计算机科学
学习迁移
宫颈癌
特征(语言学)
人工智能
传输(计算)
深度学习
领域(数学分析)
癌症
自动化
机器学习
插值(计算机图形学)
数据挖掘
医学
数学
图像(数学)
机械工程
数学分析
语言学
哲学
并行计算
工程类
内科学
作者
Lu Wen,Jianghong Xiao,Jie Zeng,Chen Zu,Xi Wu,Jiliu Zhou,Xingchen Peng,Yan Wang
标识
DOI:10.1016/j.patcog.2023.109606
摘要
Recently, deep learning has accomplished the automation of radiation therapy planning, enhancing its quality and efficiency. However, such progress comes at the cost of a large amount of clinical data. For some low-incidence cancers, i.e., cervical cancer, with limited available data, current data-hungry deep models fail to achieve satisfactory performance. To address this, in this paper, considering that cervical cancer and rectum cancer share the same scanning area and organs at risk (OARs), we resort to transfer learning to transfer the knowledge acquired from rectum cancer (source domain) to cervical cancer (target domain) to perform dose map prediction task. To overcome the possible negative transferring problem, we design a two-phase paradigm to progressively transfer knowledge. In the first phase, we aggregate the data of the two domains by linear interpolation and pre-train an aggregated network with the aggregated data to perceive the target dose distribution beforehand. In the second phase, we elaborately design two modules, i.e., a Feature-level Transfer (FT) Module, and an Image-level Transfer (IT) Module, to selectively transfer knowledge in multi-level. Specifically, the FT module aims to preserve those filters that are more helpful while the IT module tries to highlight those samples with more target-specific knowledge. Extensive experiments proclaim the exemplary performance of our proposed method compared with other state-of-the-art methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI