Objective To establish an effective model for distinguishing glandular prodromal lesions(PGL)mixed with ground-glass nodules(mGGN)from minimally invasive adenocarcinoma(MIA)on CT based on artificial intelligence.Methods A retrospective analysis was conducted on the clinical and CT image data of 180 patients with lung adenocarcinoma confirmed by surgical pathology and with CT manifestations of mGGN in the First Affiliated Hospital of Wenzhou Medical University from January 2017 to June 2023,inclu-ding 66 patients with PGL and 114 patients with MIA.Patients were divided into the training set(n=144)and the test set(n=36)in an 8∶2 ratio using a completely random method.The quantitative parameters and radiomics features of the lesions in CT images were automatically extracted using artificial intelligence soft-ware(United Imaging Research Platform uRP).By incorporating the most obvious correlation features of omics through dimensionality reduction,five machine learning classifiers were established,including logistic regression(LR),support vector machine(SVM),Random forest(RF),Gaussian process(GP),and Decision Tree(DT).The classifier with the training set highest area under the curve(AUC)was selected as the best radiomics model,and output the result as radiomics score(Rad-score).The clinical information,CT morpho-logical characteristics and quantitative data of the two groups were included in the multivariate logistic regres-sion analysis to screen the independent influencing factors for effectively differentiating PGL and MIA,and a clinical model was established.Finally,a comprehensive prediction model was constructed based on Rad-score and clinical risk factors.The diagnostic performance of the three models was evaluated by using the AUC,sen-sitivity,specificity and accuracy of receiver operating characteristic(ROC)curve.Results Eleven radiomics features for distinguishing PGL from MIA were obtained through LASSO dimensionality reduction.Among the five machine learning classifiers,GP has the best diagnostic performance,with AUC of 0.865 in the train-ing set and 0.762 in the test set,respectively.Univariate and multivariate logistic regression analyses were used for clinical feature screening.The clinical model was constructed by using the average CT value,average long and short diameter,and solid partial long diameter of mGGN,and the AUCs of the training set and the test set were 0.870 and 0.794,respectively.The comprehensive prediction model demonstrated superior diag-nostic performance,with AUC,sensitivity,specificity,and accuracy in the training set being 0.948,81.1%,91.2%and 87.5%respectively,while 0.883,76.9%,91.3%and 86.1%respectively in the test set.Conclu-sion The comprehensive prediction model established based on the quantitative and omics feature analysis of pulmonary nodules by artificial intelligence can well distinguish mGGN mixed with PGL from MIA on CT,and can be used to guide clinical treatment decisions.

Objective To observe the value of machine learning model based on MR T2WI and diffusion weighted imaging(DWI)radiomics for predicting perineural invasion(PNI)of rectal cancer.Methods Totally 343 patients with rectal cancer were retrospectively collected and divided into training set(n=275,92 PNI[+]and 183 PNI[-])and test set(n=68,23 PNI[+]and 45 PNI[-])at the ratio of 8∶2.Univariate and multivariate logistic regression(LR)were used to analyze clinical data and screen the independent predictors of PNI in rectal cancer,so as to construct a clinical model.The best radiomics features were extracted and screened based on preoperative T2WI and DWI.Then extremely randomized trees,multilayer perceptron,light gradient boosting machine,extreme gradient boosting,support vector machine(SVM),LR,K-nearest neighbor and random forest algorithms were used to construct ML models,respectively,and the optimal ML model was selected to establish a clinical-radiomics ML model combined with clinical relevant independent predictors.The predictive efficacy and clinical value of each model were evaluated.Results Patients' age was the independent predictor of PNI of rectal cancer(OR=0.988,P＜0.001),and the area under the curve(AUC)of the clinical model constructed based on it was 0.435 and 0.458 in training and test sets,respectively.SVM model was the best one among 8 ML models,with AUC in training and test set of 0.887 and 0.854,respectively.The AUC of clinical-radiomics ML model in training and test sets was 0.887 and 0.860,respectively,not different with AUC of SVM model(both P＞0.05).Decision curve analysis showed that when the threshold value was 0.20-0.45,clinical net benefit of SVM model was higher than that of other models.Conclusion SVM model based on T2WI and DWI radiomics could effectively predict PNI of rectal cancer.

