Predicting peritumoral edema development after gamma knife radiosurgery of meningiomas using machine learning methods: a multicenter study.

OBJECTIVES: Edema is a complication of gamma knife radiosurgery (GKS) in meningioma patients that leads to a variety of consequences. The aim of this study is to construct radiomics-based machine learning models to predict post-GKS edema development. METHODS: In total, 445 meningioma patients who underwent GKS in our institution were enrolled and partitioned into training and internal validation datasets (8:2). A total of 150 cases from multicenter data were included as the external validation dataset. In each case, 1132 radiomics features were extracted from each pre-treatment MRI sequence (contrast-enhanced T1WI, T2WI, and ADC maps). Nine clinical features and eight semantic features were also generated. Nineteen random survival forest (RSF) and nineteen neural network (DeepSurv) models with different combinations of radiomics, clinical, and semantic features were developed with the training dataset, and evaluated with internal and external validation. A nomogram was derived from the model achieving the highest C-index in external validation. RESULTS: All the models were successfully validated on both validation datasets. The RSF model incorporating clinical, semantic, and ADC radiomics features achieved the best performance with a C-index of 0.861 (95% CI: 0.748-0.975) in internal validation, and 0.780 (95% CI: 0.673-0.887) in external validation. It stratifies high-risk and low-risk cases effectively. The nomogram based on the predicted risks provided personalized prediction with a C-index of 0.962 (95%CI: 0.951-0.973) and satisfactory calibration. CONCLUSION: This RSF model with a nomogram could represent a non-invasive and cost-effective tool to predict post-GKS edema risk, thus facilitating personalized decision-making in meningioma treatment. CLINICAL RELEVANCE STATEMENT: The RSF model with a nomogram built in this study represents a handy, non-invasive, and cost-effective tool for meningioma patients to assist in better counselling on the risks, appropriate individual treatment decisions, and customized follow-up plans. KEY POINTS: • Machine learning models were built to predict post-GKS edema in meningioma. The random survival forest model with clinical, semantic, and ADC radiomics features achieved excellent performance. • The nomogram based on the predicted risks provides personalized prediction with a C-index of 0.962 (95%CI: 0.951-0.973) and satisfactory calibration and shows the potential to assist in better counselling, appropriate treatment decisions, and customized follow-up plans. • Given the excellent performance and convenient acquisition of the conventional sequence, we envision that this non-invasive and cost-effective tool will facilitate personalized medicine in meningioma treatment.

Hypoxia Upregulates the Notch3 Signaling Pathway to Promote Epithelial-Mesenchymal Transition in Pulmonary Artery Cells.

Objective: To investigate the role and mechanism of Notch3 in a hypoxia-induced model of pulmonary hypertension, specifically pulmonary artery hypertension. Methods: A pulmonary artery hypertension rat model was induced using monocrotaline, and hepatic encephalopathy staining was used to observe the pathomorphological changes in pulmonary artery tissue. Primary isolation and extraction of rat pulmonary artery endothelial cells were performed, and a pulmonary artery hypertension cell model was established through hypoxia induction. Notch3 overexpression lentivirus (LV-Notch3) was used for intervention, and the expression of the Notch3 gene was detected using a real-time polymerase chain reaction. Western blotting was conducted to assess the expression of vascular endothelial growth factor, matrix metalloproteinase-2, and matrix metalloproteinase-9 proteins. Cell proliferation levels were measured using a medical training therapy assay. Results: Compared to the control group, the model group showed significant thickening of the pulmonary artery membrane, increased pulmonary angiogenesis, and endothelial cell damage. After Notch3 overexpression, the LV-Notch3 group showed further thickening of the pulmonary artery tunica media, increased pulmonary angiogenesis, and significantly improved endothelial cell injury. Compared to control cells, the model group showed a significant decrease in Notch3 expression (P < .05), while the expression levels of vascular endothelial growth factor, MMP-2, and MMP-9 proteins and cell proliferation ability increased significantly (P < .05). Following Notch3 overexpression, there was a significant increase in Notch3 expression (P < .05), and the expression levels of vascular endothelial growth factor, MMP-2, and MMP-9 proteins, as well as cell proliferation ability decreased significantly (P < .05). Conclusions: Notch3 can potentially reduce angiogenesis and proliferation in pulmonary artery endothelial cells and improve hypoxia-induced pulmonary artery hypertension in rats.

