A convolutional neural network based approach for generating full PET/CT image series from shorter scan time

基于卷积神经网络的方法，用于通过更短的扫描时间生成完整的 PET/CT 图像系列

• 批准号: 19K20685
• 负责人: BhusalChhatkuli Ritu
• 金额: $ 2.66万
• 依托单位: National Institutes for Quantum Science and Technology
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Early-Career Scientists
• 财政年份: 2019
• 资助国家: 日本
• 起止时间: 2019-04-01 至 2024-03-31
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-19K20685/
• 关键词: PET/CT; Prediction; Neural Network; CNN-LSTM; dynamic images; RNN; list mode PET; neural networks; image generation; CNN; time series; prediction

Successful generation of delayed images and comparison with actual delayed images using CNN-LSTM based neural network.-Summarizing research and statistical analysis for the publication in journal.-Writing journal paper for the part of research and submitting to the journal.-Reviewing the writing according to the comments from the reviewers and repeat the analysis for the part of the research. Currently in the process of revision.

使用基于CNN-LSTM的神经网络成功生成延迟图像并与实际延迟图像进行比较。对期刊出版物的夏目研究和统计分析。编写期刊论文，以进行研究并提交杂志。-审视写作根据审稿人的评论，并重复研究的分析。目前正在修订过程中。

项目成果

Generation of delayed PET/CT images for pancreatic cancer using CNN-LSTM model

使用 CNN-LSTM 模型生成胰腺癌延迟 PET/CT 图像

• 发表时间: 2021
• 作者: Wang H;Itoh S;Matsumoto Y;Nishie A;Kurihara T;Shimagaki T;Nagao Y;Toshima T;Harada N;Kohashi K;Oda Y;Ishigami K;Maruyama H;Yoshizumi T;Mori M.;Murayama Masanori A.;Ritu Bhusal Chhatkuli
• 通讯作者: Ritu Bhusal Chhatkuli