报告时间：2026年7月15日（星期三）10:30-11:30

报告地点：理学楼901报告厅

报告题目：A lightweight image segmentation network leveraging inception and squeeze-excitation modules for efficient skin lesion analysis

报告摘要: The U-shaped network (U-Net) and its derivatives are widely regarded as the cornerstone of medical image segmentation, with performance often improved by increasing model depth and complexity. However, this results in a greater computational burden and slower inference, limiting practical deployment. To address these issues, we propose a lightweight image segmentation based on the convolutional multilayer perceptron (MLP)-based network with U-Net (IS-UNeXt) model, a lightweight segmentation model based on an MLP framework that incorporates Inception-inspired multi-scale fusion blocks and squeeze-and-excitation (SE) modules to mitigate key limitations of existing models, such as high computational complexity, excessive parameter size, and high inference time. Evaluated on the international skin imaging collaboration 2018 (ISIC2018) and the dermoscopic image database acquired at the dermatology service of Hospital Pedro Hispano, Portugal (PH2) datasets, IS-UNeXt reduces inference time by 58.7%, parameters by 37.7%, and computational complexity by 48.4% compared to the convolutional MLP-based network with U-Net (UNeXt), while reaching an intersection over union (IoU) of 81.1% and a dice coefficient (DC) of 88.9% on ISIC2018 and IoU of 90.34% and DC of 94.42% on PH2. These results demonstrate IS-UNeXt’s effectiveness and efficiency in skin lesion segmentation, rendering it highly suitable for real-time medical applications on resource-constrained devices.

报告人简介：谈伟华副教授，毕业于台湾长庚大学电机工程研究所博士班，曾任台塑集团明志科技大学兼任助理教授及宏碁集团子公司智频科技公司技术经理。现任福州外语外贸学院大数据学院专任教师。专长5G行动通讯系统、无线通信系统、计算机数字网络系统、AIoT智能物联网及雷达系统、计算机网络技术、数据挖掘、人工智能等领域研究，获选福建省高层次D类人才。在相关领域有6篇国际期刊论文(EI/SCI)发表，美国、中国各一项专利，并获得台湾物联网专业工程师、高级电信工程师认证及思科CCNA等多项专业认证。曾出任多个大型项目承办人。