Objective To observe the value of machine learning model based on MR T2WI and diffusion weighted imaging(DWI)radiomics for predicting perineural invasion(PNI)of rectal cancer.Methods Totally 343 patients with rectal cancer were retrospectively collected and divided into training set(n=275,92 PNI[+]and 183 PNI[-])and test set(n=68,23 PNI[+]and 45 PNI[-])at the ratio of 8∶2.Univariate and multivariate logistic regression(LR)were used to analyze clinical data and screen the independent predictors of PNI in rectal cancer,so as to construct a clinical model.The best radiomics features were extracted and screened based on preoperative T2WI and DWI.Then extremely randomized trees,multilayer perceptron,light gradient boosting machine,extreme gradient boosting,support vector machine(SVM),LR,K-nearest neighbor and random forest algorithms were used to construct ML models,respectively,and the optimal ML model was selected to establish a clinical-radiomics ML model combined with clinical relevant independent predictors.The predictive efficacy and clinical value of each model were evaluated.Results Patients' age was the independent predictor of PNI of rectal cancer(OR=0.988,P＜0.001),and the area under the curve(AUC)of the clinical model constructed based on it was 0.435 and 0.458 in training and test sets,respectively.SVM model was the best one among 8 ML models,with AUC in training and test set of 0.887 and 0.854,respectively.The AUC of clinical-radiomics ML model in training and test sets was 0.887 and 0.860,respectively,not different with AUC of SVM model(both P＞0.05).Decision curve analysis showed that when the threshold value was 0.20-0.45,clinical net benefit of SVM model was higher than that of other models.Conclusion SVM model based on T2WI and DWI radiomics could effectively predict PNI of rectal cancer.

Microbial induced calcium carbonate precipitation (MICP) refers to the natural biological process of calcium carbonate precipitation induced by microbial metabolism in its surrounding environment. Based on the principles of MICP, microbial cement has been developed and has received widespread attention in the field of biology, civil engineering, and environment owing to the merits of environmental friendliness and economic competence. Urease and carbonic anhydrase are the key enzymes closely related to microbial cement. This review summarizes the genes, protein structures, regulatory mechanisms, engineering strains and mutual synergistic relationship of these two enzymes. The application of bioinformatics and synthetic biology is expected to develop biocement with a wide range of environmental adaptability and high performance, and will bring the MICP research to a new height.
Calcium Carbonate/metabolism* ; Chemical Precipitation ; Urease/metabolism*

Objective:To investigate the diagnostic performance of MRI Liver Imaging Reporting and Data System version 2018 in high-risk hepatocellular carcinoma (HCC) patients with intrahepatic parenchymal substantial lesions ≤3.0 cm.Methods:A retrospective analysis was conducted in hospitals between September 2014 to April 2020. 131 pathologically confirmed non-HCC cases with lesions ≤3.0 cm in diameter were randomly matched with 131 cases with lesions ≤3.0 cm in diameter and divided into benign (56 cases), other hepatic malignant tumor (OM, 75 cases), and HCC group (131 cases) in a 1:1 ratio. MRI features of the lesions were analyzed and classified according to LI-RADS v2018 criteria (tie-break rule was applied to lesions with both HCC and LR-M features). Taking the pathological results as the gold standard, the sensitivity and specificity of the LI-RADS v2018 classification criteria and the more stringent LR-5 criteria (with three main signs of HCC at the same time) were calculated for HCC, OM or benign lesions diagnosis. Mann -Whitney U test was used to compare the classification results. Results:The number of cases classified as LR-M, LR-1, LR-2, LR-3, LR-4, and LR-5 in HCC group after applying the tie-break rule were 14, 0, 0, 12, 28, and 77, respectively. There were 40, 0, 0, 4, 17, 14 and 8, 5, 1, 26, 13, 3 cases in benign and OM group, respectively. There were 41 (41/77), 4 (4/14) and 1 (1/3) lesion case in the HCC, OM and benign group, respectively, that met the more stringent LR-5 criteria. The sensitivity of LR-4 combined with LR-5 (LR-4/5) criteria, LR-5 criteria and more stringent LR-5 criteria for HCC diagnosis were 80.2% (105/131), 58.8% (77/131) and 31.3% (41/131), respectively, and the specificity were 64.1% (84/131), 87.0% (114/131) and 96.2% (126/131), respectively. The sensitivity and specificity of LR-M were 53.3% (40/75) and 88.2% (165/187), respectively. The sensitivity and specificity using LR-1 combined with LR-2 (LR-1/2) criteria for the diagnosis of benign liver lesions were 10.7% (6/56) and 100% (206/206), respectively.Conclusions:LR-1/2, LR-5, and LR-M criteria have high diagnostic specificity for intrahepatic lesions with a diameter of ≤3.0 cm. Lesions classified as LR-3 are more likely to be benign. The specificity of LR-4/5 criteria is low, while the more stringent LR-5 criteria has a high specificity for HCC diagnosis.

