Metabolite selection for machine learning in childhood brain tumour classification.

MRS can provide high accuracy in the diagnosis of childhood brain tumours when combined with machine learning. A feature selection method such as principal component analysis is commonly used to reduce the dimensionality of metabolite profiles prior to classification. However, an alternative approach of identifying the optimal set of metabolites has not been fully evaluated, possibly due to the challenges of defining this for a multi-class problem. This study aims to investigate metabolite selection from in vivo MRS for childhood brain tumour classification. Multi-site 1.5 T and 3 T cohorts of patients with a brain tumour and histological diagnosis of ependymoma, medulloblastoma and pilocytic astrocytoma were retrospectively evaluated. Dimensionality reduction was undertaken by selecting metabolite concentrations through multi-class receiver operating characteristics and compared with principal component analysis. Classification accuracy was determined through leave-one-out and k-fold cross-validation. Metabolites identified as crucial in tumour classification include myo-inositol (P < 0.05, AUC=0.81±0.01 ), total lipids and macromolecules at 0.9 ppm (P < 0.05, AUC=0.78±0.01 ) and total creatine (P < 0.05, AUC=0.77±0.01 ) for the 1.5 T cohort, and glycine (P < 0.05, AUC=0.79±0.01 ), total N-acetylaspartate (P < 0.05, AUC=0.79±0.01 ) and total choline (P < 0.05, AUC=0.75±0.01 ) for the 3 T cohort. Compared with the principal components, the selected metabolites were able to provide significantly improved discrimination between the tumours through most classifiers (P < 0.05). The highest balanced classification accuracy determined through leave-one-out cross-validation was 85% for 1.5 T 1 H-MRS through support vector machine and 75% for 3 T 1 H-MRS through linear discriminant analysis after oversampling the minority. The study suggests that a group of crucial metabolites helps to achieve better discrimination between childhood brain tumours.

Analysis of vehicular CO2 emission in the Central Plains of China and its driving forces.

The Central Plains of China, represented by Henan province, faces a dramatic rise in vehicular stock and CO2 emissions. The refined-resolution(1 km × 1 km) vehicular CO2 emission inventory for Henan province was developed to identify emission patterns. Results show that CO2 emissions in Henan province reached 77.04 Mt in 2019, and LDGV and HDDT were the major sources that emitted 42.34% and 35.96% of CO2 emissions, respectively. Based on gridded emission, Moran's Index was used to identify spatial distribution patterns of vehicular CO2. The higher CO2 emission intensity areas were concentrated in the central and northern of the province and urban areas in each city, especially in Zhengzhou and its surrounding cities. Moreover, the analysis of the driving forces behind the differences in emissions among cities using the multi-regional (M-R) spatial decomposition model revealed that income and population-scale are significant impacts. In cities such as Zhengzhou, emissions may be dramatically increase owing to high economic growth expectations. 'Polarization phenomenon' of CO2 emission distribution should be vigilant. Findings provided insights for refined policy-making in Henan province to limit CO2 emission: (1) Take cities as transportation hubs, e.g., Zhengzhou and Shangqiu, and that in the traffic radiation circle, e.g., Jiaozuo and Zhoukou, as the critical areas for CO2 emission reduction; (2) Promote electric vehicles as replacement for traditional fuel vehicles; especially for cities with large passenger car emissions, such as Zhengzhou, and cities with large truck emissions, such as Shangqiu and Zhoukou; actively guide new consumer groups to choose EVs, especially in cities with high growth expectations such as Zhengzhou; (3) Rely on the advantages of transportation network to promote the 'road to railway' of bulk cargo transportation and mainly focus on highways with higher CO2 density, such as Beijing-Hong Kong&Macao Expressway, Shanghai-Xi'an Expressway, Da Guang Expressway, and Lian Huo Expressway.

Multi-Slice Radiomic Analysis of Apparent Diffusion Coefficient Metrics Improves Evaluation of Brain Alterations in Neonates With Congenital Heart Diseases.

Apparent diffusion coefficients (ADC) can provide phenotypic information of brain lesions, which can aid the diagnosis of brain alterations in neonates with congenital heart diseases (CHDs). However, the corresponding clinical significance of quantitative descriptors of brain tissue remains to be elucidated. By using ADC metrics and texture features, this study aimed to investigate the diagnostic value of single-slice and multi-slice measurements for assessing brain alterations in neonates with CHDs. ADC images were acquired from 60 neonates with echocardiographically confirmed non-cyanotic CHDs and 22 healthy controls (HCs) treated at Children's Hospital of Nanjing Medical University from 2012 to 2016. ADC metrics and texture features for both single and multiple slices of the whole brain were extracted and analyzed to the gestational age. The diagnostic performance of ADC metrics for CHDs was evaluated by using analysis of covariance and receiver operating characteristic. For both the CHD and HC groups, ADC metrics were inversely correlated with the gestational age in single and multi-slice measurements (P < 0.05). Histogram metrics were significant for identifying CHDs (P < 0.05), while textural features were insignificant. Multi-slice ADC (P < 0.01) exhibited greater diagnostic performance for CHDs than single-slice ADC (P < 0.05). These findings indicate that radiomic analysis based on ADC metrics can objectively provide more quantitative information regarding brain development in neonates with CHDs. ADC metrics for the whole brain may be more clinically significant in identifying atypical brain development in these patients. Of note, these results suggest that multi-slice ADC can achieve better diagnostic performance for CHD than single-slice.

Small-world properties of the whole-brain functional networks in patients with obstructive sleep apnea-hypopnea syndrome.

OBJECTIVE: To explore the small-world properties of brain functional networks in patients with obstructive sleep apnea-hypopnea syndrome (OSAHS) to aid diagnosis. METHODS: A total of 29 OSAHS patients and 26 matched healthy volunteers were scanned with blood oxygen level-dependent functional magnetic resonance imaging (BOLD-fMRI) separately, and the whole brain was divided into 90 districts via automated anatomical labeling. The matrix Z was then built through a Fisher Z transformation. Two-sample t tests were applied to evaluate the changes in small-world properties in OSAHS patients compared to the control group. The properties included Eglobal, Elocal, and small-world parameters Lp, Cp, γ, λ, and σ. RESULTS: Both groups satisfied the small-world properties (σ > 1) within the sparsity range of 0.1-0.2. However, compared with the control group, the OSAHS group performed significantly lower in Cp, Elocal, and Eglobal (p < 0.05) and higher in Lp (p < 0.05). The γ, σ, and λ values were not significantly different between the two groups. CONCLUSION: Both healthy and OSAHS patients exhibited small-world properties in functional networks, but a subset of these small-world properties in OSAHS patients performed differently. These changes will not only provide a new perspective for pathophysiological mechanisms of OSAHS but will also help in understanding the disease in terms of whole-brain functional networks.