咨询与建议

看过本文的还看了

相关文献

该作者的其他文献

文献详情 >Automatic reorientation by dee... 收藏
arXiv

Automatic reorientation by deep learning to generate short-axis SPECT myocardial perfusion images

作     者:Zhu, Fubao Wang, Guojie Zhao, Chen Malhotra, Saurabh Zhao, Min He, Zhuo Shi, Jianzhou Jiang, Zhixin Zhou, Weihua 

作者机构:School of Computer and Communication Engineering Zhengzhou University of Light Industry Henan Zhengzhou450000 China Department of Applied Computing Michigan Technological University HoughtonMI49931 United States Division of Cardiology Cook County Health and Hospitals System ChicagoIL60612 United States Division of Cardiology Rush Medical College ChicagoIL60612 United States Department of Nuclear Medicine Xiangya Hospital Central South University Changsha410008 China Department of Cardiology The First Affiliated Hospital of Nanjing Medical University Nanjing210000 China Center for Biocomputing and Digital Health Institute of Computing and Cybersystems Health Research Institute Michigan Technological University HoughtonMI49931 United States 

出 版 物:《arXiv》 (arXiv)

年 卷 期:2022年

核心收录:

主  题:Deep learning 

摘      要:Single photon emission computed tomography (SPECT) myocardial perfusion images (MPI) can be displayed both in traditional short-axis (SA) cardiac planes and polar maps for interpretation and quantification. It is essential to reorient the reconstructed transaxial SPECT MPI into standard SA slices. This study is aimed to develop a deep-learning-based approach for automatic reorientation of MPI. Methods: A total of 254 patients were enrolled, including 228 stress SPECT MPIs and 248 rest SPECT MPIs. Five-fold cross-validation with 180 stress and 201 rest MPIs was used for training and internal validation;the remaining images were used for testing. The rigid transformation parameters (translation and rotation) from manual reorientation were annotated by an experienced operator and used as the ground truth. A convolutional neural network (CNN) was designed to predict the transformation parameters. Then, the derived transform was applied to the grid generator and sampler in spatial transformer network (STN) to generate the reoriented image. A loss function containing mean absolute errors for translation and mean square errors for rotation was employed. A three-stage optimization strategy was adopted for model optimization: 1) optimize the translation parameters while fixing the rotation parameters;2) optimize rotation parameters while fixing the translation parameters;3) optimize both translation and rotation parameters together. Results: In the test set, the correlation coefficients of the translation distances and rotation angles between the model prediction and the ground truth were 0.99 in X axis, 0.99 in Y axis, 0.99 in Z axis, 0.99 along X axis, 0.99 along Y axis and 0.99 along Z axis, respectively. For the 46 stress MPIs in the test set, the Pearson correlation coefficients were 0.95 in scar burden and 0.95 in summed stress score;for the 46 rest MPIs in the test set, the Pearson correlation coefficients were 0.95 in scar burden and 0.95 in summed rest score. Conclu

读者评论 与其他读者分享你的观点

用户名:未登录
我的评分