Park JW, et al. Korean J Radiol. 2021 Jan;22(1):139-154. https://doi.org/10.3348/kjr.2019.0897

Purpose: To investigate the utility of preoperative multiparametric magnetic resonance imaging (mpMRI)-based clinical-radiomic analysis combined with machine learning (ML) algorithms in predicting the expression of the Ki-67 proliferative index and p53 tumor suppressor protein in patients with meningioma.Methods: This multicenter retrospective study included 483 and 93 patients from two centers. The Ki-67 index was classified into high (Ki-67≥5%) and low (Ki-67<5%)-expressed groups, and the p53 index was classified into positive (p53≥5%) and negative (p53<5%)-expressed groups. Clinical and radiological features were analyzed using univariate and multivariate statistical analyses. Six ML models were performed with different types of classifiers to predict Ki-67 and p53 status.Results: In the multivariate analysis, larger tumor volumes (p<0.001), irregular tumor margin (p<0.001), and unclear tumor-brain interface (p<0.001) were independently associated with a high Ki-67 status, whereas the presence of both necrosis (p=0.003) and the dural tail sign (p=0.026) were independently associated with a positive p53 status. A relatively better performance was yielded from the model constructed by combined clinical and radiological features. The area under the curve (AUC) and accuracy of high Ki-67 were 0.820 and 0.867 in the internal test, and 0.666 and 0.773 in the external test, respectively. Regarding p53 positivity, the AUC and accuracy were 0.858 and 0.857 in the internal test, and 0.684 and 0.718 in the external test.Conclusion: The present study developed clinical-radiomic ML models to non-invasively predict Ki-67 and p53 expression in meningioma using mpMRI features, and provides a novel non-invasive strategy for assessing cell proliferation.

Aging process is associated with gradual change of liver function and structure. The goal of this study was to evaluate age-related hemodynamic changes in the portal vein (PV) using four-dimensional (4D) flow MRI in healthy adults. A total of 120 healthy subjects were enrolled and categorized into groups A (n = 25, 30–39 years), B (n = 31, 40–49 years), C (n = 34, 50–59 years), and D (n = 30, 60–69 years). All subjects underwent 4D flow data acquisition using a 3-T MRI system to measure the hemodynamic parameters in the main PV. The clinical characteristics and 4D flow parameters were compared among the groups using analysis of variance and analysis of covariance after controlling for significant covariates, accordingly. The outcome metric applying the age-related quadratic model to estimate the age at which 4D flow parameters are the highest (the peak age) as well as the rates of age-related 4D flow changes was estimated. The average area, average through-plane velocity, peak velocity magnitude, average net flow, peak flow, and net forward volume in group D were significantly lower than those in groups A, B and C (P < 0.05). Group C showed significantly lower values of the average through-plane velocity and peak velocity magnitude than those of group B (P < 0.05). The peak age computed was approximately 43–44 years of age for all 4D flow parameters. The rates of age-related 4D flow changes for all 4D flow parameters were negatively correlated with age (P < 0.05). The volume and velocity of the blood flow through the PV peaked at approximately 43–44 years of age and decreased significantly after 60 years of age.

Liver cirrhosis (LC) can develop hepatocellular carcinoma (HCC). However, noninvasive early diagnosis of HCCs in the cirrhotic liver is still challenging. We aimed to quantify the hepatic metabolites in normal control (NC), cirrhotic liver without HCC, cirrhotic liver with HCC (CLH), and early-stage HCC groups using proton magnetic resonance spectroscopy (¹H-MRS) with a long echo-time (TE) and to assess the potential association between the levels of hepatic metabolites in these four groups and aging and enzymatic activity. Thirty NCs, 30 viral hepatitis-induced LC patients without HCC, and 30 viral hepatitis-induced LC patients with HCC were included in this study. ¹H-MRS measurements were performed on a localized voxel of the normal liver parenchyma (n = 30) from NCs, cirrhotic liver parenchyma (n = 30) from LC patients without HCC, and each of the cirrhotic liver parenchyma (n = 30) and HCC (n = 30) from the same patients in the CLH group. Generalized estimating equations were used to evaluate potential risk factors for changes in metabolite levels. Potential associations between metabolite levels and age and serum enzymatic activities were assessed by correlation analysis. The levels of lactate+triglyceride (Lac+TG) and choline (Cho) in HCC were significantly higher compared to those in LC and CLH. A potential risk factor for changes in the Lac+TG and Cho levels was age, specifically 60–80 years of age. In particular, the Lac+TG level was associated with a high odds ratio of HCC in males aged 60–80 years. The Lac+TG and Cho concentrations were positively correlated with lactate dehydrogenase and alkaline phosphatase activities, respectively. Our findings suggested that ¹H-MRS measurement with a long TE was useful in quantifying hepatic Lac+TG and Cho levels, where higher Lac+TG and Cho levels were most likely associated with HCC-related metabolism in the viral hepatitis-induced cirrhotic liver. Further, the level of Lac+TG in HCC was highly correlated with older age and lactate dehydrogenase activity.