Transfer learning-based PET/CT three-dimensional convolutional neural network fusion of image and clinical information for prediction of EGFR mutation in lung adenocarcinoma.

BACKGROUND: To introduce a three-dimensional convolutional neural network (3D CNN) leveraging transfer learning for fusing PET/CT images and clinical data to predict EGFR mutation status in lung adenocarcinoma (LADC). METHODS: Retrospective data from 516 LADC patients, encompassing preoperative PET/CT images, clinical information, and EGFR mutation status, were divided into training (n = 404) and test sets (n = 112). Several deep learning models were developed utilizing transfer learning, involving CT-only and PET-only models. A dual-stream model fusing PET and CT and a three-stream transfer learning model (TS_TL) integrating clinical data were also developed. Image preprocessing includes semi-automatic segmentation, resampling, and image cropping. Considering the impact of class imbalance, the performance of the model was evaluated using ROC curves and AUC values. RESULTS: TS_TL model demonstrated promising performance in predicting the EGFR mutation status, with an AUC of 0.883 (95%CI = 0.849-0.917) in the training set and 0.730 (95%CI = 0.629-0.830) in the independent test set. Particularly in advanced LADC, the model achieved an AUC of 0.871 (95%CI = 0.823-0.919) in the training set and 0.760 (95%CI = 0.638-0.881) in the test set. The model identified distinct activation areas in solid or subsolid lesions associated with wild and mutant types. Additionally, the patterns captured by the model were significantly altered by effective tyrosine kinase inhibitors treatment, leading to notable changes in predicted mutation probabilities. CONCLUSION: PET/CT deep learning model can act as a tool for predicting EGFR mutation in LADC. Additionally, it offers clinicians insights for treatment decisions through evaluations both before and after treatment.

Predicting the negative conversion time of nonsevere COVID-19 patients using machine learning methods.

Based on the patient's clinical characteristics and laboratory indicators, different machine-learning methods were used to develop models for predicting the negative conversion time of nonsevere coronavirus disease 2019 (COVID-19) patients. A retrospective analysis was performed on 376 nonsevere COVID-19 patients admitted to Wuxi Fifth People's Hospital from May 2, 2022, to May 14, 2022. The patients were divided into training set (n = 309) and test set (n = 67). The clinical features and laboratory parameters of the patients were collected. In the training set, the least absolute shrinkage and selection operator (LASSO) was used to select predictive features and train six machine learning models: multiple linear regression (MLR), K-Nearest Neighbors Regression (KNNR), random forest regression (RFR), support vector machine regression (SVR), XGBoost regression (XGBR), and multilayer perceptron regression (MLPR). Seven best predictive features selected by LASSO included: age, gender, vaccination status, IgG, lymphocyte ratio, monocyte ratio, and lymphocyte count. The predictive performance of the models in the test set was MLPR > SVR > MLR > KNNR > XGBR > RFR, and MLPR had the strongest generalization performance, which is significantly better than SVR and MLR. In the MLPR model, vaccination status, IgG, lymphocyte count, and lymphocyte ratio were protective factors for negative conversion time; male gender, age, and monocyte ratio were risk factors. The top three features with the highest weights were vaccination status, gender, and IgG. Machine learning methods (especially MLPR) can effectively predict the negative conversion time of non-severe COVID-19 patients. It can help to rationally allocate limited medical resources and prevent disease transmission, especially during the Omicron pandemic.

Quantitative evaluation of acute myocardial infarction by feature-tracking cardiac magnetic resonance imaging.

