Better efficacy in differentiating WHO grade II from III oligodendrogliomas with machine-learning than radiologist's reading from conventional T1 contrast-enhanced and fluid attenuated inversion recovery images.

BACKGROUND: The medical imaging to differentiate World Health Organization (WHO) grade II (ODG2) from III (ODG3) oligodendrogliomas still remains a challenge. We investigated whether combination of machine leaning with radiomics from conventional T1 contrast-enhanced (T1 CE) and fluid attenuated inversion recovery (FLAIR) magnetic resonance imaging (MRI) offered superior efficacy. METHODS: Thirty-six patients with histologically confirmed ODGs underwent T1 CE and 33 of them underwent FLAIR MR examination before any intervention from January 2015 to July 2017 were retrospectively recruited in the current study. The volume of interest (VOI) covering the whole tumor enhancement were manually drawn on the T1 CE and FLAIR slice by slice using ITK-SNAP and a total of 1072 features were extracted from the VOI using 3-D slicer software. Random forest (RF) algorithm was applied to differentiate ODG2 from ODG3 and the efficacy was tested with 5-fold cross validation. The diagnostic efficacy of radiomics-based machine learning and radiologist's assessment were also compared. RESULTS: Nineteen ODG2 and 17 ODG3 were included in this study and ODG3 tended to present with prominent necrosis and nodular/ring-like enhancement (P < 0.05). The AUC, ACC, sensitivity, and specificity of radiomics were 0.798, 0.735, 0.672, 0.789 for T1 CE, 0.774, 0.689, 0.700, 0.683 for FLAIR, as well as 0.861, 0.781, 0.778, 0.783 for the combination, respectively. The AUCs of radiologists 1, 2 and 3 were 0.700, 0.687, and 0.714, respectively. The efficacy of machine learning based on radiomics was superior to the radiologists' assessment. CONCLUSIONS: Machine-learning based on radiomics of T1 CE and FLAIR offered superior efficacy to that of radiologists in differentiating ODG2 from ODG3.

Fetal brain development at 25-39 weeks gestational age: A preliminary study using intravoxel incoherent motion diffusion-weighted imaging.

BACKGROUND: The fetal brain developmental changes of water diffusivity and perfusion has not been extensively explored. PURPOSE/HYPOTHESIS: To evaluate the fetal brain developmental changes of water diffusivity and perfusion using intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI). STUDY TYPE: Prospective. POPULATION: Seventy-nine normal singleton fetuses were scanned without sedation of healthy pregnant women. FIELD STRENGTH/SEQUENCE: 5 T MRI/T1 /2 -weighted image and IVIM-DWI. ASSESSMENT: Pure diffusion coefficient (D), pseudodiffusion coefficient (D*), and perfusion fraction (f) values were calculated in the frontal (FWM), temporal (TWM), parietal (PWM), and occipital white matter (OWM) as well as cerebellar hemisphere (CH), basal ganglia region (BGR), thalamus (TH), and pons using an IVIM model. STATISTICAL TESTS: One-way analysis of variable (ANOVA) followed by Bonferroni post-hoc multiple comparison was employed to reveal the difference of IVIM parameters among the investigated brain regions. The linear and the nonlinear polynomial regression analyses were utilized to reveal the correlation between gestational age (GA) and IVIM parameters. RESULTS: There were significant differences in both D (F(7,623) = 96.64, P = 0.000) and f values (F(7,623) = 2.361, P = 0.0219), but not D* values among the varied brain regions. D values from TWM (r2 = 0.1402, P = 0.0002), PWM (r2 = 0.2245, P = 0.0002), OWM (r2 = 0.2519, P = 0.0002), CH (r2 = 0.2245, P = 0.0002), BGR (r2 = 0.3393, P = 0.0001), TH (r2 = 0.1259, P = 0.0001), and D* value from pons (r2 = 0.2206, P = 0.0002) were significantly correlated with GA using linear regression analysis. Quadratic regression analysis led to results similar to those using the linear regression model. DATA CONCLUSION: IVIM-DWI parameters may indicate fetal brain developmental alterations but the conclusion is far from reached due to the not as high-powered correlation between IVIM parameters and GA. LEVEL OF EVIDENCE: 2 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2019;50:899-909.

[Effects of Microbial Fuel Cell Coupled Constructed Wetland with Different Support Matrix and Cathode Areas on the Degradation of Azo Dye and Electricity Production].

In this study, microbial fuel cell coupled constructed wetland (CW-MFC) was constructed for azo dye reactive brilliant red X-3B degradation and electricity production. The effects of support matrix and cathode areas on the degradation of X-3B and the electricity production of CW-MFC were investigated in this work to improve the performance of CW-MFC. The highest decolorization efficiency was 92.70% and was obtained when the CW-MFC was constructed with support matrix S3 with particle size of 10 mm and porosity of 30%. Small particle size increased the microbial biomass of the bottom layer of CW-MFC, which would promote the decolorization of X-3B in the bottom layer. However, it may cause the lack of nutrition in electrode layer and the increase in resistance of mass transfer, which would lead to the decline of electricity production. The decolorization efficiency and the power density of CW-MFC increased concomitantly with the increase of cathode areas, and the CW-MFC got the highest decolorization efficiency of 99.41% when the cathode area was 594 cm2. The electricity production performance became stable when the cathode area continued to increase, while the decolorization efficiency declined. This may be attributed to that more electrons were transferred to the cathode to produce current instead of used in degradation of X-3B.