Purpose To investigate the feasibility of multi-sequence MRI-based radiomics for predicting epidermal growth factor receptor(EGFR)mutation status in brain metastases from non-small cell lung cancer(NSCLC).Materials and Methods This retrospective study included 237 patients with NSCLC brain metastases from the Second Xiangya Hospital of Central South University(January 1,2017 to December 31,2023)who underwent EGFR genetic testing.All patients underwent pretreatment brain MRI including contrast-enhanced T1-weighted,T2-weighted FLAIR,and T2-weighted sequences,along with chest CT for primary lung lesions.EGFR mutations were identified in 120 patients.Using December 31,2021 as the cutoff date,patients were divided into training(n=146)and validation(n=91)cohorts.Senior radiologists delineated brain metastases on multi-sequence MRI and primary lesions on CT.A total of 851 radiomic features were extracted using PyRadiomics.Following feature selection,machine learning models were constructed using support vector machine algorithm and compared with least absolute shrinkage and selection operator-derived radiomic signatures.Five models were developed:three single-sequence MRI models,a multi-sequence MRI fusion model,and a CT model,with diagnostic performance evaluated by area under the receiver operating characteristic curve.Results The multi-sequence MRI fusion model demonstrated superior performance across all imaging types.The least absolute shrinkage and selection operator and support vector machine models achieved training set area under the curve of 0.854(95%CI 0.748-0.960)and 0.948(95%CI 0.923-0.973),respectively,and validation set area under the curve of 0.810(95%CI 0.751-0.869)and 0.951(95%CI 0.917-0.985),respectively.The optimal prediction model utilized support vector machine algorithm with multi-sequence MRI features.Conclusion Pretreatment multi-sequence MRI radiomics combined with machine learning accurately predicts EGFR mutation status in NSCLC patients with brain metastases.

Purpose To investigate the feasibility of multi-sequence MRI-based radiomics for predicting epidermal growth factor receptor(EGFR)mutation status in brain metastases from non-small cell lung cancer(NSCLC).Materials and Methods This retrospective study included 237 patients with NSCLC brain metastases from the Second Xiangya Hospital of Central South University(January 1,2017 to December 31,2023)who underwent EGFR genetic testing.All patients underwent pretreatment brain MRI including contrast-enhanced T1-weighted,T2-weighted FLAIR,and T2-weighted sequences,along with chest CT for primary lung lesions.EGFR mutations were identified in 120 patients.Using December 31,2021 as the cutoff date,patients were divided into training(n=146)and validation(n=91)cohorts.Senior radiologists delineated brain metastases on multi-sequence MRI and primary lesions on CT.A total of 851 radiomic features were extracted using PyRadiomics.Following feature selection,machine learning models were constructed using support vector machine algorithm and compared with least absolute shrinkage and selection operator-derived radiomic signatures.Five models were developed:three single-sequence MRI models,a multi-sequence MRI fusion model,and a CT model,with diagnostic performance evaluated by area under the receiver operating characteristic curve.Results The multi-sequence MRI fusion model demonstrated superior performance across all imaging types.The least absolute shrinkage and selection operator and support vector machine models achieved training set area under the curve of 0.854(95%CI 0.748-0.960)and 0.948(95%CI 0.923-0.973),respectively,and validation set area under the curve of 0.810(95%CI 0.751-0.869)and 0.951(95%CI 0.917-0.985),respectively.The optimal prediction model utilized support vector machine algorithm with multi-sequence MRI features.Conclusion Pretreatment multi-sequence MRI radiomics combined with machine learning accurately predicts EGFR mutation status in NSCLC patients with brain metastases.

Objective:To analyze the distribution and drug sensitivity of pathogens and cerebrospinal fluid (CSF) related measurements in AIDS patients with central nervous system (CNS) infections in Chongqing, so as to provide guidance for etiological diagnosis and rational use of antibiotics in AIDS patients with CNS infections.Methods:A total of 173 AIDS patients with CNS infections were divided into fungal group, Gram-positive bacilli group, Gram-positive cocci group and Gram-negative bacilli group. During the same period, 198 AIDS patients with non-CNS infection visited this hospital were enrolled into the control group. CSF and blood were collected for bacterial culture. The composition and drug resistance of pathogens were analyzed. The levels of CSF related measurements were determined and compared.Results:A total of 173 strains of pathogens were isolated from the CSF of the AIDS patients with CNS infections. The 173 strains included 101 (58.38%) fungi, 39 (22.54%) Gram-positive bacilli, 24 (13.87%) Gram positive cocci and 9 (5.20%) Gram-negative bacilli; 230 strains of pathogens were isolated from the blood of the AIDS patients with non CNS infections. The 198 strains were composed of 107(54.04%) fungi, 65 (32.83%) Gram positive cocci and 26 (13.13%) Gram-negative bacilli. Antifungal sensitivity testing result of Cryptococcus neoformans showed that MIC of amphotericin B, fluorocytosine, fluconazole, voriconazole and itraconazole were≤4, ≤32, ≤8, ≤1 and ≤1 μg/ml. The resistance rate of Mycobacterium tuberculosis to rifampicin was 7.69%. The result of drug sensitivity of coagulase negative staphylococci isolated from patients with CNS infections and non-CNS infections were consistent. There were significant differences among Staphylococcus aureus, Enterobacteriaceae and Acinetobacter. Compared with the control group, the levels of protein were higher and the levels of chloride and glucose were lower in fungal group, Gram-positive bacteria group, Gram-positive coccus group and Gram-negative bacteria group ( t=3.408-9.249, all P<0.011). The levels of protein, adenosine deaminase (ADA) and lactic dehydrogenase (LDH) in Gram-positive bacilli group were significantly higher than those in fungal group, Gram-positive coccus group, Gram-negative bacteria group and control group ( t=3.836-7.686, all P<0.037). Conclusions:The pathogens causing CNS and blood infections in AIDS patients were widely distributed, mainly dominated by fungus. The CSF related measurements varied with different pathogens, so as to assist in the etiological diagnosis of CNS infections.

Aged ; Coronary Artery Disease ; diagnosis ; Coronary Vessel Anomalies ; diagnosis ; Coronary Vessels ; pathology ; Humans ; Male