Objective: To assess the value of feature-tracking cardiac magnetic resonance (FT-CMR) imaging in the quantitative evaluation of acute myocardial infarction (AMI). Methods: We retrospectively analyzed medical records of patients with acute myocardial infarction (AMI) diagnosed in the Department of Cardiology of Hubei No.3 People's Hospital of Jianghan University from April 2020 to April 2022, who underwent feature-tracking cardiac magnetic resonance (FT-CMR) examination. Based on the electrocardiogram (ECG) findings, patients were divided into ST-elevation myocardial infarction (STEMI) (n=52) and non-STEMI (NSTEMI) (n=48) groups. We compared myocardial strain parameters between the two groups and applied the Pearson's test to reveal any correlations between the left ventricular myocardial strain parameters and the number of late gadolinium enhancement (LGE) positive segments; we assessed the clinical value of FT-CMR for predicting STEMI using a receiver operating characteristic (ROC) curve. Results: The number of LGE-positive segments in the STEMI group was significantly higher than that in the NSTEMI group. The myocardial radial, circumferential and longitudinal strains in the STEMI group were significantly lower than those in the NSTEMI group (p<0.05). The number of LGE-positive segments in patients with AMI negatively correlated with the radial, circumferential and longitudinal strains. The results of the ROC curve analysis showed that radial, circumferential and longitudinal strain values have a diagnostic value for STEMI (p<0.05). Conclusion: FT-CMR, a non-invasive and rapid method for analyzing myocardial strains, has a high diagnostic value for AMI and should be helpful for the prevention and intervention of ventricular remodeling after myocardial infarctions.

A negative association between low-density lipoprotein cholesterol level and infection risk in elderly stage 5 chronic kidney disease patients.

BACKGROUND: To explore the relationship between low-density lipoprotein cholesterol (LDL-C) level and infection risk in elderly stage 5 kidney disease (CKD) patients. METHODS: This study retrospectively analyzed all 378 patients with grade 5 CKD over 60 years old treated in the Nephrology Department of our hospital from February 2014 to July 2019, including 286 cases with infection and 92 cases without. According to LDL-C levels, the patients were divided into three groups (Tertile 1-Tertile 3). Basic patient data and laboratory test results were collected for all three groups for analysis. RESULTS: The incidence of infection showed a gradually decreasing trend in the three groups (from 80.2, 78.6 to 68.3%), along with increasing LDL-C levels from Tertile 1 to Tertile 3, although the differences were not statistically significant (p = 0.075). After fully adjusting for confounding factors, the risk of infection was significantly reduced (OR = 0.646, 95% CI 0.420-0.993, p = 0.046) with increasing LDL-C levels. For the LDL-C levels of the three groups, the rising trend of LDL-C was significantly associated with the reduction in infection risk (OR = 0.545, 95% CI 0.317-0.937, p = 0.028). Curve fitting revealed that LDL-C levels were linearly negatively associated with the risk of infection, and the relationship between the two was not affected by the other factors (p for interaction: 0.567-1.000). CONCLUSIONS: LDL-C level is linearly negatively associated with the risk of infection in elderly patients with stage 5 CKD.

Association between squamous cell carcinoma antigen level and EGFR mutation status in Chinese lung adenocarcinoma patients.

BACKGROUND: To investigate the association between squamous cell carcinoma antigen (SCCAg) level and epidermal growth factor receptor (EGFR) mutation status in Chinese lung adenocarcinoma patients. METHODS: We retrospectively analyzed 293 patients with lung adenocarcinoma, divided into EGFR mutant group (n = 178) and EGFR wild-type group (n = 115). The general data and laboratory parameters of the two groups were compared. We used univariable and multivariable logistic regression to analyze the association between SCCAg level and EGFR mutation. Generalized additive model was used for curve fitting, and a hierarchical binary logistic regression model was used for interaction analysis. RESULTS: Squamous cell carcinoma antigen level in the EGFR wild-type group was significantly higher than that in the mutant group (p < 0.001). After adjusting for confounding factors, we found that elevated SCCAg was associated with a lower probability of EGFR mutation, with an OR of 0.717 (95% CI: 0.543-0.947, p = 0.019). For the tripartite SCCAg groups, the increasing trend of SCCAg was significantly associated with the decreasing probability of EGFR mutation (p for trend = 0.015), especially for Tertile 3 versus Tertile 1 (OR = 0.505; 95% CI: 0.258-0.986; p = 0.045). Curve fitting showed that there was an approximate linear negative relationship between continuous SCCAg and EGFR mutation probability (p = 0.020), which was first flattened and then decreased (p < 0.001). The association between the two was consistent among different subgroups, suggesting no interaction (all p > 0.05). CONCLUSION: There is a negative association between SCCAg level and EGFR mutation probability in Chinese lung adenocarcinoma patients.

Role of PET/CT in Management of Early Lung Adenocarcinoma.