The methylation profiles of PRDM promoters in non-small cell lung cancer.

BACKGROUND: Non-small cell lung cancer (NSCLC) is one of the leading malignant tumors worldwide. Aberrant gene promoter methylation contributes to NSCLC, and PRDM is a tumor suppressor gene family that possesses histone methyltransferase activity. This study aimed to investigate whether aberrant methylation of PRDM promoter is involved in NSCLC. MATERIALS AND METHODS: Primary tumor tissues, adjacent nontumorous tissues, and distant lung tissues were collected from 75 NSCLC patients including 52 lung squamous cell carcinoma (LSCC) patients and 23 lung adenocarcinoma patients. The expression of PRDMs was detected by polymerase chain reaction (PCR), Western blot, and immunohistochemical analysis. The methylation of PRDM promoters was detected by methylation-specific PCR. The correlation of methylation and expression of PRDMs with clinicopathological characteristics of patients were analyzed. RESULTS: mRNA expression of PRDM2, PRDM5, and PRDM16 was low or absent in tumor tissues compared to distant lung tissues. The methylation frequencies of PRDM2, PRDM5, and PRDM16 in tumor tissues were significantly higher than those in distal lung tissues. In LSCC patients, methylation of PRDM2 and PRDM16 was correlated with smoking status and methylation of PRDM5 was correlated with tumor differentiation. CONCLUSION: The expression of PRDM2, PRDM5, and PRDM16 is low or absent in NSCLC, and this is mainly due to gene promoter methylation. Smoking may be an important cause of PRDM2 and PRDM16 methylation in NSCLC.

Methylation of PRDM2, PRDM5 and PRDM16 genes in lung cancer cells.

AIMS: To investigate the changes of expression and methylation status of PRDM2, PRDM5, PRDM16 in lung cancer cells after treatment with demethylation agent. METHODS: A549 (lung adenocarcinoma cell line), HTB-182 (lung squamous cell carcinoma cell line) and HBE (normal bronchial cell line) were treated with 5-aza-2dC. The methylation state of PRDM2, PRDM5, PRDM16 was detected by MSP. The expression of PRDM2, PRDM5, PRDM16 was detected by RT-PCR and Western blot analysis. Cell growth was detected by MTT assay. RESULTS: 5-aza-2-dC reduced the methylation of PRDM2, PRDM5, PRDM16 gene in A549 and HTB-182 cells but not in HBE cells. Consistently, 5-aza-2dC increased mRNA and protein expression of PRDM2, PRDM5, PRDM16 in A549 and HTB-182 cells but not in HBE cells. Furthermore, 5-aza-2dC inhibited the growth of A549 and HTB-182 cells but not HBE cells. CONCLUSIONS: PRDM2, PRDM5, PRDM16 promoters are methylated and their expression is suppressed in lung cancer cells. Demethylation drug 5-aza-2dC could upregulate the expression of PRDM2, PRDM5, PRDM16 and suppress lung cancer cell growth. 5-aza-2dC has potential to be used for lung cancer therapy by epigenetic mechanism.

Promoter methylation-mediated downregulation of PRDM5 contributes to the development of lung squamous cell carcinoma.

PRDM5 has been proposed as a tumor suppressor frequently downregualted in tumor. In this study, lung squamous cell carcinoma tissues and adjacent nontumorous normal tissues were collected from 30 patients. PRDM5 expression was detected by reverse transcription polymerase chain reaction and Western blot analysis, DNA methylation of PRDM5 promoter was analyzed by methylation-specific PCR. SK-MES-1 cells or xenografts in nude mice were treated with 5-aza-2'-deoxycitydine, and cell proliferation and tumor growth in nude mice were examined. We found that PRDM5 promoter was methylated and PRDM5 expression at both mRNA and protein levels was reduced in lung squamous cell carcinoma tissues. Furthermore, PRDM5 promoter methylation was significantly correlated with tumor differentiation and lymph node metastasis of lung squamous cell carcinoma, but not with age, gender, smoking, or tumor grade. 5-aza-2'-deoxycitydine inhibited the proliferation of SK-MES-1 cells and the growth of xenografts in nude mice, accompanied by reduced methylation of PRDM5 promoter and increased expression of PRDM5. Taken together, our data suggest that PRDM5 is a tumor suppressor in lung cancer and is a promising target for the diagnosis, prognosis, and therapy of lung squamous cell carcinoma.