S. Kannan^1,*, S. Anusuya²

CMC-Computers, Materials & Continua, Vol.77, No.3, pp. 3835-3851, 2023, DOI:10.32604/cmc.2023.042465

Abstract Gliomas, the most prevalent primary brain tumors, require accurate segmentation for diagnosis and risk assessment. In this paper, we develop a novel deep learning-based method, the Dynamic Hierarchical Attention for Improved Segmentation and Survival Prognosis (DHA-ISSP) model. The DHA-ISSP model combines a three-band 3D convolutional neural network (CNN) U-Net architecture with dynamic hierarchical attention mechanisms, enabling precise tumor segmentation and survival prediction. The DHA-ISSP model captures fine-grained details and contextual information by leveraging attention mechanisms at multiple levels, enhancing segmentation accuracy. By achieving remarkable results, our approach surpasses 369 competing teams in the 2020 Multimodal Brain Tumor Segmentation Challenge. With… More >

Yuanshan Yao, Yinjie Zhou, Zhenhua Yang, Hongbo Huang, Haibo Shen

Oncology Research, Vol.27, No.2, pp. 203-210, 2019, DOI:10.3727/096504018X15202953107093

Abstract The purpose of this study was to determine the effects of resection coupled with standard chemotherapy on the survival prognosis of patients with early stage small cell lung carcinoma (SCLC). Patients (n=110) with mediastinal lymph node-negative SCLC were enrolled in this study. The baseline clinical data of patients with surgery were retrospectively reviewed. Overall survival (OS) and progression-free survival (PFS) were measured by Kaplan–Meier and log-rank test analyses. Ninety-eight patients received mediastinoscopy biopsy, and pulmonary lobectomy or sublobar resection, and 67 patients underwent adjuvant chemotherapy after pulmonary lobectomy. Adjuvant chemotherapy after surgical intervention was associated with longer OS (median OS:… More >