OBJECTIVE. The purpose of this study was to explore the value of FDG PET combined with high-resolution CT (HRCT) in predicting the pathologic subtypes and growth patterns of early lung adenocarcinoma. MATERIALS AND METHODS. A retrospective analysis was conducted on the PET/CT data on ground-glass nodules (GGNs) resected from patients with stage IA lung adenocarcinoma. The efficacy of PET maximum standardized uptake value (SUVmax) combined with HRCT signs in prediction of histopathologic subtype and growth pattern of lung adeno-carcinoma was evaluated. RESULTS. SUVmax was significantly higher in GGNs with invasive HRCT signs. The diameter of GGN (odds ratio, 1.660; p = 0.000) and the difference in attenuation value (odds ratio, 1.012; p = 0.011) between ground-glass components and adjacent lung tissues were independent predictors of FDG uptake by GGNs. SUVmax was higher in invasive adenocarcinoma than in adenocarcinoma in situ (AIS)-minimally invasive adenocarcinoma (MIA) (median SUVmax, 2.0 vs 1.1; p = 0.008). An SUVmax of 2.0 was the optimal cutoff value for differentiating invasive adenocarcinoma from AIS-MIA. Acinar-papillary adenocarcinoma had a higher SUVmax than lepidic adenocarcinoma (median SUVmax, 2.1 vs 1.3; p = 0.037). An SUVmax of 1.4 was the optimal cutoff value for differentiating the growth pattern of adenocarcinoma. Use of PET/CT with HRCT significantly improved efficacy for differentiating invasive adeno-carcinoma from AIS-MIA. However, use of HRCT cannot significantly improve the diagnostic efficacy of FDG PET in the evaluation of tumors with different growth patterns. CONCLUSION. FDG PET can be used to predict the histopathologic subtypes and growth patterns of early lung adenocarcinoma. Combined with HRCT, it has value for predicting invasive histopathologic subtypes but no significance for predicting invasive growth patterns.

Hepatic steatosis is associated with abnormal hepatic enzymes, visceral adiposity, altered myocardial glucose uptake measured by 18F-FDG PET/CT.

BACKGROUND: Nonalcoholic fatty liver disease (NAFLD) is a multisystem disease that affects the liver and a variety of extra-hepatic organ systems. This study aimed to investigate the relationship between hepatic steatosis and glucose metabolism in liver and extra-hepatic tissues and organs. METHODS: The whole body 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET)/computed tomography (CT) images of 191 asymptomatic tumor screening patients were retrospectively analyzed. Patients with the ratio of spleen/liver CT densities > 1.1 were defined to have NAFLD, and their clinical symptoms, laboratory markers, FDG uptake in a variety of tissues and organs including heart, mediastinal blood pool, liver, spleen, pancreas, and skeletal muscle, as well as abdominal adipose tissue volumes including visceral adipose tissue (VAT) volume and subcutaneous adipose tissue (SAT) volume were compared with those of the non-NAFLD patients and used to analyze the independent correlation factors of NAFLD. RESULTS: Among the 191 patients, 33 (17.3%) were NAFLD, and 158 (82.7%) were non-NAFLD. There was no significant correlation between the mean standardized uptake value (SUVmean) and CT density of liver as well as the ratio of spleen/liver CT densities. Hepatic steatosis, but not FDG intake, was more significant in NAFLD patients with abnormal liver function than those with normal liver function. Compared with the non-NAFLD patients, NAFLD patients had significantly reduced myocardial glucose metabolism, but significantly increased mediastinal blood pool, spleen SUVmean and abdominal adipose tissue volumes (including VAT and SAT volumes) (P < 0.05). Multivariate regression analysis showed that elevated serum ALT, increased abdominal VAT volume, and decreased myocardial FDG uptake were independent correlation factors for NAFLD. Further studies showed that hepatic steatosis and myocardial FDG uptake were mildly linearly correlated (r = 0.366 with hepatic CT density and - 0.236 with the ratio of spleen/liver CT densities, P < 0.05). CONCLUSIONS: NAFLD is a systemic disease that can lead to the change of glucose metabolism in some extra-hepatic tissues and organs, especially the myocardium.

Application of a Prediction Model Based on the Laboratory Index Score in Prelabor Rupture of Membranes with Histologic Chorioamnionitis During Late Pregnancy.

