ABSTRACT
Cerebral metastases are the most common intracranial tumors in adults,with an increasing incidence in recent years.Radiomics can quantitatively analyze and process medical images to guide clinical practice.In recent years,CT and MRI-based radiomics has been gradually applied to the precise diagnosis and treatment of cerebral metastases,such as the precise detection and segmentation of tumors,the differential diagnosis with other cerebral tumors,the identification of primary tumors,the evaluation of treatment efficacy,and the prediction of prognosis.This article reviews the advances in radiomics of cerebral metastases.
Subject(s)
Humans , Brain Neoplasms/diagnostic imaging , Diagnosis, Differential , Magnetic Resonance Imaging , Prognosis , Supratentorial NeoplasmsABSTRACT
Objective To explore the correlation between EBV DNA load and peripheral immune cells (including lymphocyte supsets and natural killer cells) before treatment in patients with NPC, and analyze the influence of circulating immune cell supsets related to EBV on the prognosis of NPC patients. Methods We retrospectively analyzed the general data of 203 NPC patients without distant metastasis at the first treatment, as well as the data of peripheral blood EBV DNA and circulating immune cell supset. The ROC curve analysis was used to determine the cutoff value of each circulating immune cell supset. Kaplan-Meier method was used for survival analysis, and Cox regression model was used for multi-factor prognostic correlation analysis. Results The 3-year OS, PFS, DMFS and LRFS of EBV DNA < 400 copies/ml group and EBV DNA≥400 copies/ml group were 99.2% vs. 90.1% (P=0.001), 96.7% vs. 90.1% (P=0.028), 98.4% vs. 90.1% (P=0.005) and 98.4% vs. 100% (P > 0.05), respectively. EBV DNA is negatively correlated with the ratio of CD19+ B cells before treatment (r=-0.138, P=0.040), and there was no significant correlation between EBV DNA and other circulating immune supgroups (P > 0.05). ROC analysis showed that the cut-off value of CD19+B cell ratio before treatment related to the 3-year OS was 8.33% (P=0.02). The 3-year OS, PFS, DMFS and LRFS of patients with CD19+B cells ratio ≤8.33% and CD19+B cells ratio > 8.33% were respectively 90.4% vs. 99.2% (P=0.003), 89.2% vs. 97.5% (P=0.008), 90.4% vs. 98.3% (P=0.008) and 98.8% vs. 99.2% (P > 0.05). However, ROC analysis showed that there was no significant correlation between OS and other peripheral immune cells (including the proportion of CD3+T, CD3+CD4+T, CD3+CD8+T and CD56+NK cells and CD4+/CD8+ ratio). Multivariate analysis showed that EBV DNA load was an independent prognostic factor of 3-year PFS of NPC patients, and the ratio of CD19+B cells was an independent prognostic factor of 3-year PFS, MFS and OS of NPC patients. Conclusion Before treatment, there is a negative correlation between plasma EBV DNA and the proportion of CD19+B cells in peripheral blood. Both can be used as the predictors of 3-year OS, PFS and DMFS of NPC patients.
ABSTRACT
Artificial intelligence (AI) represents the latest wave of computer revolution and is considered revolutionary technology in many industries including healthcare. AI has been applied in medical imaging mainly due to the improvement of computational learning,big data mining,and innovations of neural network architecture. AI can improve the efficiency and accuracy of imaging diagnosis and reduce medical cost;also,it can be used to predict the disease risk. In this article we summarize and analyze the application of AI in musculoskeletal imaging.