Objective:To investigate the feasibility of tube potential of 80 kV combined with personalized contrast agent protocol in carotid artery CT angiography (CTA).Methods:A total of 136 consecutive patients undergoing neck CTA were prospectively enrolled in this study. The patients were randomly divided into Groups A, B, C and D. Tube potential of 100 kV and 15 s contrast agent injection protocol was used for Group A (53 cases) as conventional group, while tube voltage of 80 kV and 10 s contrast agent injection protocol was used for Groups B, C and D as experimental groups, with the contrast agent dosages of 20, 25 and 30 ml used according to the body weights of ≤50 kg(Group B, 20 cases), 50-70 kg (Group C, 38 cases), and 70-90 kg (Group D, 25 cases), respectively. The subjective and objective evaluation results of image quality and the effective doses were compared among the four groups.Results:The effective doses in Groups B, C and D were 1.54±0.91, 1.89±1.08 and 2.14±1.27 mSv, respectively, significantly lower than that in Group A [(5.66±0.56) mSv] ( F=169.34, P<0.05). The image quality of four groups met the requirements of clinical diagnosis. No significant differences were found in subjective evaluation and diagnostic efficacy of the four groups ( P>0.05). The CT number of carotid artery, signal-to-noise ratio and contrast-to-noise ratio of the neck region were significantly lower in Groups B, C and D compared with Group A ( F=14.9, 12.94, 14.43, P<0.05). The CT numbers of target carotid vessel were all higher than 250 HU. Conclusions:The scanning protocol of low tube potential (80 kV) combined with 10 s contrast agent injection protocol could not only reduce the doses of radiation and contrast agent, but also preserve the diagnosis effect. Thus, this scanning protocol was feasible and valuable in clinical application.

Objective:To evaluate the value of the crescent sign for predicting the invasiveness of lung adenocarcinoma presenting as pure ground-glass nodule (pGGN).Methods:The clinical, pathological and imaging data of 316 patients (320 pGGNs) confirmed lung adenocarcinoma by surgery and pathology from July 2013 to June 2018 in the First Affiliated Hospital of Wenzhou Medical University were retrospectively analyzed. All pGGNs were divided into preinvasive group (148 pGGNs) and invasive group (172 pGGNs) according to histopathology. Logistic regression analysis was used to determine the risk factors for invasiveness of pGGN, and the ROC curve analysis was performed on each risk factor.Results:Crescent sign was found in 24 cases (16.2%) in the preinvasive group and 49 (28.5%) in the invasive group, and the difference between the two groups was statistically significant (χ2=6.804 ,P=0.009).There were statistically significant differences in patient′s age, lesion size, shape, lobulation sign, and vascular stretch sign between the two groups ( P<0.05). The ROC curve showed that with the lesion size 10.5 mm as the optimal cut off value, the sensitivity for differential diagnosis of preinvasive and invasive lesions was 65.7%, the specificity was 61.5%, and the area under the curve was 0.666. Logistic regression analysis showed that maximum diameter of the lesion ≥10.5 mm, irregular shape, crescent sign and vascular stretch were independent risk factors of invasiveness of pGGN, and the OR value (95%CI) were 3.192 (1.981-5.144), 3.672 (1.545-8.725), 1.972 (1.104-3.521), and 2.026 (1.087-3.777), respectively. A logistic model was established based on the above four independent risk factors, and the area under curve was 0.711 (95%CI 0.655-0.768). Conclusion:Crescent sign can effectively reflect the invasiveness of pGGN. Maximum diameter of the lesion ≥10.5 mm, irregular shape, crescent sign and vascular stretch sign are independent risk factors of invasiveness of pGGN.