BACKGROUND This study aimed to establish a prediction model based on the maternal laboratory index score (Lab-score) for histologic chorioamnionitis (HCA) in patients with prelabor rupture of membranes (PROM) during late pregnancy. MATERIAL AND METHODS Sixty-nine cases of pregnant women with PROM were retrospectively analyzed. The general information and laboratory indicators were compared between the HCA (n=22) and non-HCA (n=47) groups. A multivariate logistic regression method was used to establish the prediction model. We plotted the receiver operating characteristic curve and calculated the area under the curve (AUC). The clinical effectiveness of each model was compared by decision curve analysis. RESULTS Only C-reactive protein (CRP) in the laboratory index predicted HCA, but its diagnostic efficacy was not ideal (AUC=0.651). Then, we added CRP to the platelet/white blood cell count ratio and triglyceride level to construct the Lab-score. Based on the Lab-score, important clinical parameters, including body mass index, diastolic blood pressure, and preterm birth, were introduced to construct a complex joint prediction model. The AUC of this model was significantly larger than that of CRP (0.828 vs. 0.651, P=0.035), but not significantly different from that of Lab-score (0.828 vs. 0.724, P=0.120). Considering the purpose of HCA screening, the net benefit of the complex model was better than that of Lab-score and CRP. CONCLUSIONS The complex model based on Lab-score is useful in the clinical screening of high-risk populations with PROM and HCA during late pregnancy.

Lung Adenocarcinoma Manifesting as Ground-Glass Opacity Nodules 3 cm or Smaller: Evaluation With Combined High-Resolution CT and PET/CT Modality.

OBJECTIVE. The purpose of this study is to evaluate high-resolution CT (HRCT) combined with PET/CT for preoperative differentiation of invasive adenocarcinoma (IAC) from preinvasive lesions and minimally invasive adenocarcinoma (MIA) (the combination of which is hereafter referred to as preinvasive-MIA) in lung adenocarcinoma manifesting as ground-glass opacity nodules (GGNs) 3 cm or smaller. MATERIALS AND METHODS. We retrospectively analyzed the data of patients with lung adenocarcinoma with GGNs that were 3 cm or smaller between November 2011 and November 2018. The HRCT and PET/CT parameters for GGNs were compared to differentiate between IAC and preinvasive-MIA. Qualitative and quantitative parameters were analyzed using univariate and multivariate logistic regression models. The diagnostic performance of different parameters was compared using ROC curves and the McNemar test. RESULTS. The study enrolled 89 patients (24 men and 65 women) with lung adenocarcinoma who had a mean (± SD) age of 60.1 ± 8.1 years (range, 36-78 years). The proportions of mixed GGN type, polygonal or irregular shape, lobulated or spiculated edge, and dilated, distorted, or cutoff bronchial sign were higher for IAC GGNs than for preinvasive-MIA GGNs, and the attenuation value of the ground-glass opacity component on CT (CTGGO), maximum standardized uptake value, and the standardized uptake value (SUV) index (i.e., the ratio of the tumor maximum SUV to the liver mean SUV) for IAC GGNs were also higher (p = 0.001-0.022). Logistic regression analyses showed that the CTGGO and SUV index were independent predictors for IAC GGNs. The accuracy of CTGGO in combination with the SUV index for predicting IAC was 81.4% on a per-GGN basis and 85.4% on a per-patient basis. The combined HRCT and PET/CT modality had higher sensitivity and accuracy than did morphologic features, HRCT, and PET/CT measurement parameters alone (p < 0.001). CONCLUSION. The combined HRCT and PET/CT modality is an effective method to preoperatively identify IAC in lung adenocarcinoma manifesting as GGNs 3 cm or smaller.

Circulating microRNA-1 in the diagnosis and predicting prognosis of patients with chest pain: a prospective cohort study.

