

Low-radiation-dose CT:quantitative research for lung volume using iterative model reconstruction / 实用放射学杂志

Objective To investigate the impact of quantitative measurement for lung volume using iterative model reconstruction (IMR),hybrid iterative reconstruction (iDose4 )and filtered back projection (FBP),and to compare the image noise between different reconstruction methods.Methods 70 subjects were performed with low-dose chest CT scan (Philips Brilliance 256 iCT),and the original data were reconstructed with IMR (algorithm:Routine,SharpPlus,Soft Tissue,level:1 - 3 ),iDose4 and FBP respectively.We set less than -950 HU as emphysema threshold,calculated the total lung volume (TLV),total emphysema volume (TEV),emphysema index (EI)and objective image noise (OIN),and then compared the quantitative parameters and OIN between different groups.Results All parameters showed a significantly statistical difference (P =0.000)except TLV (P =1.000).The TEV and EI are significant higher in IMR-S group than in other groups.The OIN in IMR-S-L1 group was the highest,and the FBP group was the second-highest.OIN in iDose4 group was lower than that in IMR-S groups but higher than that in IMR-R and IMR-ST group.Conclusion SharpPlus algorithm of IMR will affect the quantitative measurement of lung volume under low-radiation-dose condition,and the OIN in IMR-S groups is obvious.Therefore SharpPlus algorithm is not recommended for quantitative analysis of lung volume.The Routine and Soft Tissue algorithm will not affect the quantitative measurement,and can distinctly reduce the OIN compared with idose4 and FBP.

Morphological and volumetric quantitative assessment of smokers by pulmonary MDCT scan and the correlation with pulmonary function / 实用放射学杂志

Objective To analyze the morphological features of smokers' lung on MDCT scan,measure the CT volumetric parameters,and explore the correlation with pulmonary functional test(PFT) indexes.Methods 59 smokers were enrolled,in which 14 were chronic obstructive pulmonary disease(COPD) patients,and 39 non-smokers were chosen as control group.All subjects underwent inspiratory and expiratory phase MDCT scan and PFT.Eleven pulmonary CT features caused by smoking among three groups were analyzed and compared.The emphysema index (EI 95) and mean lung density (MLD) were measured.The correlation between above mentioned parameters and PFT indexes were analyzed.Results ①Among three groups,significant differences were found for the score and incidence of entrilobular emphysema,paraseptal emphysema and brochiectasis or bronchial wall thickness(P＜0.01).②In COPD patients,paraseptal emphysema and DLCO/VA,brochiectasis or bronchial wall thickness and DLCO SB(％P),DLCO/VA(％P),as well as EI and MEF25％ (％P),DLCO SB(％P),DLCO/VA (％P)were negatively related.In smokers without COPD,there were negative correlation between centrilobular emphysema and FEV1/FVC,MEF25％ (％ P),MEF5％ (％ P),DLCO SB (％ P),DLCO/VA (％ P),paraseptal emphysema and DLCO SB(％P),DLCO/VA(％P),brochiectasis or bronchial wall thickness and DLCO/VA(％P),as well as EI and FEV1/FVC,MEF5％ (％P),and MLD and FEV1 (％ P),MEF25％ (％ P)were positively related.Conclusion MDCT can be used to analyze smokers' pulmonary morphology,and the morphological features and volumetric parameters are good predictions for pulmonary function.