Objective:To explore the feasibility of CT angiography (CTA) in investigating vascular dilatation of anterior choroidal artery (AChA) and posterior communicating artery (PComA) in patients with Moyamoya syndrome (MMS).Methods:From July 2017 to July 2018, the clinical and imaging data of MMS patients with brain CTA and DSA performed were analyzed retrospectively. According to DSA results, 71 MMS patients were divided into unilateral MMS group (20 cases, 20 hemispheres) and bilateral MMS group (51 cases, 102 hemispheres). There were 20 cases in unilateral MMS group, 10 males and 10 females, with an average age of (45±9) years; 51 cases in bilateral MMS group, 24 males and 27 females, with an average age of (44±12) years. The hemispheres were divided into dilated group and non-dilated group according to the dilatation of AChA or PComA. Kappa analysis was used to evaluate the consistency of two inspection methods to judge the expansion of AChA. The lumen diameters of PComA, P1 and P2 segments of posterior cerebral artery were measured on CTA images, and the ratio of PComA/P1 and PComA/P2 were calculated. The repeatability of CTA measures was evaluated by intra-group correlation coefficient. Independent sample t-test was used to compare CTA measurement results between PComA dilated group and non-dilated group, and ROC curve was drawn to calculate the best threshold for diagnosis of PComA expansion. The sensitivity, specificity, accuracy, positive predictive value and negative predictive value of CTA measures were calculated. Results:The sensitivity, specificity, accuracy, positive predictive value and negative predictive value of CTA diagnosis of AChA expansion inunilateral MMS were all 100.00%. The sensitivity, specificity, accuracy, positive predictive value and negative predictive value of CTA diagnosis of AChA expansionin bilateral MMS were 90.00%, 93.90%, 93.14%, 78.26% and 97.47%. Compared with DSA, there was no significant difference in the diagnostic performance of AChA expansion between single and bilateral MMS diagnosed by CTA ( P>0.05). The two methods had strong consistency (Kappa value was 1.00 and 0.79 respectively, P<0.01). A total of 46 patients (69 cerebral hemispheres) were included in the evaluation of PComA. PComA/P1 (1.09±0.41) and PComA/P2 (0.86±0.13) in the dilated group were significantly higher than those in the non-dilated group (0.71±0.21 for PComA/P1 and 0.75±0.23 for PComA/P2). The differences were statistically significant ( t=-4.59, -2.50, P<0.05). The best threshold in diagnosing PComA expansion was 0.87 (PComA/P1) and 0.76 (PComA/P2), and the sensitivity, specificity, accuracy, positive predictive value and negative predictive value were 84.62%, 83.33%, 84.06%, 86.84%, 80.65% and 79.49%, 60.00%, 71.01%, 72.09% and 69.23%, respectively. Compared with DSA, the Kappa value of CTA measures in diagnosis of PComA expansion was 0.68 (PComA/P1) and 0.40 (PComA/P2), respectively, and the difference was statistically significant ( P<0.05). Conclusions:CTA has a strong consistency with DSA in evaluating the AChA expansion in MMS. When the PComA/P1 ratio on CTA is greater than 0.87, it can be used as the diagnosis criterion for PComA expansion.