BACKGROUND: To investigate the early diagnostic and prognostic value of microRNA-1 in patients with acute chest pain. METHODS: This study enrolled 341 patients attacked by chest pain within 3 h, and another 100 volunteers as control group. Circulating microRNA-1 was collected and determined by real-time quantitative reverse transcription-polymerase chain reaction. The clinical follow-up period was 720 days. RESULTS: There were 174 patients in acute myocardial infarction (AMI) group, 167 in non-AMI group. The relative expression of microRNA-1 was significantly increased within 3 h in AMI group, and it continued rising within 12 h, lower at 24 h than that 12 h in AMI group without reperfusion therapy. Otherwise, microRNA-1 concentration was markedly low at 12 h after primary percutaneous coronary intervention in AMI group. The 95% reference range of circulating microRNA-1 was 0.171-0.653. It was significantly available for microRNA-1 to early diagnose AMI with an optimal cutoff value of 2.215 and diagnostic accuracy could be improved when combined with cardiac troponin I. It was not statistically significant for microRNA-1 to forecast future AMI but might prognose mortality of 720 days in chest pain patients. In patients with chest pain, microRNA-1 concentration was high with major adverse cardiac events within 30 days, low with high overall survival within 720 days. CONCLUSIONS: Circulating microRNA-1 might diagnose early AMI and predict the prognosis of patients with chest pain.

Establishment of reference intervals for maternal blood and umbilical cord blood procalcitonin in healthy Chinese women in late pregnancy.

AIM: To establish reference intervals (RIs) for maternal blood and umbilical cord blood procalcitonin (PCT) in healthy Chinese women in late pregnancy. METHODS: One hundred and twenty-seven healthy Chinese women in late pregnancy, including 70 vaginal deliveries and 57 cesarean section deliveries, were retrospectively analyzed. These pregnant women gave birth to 58 male infants and 69 female infants. Another 127 age-matched healthy women who were not pregnant were enrolled as the control group. PCT levels in maternal blood, umbilical cord blood and control blood were determined using electrochemiluminescence immunoassay. The RIs of PCT were defined using an intermediate 95% interval. RESULTS: The RIs for maternal blood and umbilical cord blood PCT were 0.020-0.075 ng/mL and 0.020-0.159 ng/mL, respectively. The cord blood PCT level was not significantly different between different delivery methods (P > 0.05). In contrast, the umbilical cord blood PCT in female newborns was higher than that in male newborns (0.088 ± 0.046 ng/mL vs 0.072 ± 0.030 ng/mL, P < 0.05). CONCLUSION: Maternal blood and umbilical cord blood PCT of Chinese women in late pregnancy have different RIs, and umbilical cord blood PCT level is affected by the gender of newborns.

Summed thickening score by myocardial perfusion imaging: A risk factor of left ventricular remodeling in patients with myocardial infarction.

BACKGROUND: Left ventricular (LV) remodeling has adverse effects on the prognosis of patients with myocardial infarction (MI). The aim of this study is to identify the risk factors of LV remodeling in MI patients by radionuclide myocardial imaging. METHODS AND RESULTS: This retrospective study consisted of 92 patients who had a history of definite prior MI on ECG and underwent both resting gated single photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) and positron emission tomography (PET) myocardial metabolism imaging. LV remodeling was defined as > mean + 2SD of LV end-diastolic volume index (LVEDVi) in the normal database. LV enlargement, cardiac dysfunction, wall thickening abnormalities expressed as summed thickening score (STS) were more severe in the old MI patients as compared to those with subacute MI. STS (Odds ratio, 1.296; P = .004) and the proportion of segments with reduced wall thickening in segments with normal perfusion (Odds ratio, 1.110; P = .001) were identified as the independent factors of LV remodeling in subacute and old MI patients in the multivariate binary regression model. Total perfusion deficit (TPD), viable myocardium, scar, and the proportion of segments with reduced wall thickening in segments with decreased perfusion showed strong correlation with LV remodeling in the univariate regression model as well. CONCLUSIONS: LV remodeling in old MI patients is more extensive and severe than that in subacute MI patients. LV wall thickening abnormalities as expressed by STS and the proportion of segments with reduced wall thickening in segments with normal perfusion are the independent risk factors of LV remodeling in MI patients.

Two-step irradiance schedule versus single-dose cold compress for pain control during 5-aminolevulinic acid-based photodynamic therapy of condyloma acuminatum.

