RESUMEN
Objective This study aimed to explore the prognostic value of 18F-FDG PET/CT Metabolic and Heterogeneity Parameters Combined with Clinical Features Before Definitive Chemoradiotherapy(D-CRT)in predicting the prognosis of esophageal squamous cell carcinoma(ESCC)Patients.Methods A retrospective analysis was conducted on clinical data from 106 patients with ESCC who received D-CRT at the first affiliated Hospital of University of Science and Technology of China between January 2017 and December 2021.All patients underwent 18F-FDG PET/CT examination before the treatment.The primary tumor′s metabolic and heterogeneity parameters were obtained through data processing.All patients were followed up for overall survival.The Kaplan-Meier method and Cox proportional hazards models were used to analyze the association between clinical features,tumor metabo-lism and heterogeneity parameters and patient prognosis.Results The 1-and 1.5-year overall survival rates of all patients were 77.4%and 51.9%.The median survival time was 20 months.Univariate analysis showed that N stage,M stage,metabolic tumor volume,total lesion glycolysis,heterogeneity index-2(HI-2),and coefficient of variation with a threshold of 40%maximum standard uptake value(CV40%)were correlated with the prognosis of ESCC(all P<0.05).Multivariate analysis showed that N stage and CV40%were independent predictors of prognosis in patients with ESCC(P = 0.039 and P<0.001,respectively).Conclusion N stage and tumor metabolic heterogeneity parameter CV40%,which offering a degree of predictive value,are closely related to the prognosis of patients with ESCC treated with D-CRT.
RESUMEN
Magnetic resonance (MR) imaging is an important tool for prostate cancer diagnosis, and accurate segmentation of MR prostate regions by computer-aided diagnostic techniques is important for the diagnosis of prostate cancer. In this paper, we propose an improved end-to-end three-dimensional image segmentation network using a deep learning approach to the traditional V-Net network (V-Net) network in order to provide more accurate image segmentation results. Firstly, we fused the soft attention mechanism into the traditional V-Net's jump connection, and combined short jump connection and small convolutional kernel to further improve the network segmentation accuracy. Then the prostate region was segmented using the Prostate MR Image Segmentation 2012 (PROMISE 12) challenge dataset, and the model was evaluated using the dice similarity coefficient (DSC) and Hausdorff distance (HD). The DSC and HD values of the segmented model could reach 0.903 and 3.912 mm, respectively. The experimental results show that the algorithm in this paper can provide more accurate three-dimensional segmentation results, which can accurately and efficiently segment prostate MR images and provide a reliable basis for clinical diagnosis and treatment.