Objective To determine clinical features and rupture risk of anterior communicating artery (AComA) aneurysms in different age groups. Methods The clinical data of 519 consecutive patients with AComA aneurysms in the First Affiliated Hospital of Wenzhou Medical University between December 2007 and February 2015 were reviewed and divided into younger group (<65 years) and older group (≥65 years). The clinical characteristics and aneurysm morphologies were compared between the two groups. Results There were 390 aneurysms in younger group, and 129 in older groups. For the younger group, hypertension,the size of the aneurysms, maximum height, perpendicular height, size ratio (SR), aspect ratio (AR), aneurysm angle, A1 segment configuration, morphology showed significantly differences in ruptured aneurysms group compared with those in unruptured aneurysms (P<0.05). The multivariate analysis showed that significant difference between the two groups was aneurysm size ( OR＝1.461,95% CI 1.027-2.079, P＝0.035). For the older group, there were statistically significant differences in hypertension,size of the aneurysms, maximum height, perpendicular height, SR, aneurysm angle, vessel size and the distribution of aneurysm projection between the ruptured aneurysms group and unruptured aneurysms group (P<0.05). The multivariate analysis showed that SR ( OR＝11.516,95% CI 1.782-74.445,P＝0.01) was the only significant predictor of aneurysm rupture. Between the younger and older groups,the distributions of sex, hypertension, smoke, vessel size and SR were statistically significant (P < 0.05). Conclusions For younger people, the males who smoked are more likely to have AcomA aneurysms and the size of the aneurysms is independent risk of aneurysm rupture. For older people, the females with hypertension also more often have AcomA aneurysms and the SR is independently associated with aneurysm rupture.

Objective To evaluate the CT features of small lung invasive adenocarcinoma with air?containing space and its relationship with pathological types, and to explore the pathological basis of air?containing space. Methods CT and pathological data of fifty patients with surgically proven lung invasive adenocarcinoma with air?containing space in our hospital from January 2012 to December 2017 were retrospectively reviewed. CT image analysis included image features of tumor and air?containing space. Pathological analysis included pathological subtype, differentiation degree. CT features of tumor and air?containing space were compared with regard to pathological types using chi?square test or Fisher exact text. Analysis of variance was used to compare quantitative data satisfying normal distribution, while those data not satisfying normal distribution were compared with Kruskal?Wallis test. In addition, Spearman correlation was used to analyze the correlation between nodule density and pathological types. Results (1) CT features of tumors: Tumors were predominantly located in peripheral lungs (46/50). Most of the tumors were subsolid nodules (37/50). Tumor?lung interface was generally clear (46/50). Tumors are often accompanied by malignant signs such as lobulation (37/50), spicule sign (27/50), air bronchogram sign (43/50), and pleural indentation (36/50). The mean diameter of nodules ranged from 7.50 mm to 18.12 mm, with an average of (12.91±2.85)mm. The nodule density ranged from-657.00 to 73.00 HU with an average of (-213.88±206.16) HU. (2) CT features of air?containing space:Air?containing spaces were commonly solitary (37/50) and were found to be mainly in an eccentric distribution (29/37). The maximum diameter of air?containing space ranged from 1.00 to 16.00mm, and the average diameter was (4.23±3.14)mm. Air?containing spaces less than 5mm were found in 35 cases (70%), and air?containing spaces more than 5mm were found in 15 cases. (3) Comparison of CT features and corresponding pathological types: Nodule density, number of air?containing space, and type of nodule density in different pathological types were statistically different (P<0.05). There was a correlation between nodule density and pathological subtypes (r=0.371, P=0.008). Differences of nodule density, short?dimension of nodule, type of nodule density, spicule sign, pleural indentation among different tumor differentiation degrees were significant (P<0.05). The degree of tumor differentiation was negatively correlated with nodule density (r=-0.451, P=0.001). Conclusion The detection rate of air?containing space in lung invasive adenocarcinomas is 12.7%. Most small lung invasive adenocarcinomas with air?containing space are presented as peripheral subsolid nodule, and there is a certain correlation between their CT features and pathological types. The pathological basis of air?containing space was supposed to be dilated distal bronchiole induced by check?valve mechanism and destruction of alveolar structure by tumor.