OBJECTIVE: The purpose of this study was to investigate the effect of two-step irradiance schedule in relieving pain during PDT of CA. METHODS: The study was a prospective, controlled trial of 141 CA patients who were randomly divided into Group A (two-step irradiance schedule) and Group B (single-dose cold compress). The numeric rating scales (NRS) of patients' pain were recorded at 5, 10, 15, and 20 minutes during each PDT. RESULTS: The efficacy of PDT and NRS scores of patients in the two groups were compared. There was no significant difference in gender, age, lesion site, and disease course between the two groups (P > 0.05). In addition, the cure rate of patients in the two groups was not significantly different (97.1% vs. 95.8%, χ2 = 0.000, P = 1.000). However, the NRS scores at different time points and number of PDT sessions were significantly different (F = 198.233 and 165.224, respectively, P < 0.05). The NRS scores of patients in Group A were significantly lower than those of patients in Group B (F = 82.762, P < 0.0001). Moreover, the NRS scores at different positions were significantly different (F = 28.286, P < 0.0001). The NRS scores of penis were significantly lower than those of the vulva and crissum (P < 0.05). CONCLUSIONS: Compared with single-dose cold compress, two-step irradiance schedule could more significantly reduce the patients' pain degree during treatment, especially for vulva and crissum. Lasers Surg. Med. 49:908-912, 2017. © 2017 Wiley Periodicals, Inc.

Prevalence of and Trends in Diabetes Among Veterans, United States, 2005-2014.

Diabetes is a highly prevalent chronic disease among US adults, and its prevalence among US veterans is even higher. This study aimed to examine the prevalence of and trends in diabetes in US veterans by using data from the US National Health and Nutrition Examination Survey from 2005 through 2014. The overall prevalence of diabetes and undiagnosed diabetes was 20.5% and 3.4%, respectively, and increased from 15.5% in 2005-2006 to 20.5% in 2013-2014 (P = .04). Effective prevention and intervention approaches are needed to lower diabetes prevalence among US veterans and ultimately improve their health status.

Efficacy comparison of transcatheter arterial embolization with gelatin sponge and polyvinyl alcohol particles for the management of cesarean scar pregnancy and follow-up study.

AIM: The aim of this study was to compare the therapeutic efficacy of transcatheter arterial embolization (TAE) with gelatin sponge (GS) and polyvinyl alcohol (PVA) particles for cesarean scar pregnancy (CSP). METHODS: A total of 35 patients with CSP, who were classified into either the GS group (n = 22) or the PVA group (n = 13), underwent TAE and postoperative ultrasound-guided curettage. Their hospital stay, first-scheme success rate, intra-curettage blood loss, serum ß-human chorionic gonadotropin (hCG) level, and other indicators were simultaneously recorded. During the follow-up period, time for the serum ß-hCG level to return to normal, time for the return of menstrual cycle, and menstrual blood volume were recorded. RESULTS: Compared with the GS group, patients in the PVA group: (i) were older; (ii) had greater number of abortions or curettages, and had longer times since last cesarean (P < 0.05); (iii) had similar hospital stay and first-scheme success rate (P > 0.05); (iv) had lower, but not significantly different, hemorrhage rate (7.7% vs 36.4%, P = 0.066); (v) had a significantly higher serum ß-hCG level at discharge and a smaller drop in serum ß-hCG level from admission to discharge (P < 0.05); (vi) had a similar time for the serum ß-hCG level to return to normal (P > 0.05); (vii) had a shorter time for the return of menstrual cycle (P = 0.012); and (viii) had a significantly higher incidence of abnormal menstrual blood volume reduction (50.0% vs 8.3%, P = 0.034). CONCLUSION: TAE with either GS or PVA particles for CSP treatment had relatively good efficacy. During the selection of the ideal embolic agent, the patient's age, hemorrhage risk, and requirement for protecting ovarian function and reserving fertility should be comprehensively considered.

The role of active brown adipose tissue (aBAT) in lipid metabolism in healthy Chinese adults.

