参数化复杂度
计算机科学
特征(语言学)
人工神经网络
人工智能
迭代重建
计算机断层摄影术
火车
模式识别(心理学)
算法
数学
医学
哲学
放射科
地理
地图学
语言学
作者
Wenjun Xia,Zexin Lu,Yongqiang Huang,Yan Liu,Hu Chen,Jiliu Zhou,Yi Zhang
出处
期刊:IEEE Transactions on Medical Imaging
[Institute of Electrical and Electronics Engineers]
日期:2021-11-01
卷期号:40 (11): 3065-3076
被引量:35
标识
DOI:10.1109/tmi.2021.3085839
摘要
The current mainstream computed tomography (CT) reconstruction methods based on deep learning usually need to fix the scanning geometry and dose level, which significantly aggravates the training costs and requires more training data for real clinical applications. In this paper, we propose a parameter-dependent framework (PDF) that trains a reconstruction network with data originating from multiple alternative geometries and dose levels simultaneously. In the proposed PDF, the geometry and dose level are parameterized and fed into two multilayer perceptrons (MLPs). The outputs of the MLPs are used to modulate the feature maps of the CT reconstruction network, which condition the network outputs on different geometries and dose levels. The experiments show that our proposed method can obtain competitive performance compared to the original network trained with either specific or mixed geometry and dose level, which can efficiently save extra training costs for multiple geometries and dose levels.
科研通智能强力驱动
Strongly Powered by AbleSci AI