Radiomics Analysis of Quantitative Maps from Synthetic MRI for Predicting Grades and Molecular Subtypes of Diffuse Gliomas.

PURPOSE: To investigate the feasibility of using radiomics analysis of quantitative maps from synthetic MRI to preoperatively predict diffuse glioma grades, isocitrate dehydrogenase (IDH) subtypes, and 1p/19q codeletion status. METHODS: Data from 124 patients with diffuse glioma were used for analysis (n = 87 for training, n = 37 for testing). Quantitative T1, T2, and proton density (PD) maps were obtained using synthetic MRI. Enhancing tumour (ET), non-enhancing tumour and necrosis (NET), and peritumoral edema (PE) regions were segmented followed by manual fine-tuning. Features were extracted using PyRadiomics and then selected using Levene/T, BorutaShap and maximum relevance minimum redundancy algorithms. A support vector machine was adopted for classification. Receiver operating characteristic curve analysis and integrated discrimination improvement analysis were implemented to compare the performance of different radiomics models. RESULTS: Radiomics models constructed using features from multiple tumour subregions (ET + NET + PE) in the combined maps (T1 + T2 + PD) achieved the highest AUC in all three prediction tasks, among which the AUC for differentiating lower-grade and high-grade diffuse gliomas, predicting IDH mutation status and predicting 1p/19q codeletion status were 0.92, 0.95 and 0.86 respectively. Compared with those constructed on individual T1, T2, and PD maps, the discriminant ability of radiomics models constructed on the combined maps separately increased by 11, 17 and 10% in predicting glioma grades, 35, 52 and 19% in predicting IDH mutation status, and 16, 15 and 14% in predicting 1p/19q codeletion status (p < 0.05). CONCLUSION: Radiomics analysis of quantitative maps from synthetic MRI provides a new quantitative imaging tool for the preoperative prediction of grades and molecular subtypes in diffuse gliomas.

Noninvasive prediction of perineural invasion in intrahepatic cholangiocarcinoma by clinicoradiological features and computed tomography radiomics based on interpretable machine learning: a multicenter cohort study.

BACKGROUND: Perineural invasion (PNI) of intrahepatic cholangiocarcinoma (ICC) is a strong independent risk factor for tumour recurrence and long-term patient survival. However, there is a lack of noninvasive tools for accurately predicting the PNI status. The authors develop and validate a combined model incorporating radiomics signature and clinicoradiological features based on machine learning for predicting PNI in ICC, and used the Shapley Additive explanation (SHAP) to visualize the prediction process for clinical application. METHODS: This retrospective and prospective study included 243 patients with pathologically diagnosed ICC (training, n =136; external validation, n =81; prospective, n =26, respectively) who underwent preoperative contrast-enhanced computed tomography between January 2012 and May 2023 at three institutions (three tertiary referral centres in Guangdong Province, China). The ElasticNet was applied to select radiomics features and construct signature derived from computed tomography images, and univariate and multivariate analyses by logistic regression were used to identify the significant clinical and radiological variables with PNI. A robust combined model incorporating radiomics signature and clinicoradiological features based on machine learning was developed and the SHAP was used to visualize the prediction process. A Kaplan-Meier survival analysis was performed to compare prognostic differences between PNI-positive and PNI-negative groups and was conducted to explore the prognostic information of the combined model. RESULTS: Among 243 patients (mean age, 61.2 years ± 11.0 (SD); 152 men and 91 women), 108 (44.4%) were diagnosed as PNI-positive. The radiomics signature was constructed by seven radiomics features, with areas under the curves of 0.792, 0.748, and 0.729 in the training, external validation, and prospective cohorts, respectively. Three significant clinicoradiological features were selected and combined with radiomics signature to construct a combined model using machine learning. The eXtreme Gradient Boosting exhibited improved accuracy and robustness (areas under the curves of 0.884, 0.831, and 0.831, respectively). Survival analysis showed the construction combined model could be used to stratify relapse-free survival (hazard ratio, 1.933; 95% CI: 1.093-3.418; P =0.021). CONCLUSIONS: We developed and validated a robust combined model incorporating radiomics signature and clinicoradiological features based on machine learning to accurately identify the PNI statuses of ICC, and visualize the prediction process through SHAP for clinical application.

Circulating endothelial microvesicles and their carried miR-125a-5p: potential biomarkers for ischaemic stroke.

BACKGROUND: Endothelial microvesicles (EMVs) are closely associated with the status of endothelial cells (ECs). Our earlier study has shown that EMVs could exert protective roles in ECs by transferring their carried miR-125a-5p. However, whether circulating EMVs and their carried miR-125a-5p can be used as biomarkers in ischaemic stroke (IS) are remain unknown. METHODS: We recruited 72 subjects with IS, 60 subjects with high stroke risk and 56 age-matched controls. The circulating EMVs and their carried miR-125a-5p (EMV-miR-125a-5p) levels were detected. We used microRNA (miR) array to study expression changes of miRs in plasma EMVs samples of three IS patients and three matched healthy controls. Transient middle cerebral artery occlusion (tMCAO) was used to establish IS mouse model. RESULTS: EMVs level was obviously elevated in IS patients, with the highest level in acute stage, and was positively related to carotid plaque, carotid intima-media thickness (IMT), National Institutes of Health Stroke Scale (NIHSS), infarct volume. On the contrary, we observed that EMV-miR-125a-5p level was obviously reduced in IS, with the lowest level in acute stage, and was negatively correlated with carotid plaque, IMT, NIHSS scores, infarct volume. EMVs and EMV-miR-125a-5p levels were closely related with large artery atherosclerosis subgroup. Importantly, EMVs and EMV-miR-125a-5p levels could serve as independent risk factors, and receiver operating characteristic curve achieved an area under curve (AUC) of 0.720 and 0.832 for IS, respectively, and elevated to 0.881 after their combination. In IS mouse model, control EMVs or n-EMVs administration could decrease the infarct volume and neurological deficit score, while increase the cerebral blood flow of IS mice compared with vehicle group, while IS EMVs or oxygen and glucose deprivation (OGD)-EMVs administration aggravated the tMCAO induced ischaemic injury. In addition, we observed that OGD EMVmiR-125a-5p could partially ameliorate the OGD EMVs induced brain injury after IS. CONCLUSIONS: These findings demonstrate that circulating EMVs and EMV-miR-125a-5p are closely related with the occurrence, progress, subtypes and severity of IS, and they can serve as innovative biomarkers and therapeutic targets for IS, especially when they are combined.

Rab27a-dependent exosomes protect against cerebral ischemic injury by reducing endothelial oxidative stress and apoptosis.

INTRODUCTION: Multicellular crosstalk within the brain tissue has been suggested to play a critical role in maintaining cerebral vascular homeostasis. Exosomes (EXs) mediated cell-cell communication, but its role in cerebral ischemic injury is largely unknown. Rab27a is one of the major genes controlling EX release. Here, we explored the role of Rab27a in regulating brain EXs secretion, and the effects of Rab27a-mediated EXs on ischemia evoked cerebral vascular disruption and brain injury. METHODS: Cerebral ischemia was induced in Rab27a knockout (Rab27a-/- ) and wide type (WT) mice by transient middle cerebral artery occlusion (tMCAO). Differential gene expression analysis was performed in ischemic brain tissue by using mRNA sequencing. EXs isolated from brain tissue of Rab27a-/- and WT mice (EXWT or EXRab27a-/- ) were pre-administrated into tMCAO operated Rab27a-/- mice or oxygen and glucose deprivation (OGD) treated primary brain vascular endothelial cells (ECs). RESULTS: We demonstrated that Rab27a expression in the peri-infarct area of brain was significantly elevated, which was associated with local elevation in EXs secretion. Rab27a deficiency dramatically decreased the level of EXs in brain tissue of normal and tMCAO-treated mice, and Rab27a-/- mice displayed an increase in infarct volume and NDS, and a decrease in cMVD and CBF following tMCAO. Pre-infusion of EXWT increased the brain EXs levels in the tMCAO operated Rab27a-/- mice, accompanied with an increase in cMVD and CBF, and a decrease in infarct volume, NDS, ROS production, and apoptosis. The effects of EXRab27a-/- infusion were much diminished although in a dose-dependent manner. In OGD-treated ECs, EXRab27a-/- showed less effectivity than EXWT in decreasing ROS overproduction and apoptosis, paralleling with down-regulated expression of NOX2 and cleaved caspase-3. CONCLUSION: Our study demonstrates that Rab27a controls brain EXs secretion and functions, contributing to cerebral vascular protection from ischemic insult by preventing oxidative stress and apoptosis via down-regulating NOX2 and cleaved caspase-3 expression.

Exosomes and Exosomal microRNAs in Age-associated Stroke.

Aging has been considered to be the most important non-modifiable risk factor for stroke and death. Changes in circulation factors in the systemic environment, cellular senescence and artery hypertension during human ageing have been investigated. Exosomes are nanosize membrane vesicles that can regulate target cell functions via delivering their carried bioactive molecules (e.g. protein, mRNA, and microRNAs). In the central nervous system, exosomes and exosomal microRNAs play a critical role in regulating neurovascular function and are implicated in stroke initiation and progression. MicroRNAs are small non-coding RNAs that have been reported to play critical roles in various biological processes. Recently, evidence has shown that microRNAs are packaged into exosomes and can be secreted into the systemic and tissue environment. Circulating microRNAs participate in cellular senescence and contribute to age-associated stroke. Here, we provide an overview of current knowledge on exosomes and their carried microRNAs in the regulation of cellular and organismal ageing processes, demonstrating the potential role of exosomes and their carried microRNAs in age-associated stroke.