BACKGROUND: The prevalence of dyslipidemia in China was increased over the last several years. Studies have shown that the activity of aBAT is related to the lipid metabolism. In this study, we analyzed blood lipid level in tumor-free healthy Chinese adults in order to determine the role of aBAT in lipid metabolism. METHODS: We retrospectively analyzed the factors that affect the blood lipid level in 717 tumor-free healthy adults who received blood lipid measurement and PET/CT scan by multivariate regression analysis. We also determined the role of aBAT on lipid profile by case-control study. RESULTS: (1) Our results showed that 411 (57.3 %) subjects had dyslipidemia. The prevalence of the subjects with hypercholesteremia, hypertriglyceridemia, low high-density lipoprotein cholesterol and high low-density lipoprotein cholesterol was 9.5 %, 44.4 %, 30.8 % and 1.4 %, respectively. Multivariate logistic regression analysis with dyslipidemia as the dependent variable showed that body mass index (BMI) and smoking are independent risk factors for dyslipidemia (OR > 1, P < 0.05), while the presence of aBAT is the independent protective factor for dyslipidemia (OR < 1, P < 0.05). (2) The incidence of aBAT was 1.81 %. Subjects with aBAT had significantly lower serum triglyceride and higher serum high-density lipoprotein cholesterol than the subjects without aBAT. The serum total cholesterol and low-density lipoprotein cholesterol were not significantly different between the subjects with aBAT and those without aBAT. CONCLUSIONS: Dyslipidemia is caused by multiple factors and the presence of aBAT is a protective factor for dyslipidemia in healthy Chinese adults.

Association Analysis of Maximum Standardized Uptake Values Based on 18F-FDG PET/CT and EGFR Mutation Status in Lung Adenocarcinoma.

(1) Background: To investigate the association between maximum standardized uptake value (SUVmax) based on 18F-FDG PET/CT and EGFR mutation status in lung adenocarcinoma. (2) Methods: A total of 366 patients were retrospectively collected and divided into the EGFR mutation group (n = 228) and EGFR wild-type group (n = 138) according to their EGFR mutation status. The two groups' general information and PET/CT imaging parameters were compared. A hierarchical binary logistic regression model was used to assess the interaction effect on the relationship between SUVmax and EGFR mutation in different subgroups. Univariate and multivariate logistic regression was used to analyze the association between SUVmax and EGFR mutation. After adjusting for confounding factors, a generalized additive model and smooth curve fitting were applied to address possible non-linearities. (3) Results: Smoking status significantly affected the relationship between SUVmax and EGFR mutation (p for interaction = 0.012), with an interaction effect. After adjusting for age, gender, nodule type, bronchial sign, and CEA grouping, in the smoking subgroup, curve fitting results showed that the relationship between SUVmax and EGFR mutation was approximately linear (df = 1.000, c2 = 3.897, p = 0.048); with the increase in SUVmax, the probability of EGFR mutation gradually decreased, and the OR value was 0.952 (95%CI: 0.908-0.999; p = 0.045). (4) Conclusions: Smoking status can affect the relationship between SUVmax and EGFR mutation status in lung adenocarcinoma, especially in the positive smoking history subgroup. Fully understanding the effect of smoking status will help to improve the accuracy of SUVmax in predicting EGFR mutations.

The predictive value of [18F]FDG PET/CT radiomics combined with clinical features for EGFR mutation status in different clinical staging of lung adenocarcinoma.

BACKGROUND: This study aims to construct radiomics models based on [18F]FDG PET/CT using multiple machine learning methods to predict the EGFR mutation status of lung adenocarcinoma and evaluate whether incorporating clinical parameters can improve the performance of radiomics models. METHODS: A total of 515 patients were retrospectively collected and divided into a training set (n = 404) and an independent testing set (n = 111) according to their examination time. After semi-automatic segmentation of PET/CT images, the radiomics features were extracted, and the best feature sets of CT, PET, and PET/CT modalities were screened out. Nine radiomics models were constructed using logistic regression (LR), random forest (RF), and support vector machine (SVM) methods. According to the performance in the testing set, the best model of the three modalities was kept, and its radiomics score (Rad-score) was calculated. Furthermore, combined with the valuable clinical parameters (gender, smoking history, nodule type, CEA, SCC-Ag), a joint radiomics model was built. RESULTS: Compared with LR and SVM, the RF Rad-score showed the best performance among the three radiomics models of CT, PET, and PET/CT (training and testing sets AUC: 0.688, 0.666, and 0.698 vs. 0.726, 0.678, and 0.704). Among the three joint models, the PET/CT joint model performed the best (training and testing sets AUC: 0.760 vs. 0.730). The further stratified analysis found that CT_RF had the best prediction effect for stage I-II lesions (training set and testing set AUC: 0.791 vs. 0.797), while PET/CT joint model had the best prediction effect for stage III-IV lesions (training and testing sets AUC: 0.722 vs. 0.723). CONCLUSIONS: Combining with clinical parameters can improve the predictive performance of PET/CT radiomics model, especially for patients with advanced lung adenocarcinoma.

New research progress on 18F-FDG PET/CT radiomics for EGFR mutation prediction in lung adenocarcinoma: a review.

Lung cancer, the most frequently diagnosed cancer worldwide, is the leading cause of cancer-associated deaths. In recent years, significant progress has been achieved in basic and clinical research concerning the epidermal growth factor receptor (EGFR), and the treatment of lung adenocarcinoma has also entered a new era of individualized, targeted therapies. However, the detection of lung adenocarcinoma is usually invasive. 18F-FDG PET/CT can be used as a noninvasive molecular imaging approach, and radiomics can acquire high-throughput data from standard images. These methods play an increasingly prominent role in diagnosing and treating cancers. Herein, we reviewed the progress in applying 18F-FDG PET/CT and radiomics in lung adenocarcinoma clinical research and how these data are analyzed via traditional statistics, machine learning, and deep learning to predict EGFR mutation status, all of which achieved satisfactory results. Traditional statistics extract features effectively, machine learning achieves higher accuracy with complex algorithms, and deep learning obtains significant results through end-to-end methods. Future research should combine these methods to achieve more accurate predictions, providing reliable evidence for the precision treatment of lung adenocarcinoma. At the same time, facing challenges such as data insufficiency and high algorithm complexity, future researchers must continuously explore and optimize to better apply to clinical practice.

18F-FDG PET-CT for the prediction of mortality in patients with dermatomyositis and without malignant tumors: a pilot study.

Background: 18F-fluorodeoxyglucose positron emission tomography-computed tomography (18F-FDG PET-CT) is typically used to screen malignancy in patients with dermatomyositis (DM). The aim of this study was to investigate the value of using PET-CT in assessing the prognosis of patients with DM and without malignant tumors. Methods: A total of 62 patients with DM who underwent 18F-FDG PET-CT were enrolled in the retrospective cohort study. Clinical data and laboratory indicators were obtained. The muscle max standardized uptake value (SUVmax), splenic SUVmax, target-to-background ratio (TBR) of the aorta, pulmonary highest value (hv)/SUVmax, epicardial fat volume (EFV), and coronary artery calcium (CAC) were measured using 18F-FDG PET-CT. The follow-up was conducted until March 2021, and the endpoint was death from any cause. Univariable and multivariable Cox regression analyses were used to analyze prognostic factors. The survival curves were produced with the Kaplan-Meier method. Results: The median duration of follow-up was 36 [interquartile range (IQR), 14-53] months. The survival rates were 85.2% and 73.4% for 1 and 5 years, respectively. A total of 13 (21.0%) patients died during a median follow-up of 7 (IQR, 4-15.5) months. Compared with the survival group, the death group had significantly higher levels of C-reactive protein [CRP; median (IQR), 4.2 (3.0, 6.0) vs. 6.30 (3.7, 22.8)], hypertension [7 (14.3%) vs. 6 (46.2%)], interstitial lung disease [ILD; 26 (53.1%) vs. 12 (92.3%)], positive anti-Ro52 antibody [19 (38.8%) vs. 10 (76.9%)], pulmonary FDG uptake [median (IQR), 1.8 (1.5, 2.9) vs. 3.5 (2.0, 5.8)], CAC [1 (2.0%) vs. 4 (30.8%)], and EFV [median (IQR), 74.1 (44.8, 92.1) vs. 106.5 (75.0, 128.5)] (all P values <0.001). Univariable and multivariable Cox analyses identified high pulmonary FDG uptake [hazard ratio (HR), 7.59; 95% confidence interval (CI), 2.08-27.76; P=0.002] and high EFV (HR, 5.86; 95% CI, 1.77-19.42; P=0.004) as independent risk factors for mortality. The survival rate was significantly lower in patients with the concurrent presence of high pulmonary FDG uptake and high EFV. Conclusions: Pulmonary FDG uptake and EFV detected with PET-CT were independent risk factors for death in patients with DM and without malignant tumors. Patients with the concurrent presence of high pulmonary FDG uptake and high EFV had a worse prognosis compared with patients with 1 or neither of these two risk factors. Early treatment should be applied in patients with concurrent presence of high pulmonary FDG uptake and high EFV to improve the survival rate.