Jiale Wang;Rui Guo;Ying Miao;Song Xue;Yu Zhang;Kuangyu Shi;Guoyan Zheng;Biao Li
{"title":"利用自组装技术降低跨扫描仪低剂量脑 PET 图像噪声","authors":"Jiale Wang;Rui Guo;Ying Miao;Song Xue;Yu Zhang;Kuangyu Shi;Guoyan Zheng;Biao Li","doi":"10.1109/TRPMS.2023.3347602","DOIUrl":null,"url":null,"abstract":"Deep learning models have shown great potential in reducing low-dose (LD) positron emission tomography (PET) image noise by estimating full-dose (FD) images from the corresponding LD images. Those models, however, when trained on paired LD-FD PET images from a source scanner, fail to generalize well when applied to LD PET images from a target scanner, due to a phenomenon called “domain drift.” In this study, we present a method for cross-scanner LD PET image noise reduction. This is done via a self-ensembling framework using a limited number of paired LD-FD PET images and a large number of LD PET images from the target scanner. The self-ensembling framework leverages the paired 2-D slices from both scanners to learn a regression model. It additionally incorporates a consistency loss on the LD PET images from the target scanner to enhance the model’s generalization capability. We conduct experiments on three datasets, respectively, acquired from three different scanners, including a GE Discovery MI (DMI) scanner, a Siemens Biograph Vision 450 (Vision) scanner, and a UI uMI 780 (uMI) scanner. Results from our comprehensive experiments demonstrate the generalization capability of our method.","PeriodicalId":46807,"journal":{"name":"IEEE Transactions on Radiation and Plasma Medical Sciences","volume":"8 4","pages":"391-401"},"PeriodicalIF":4.6000,"publicationDate":"2023-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Cross-Scanner Low-Dose Brain-PET Image Noise Reduction With Self-Ensembling\",\"authors\":\"Jiale Wang;Rui Guo;Ying Miao;Song Xue;Yu Zhang;Kuangyu Shi;Guoyan Zheng;Biao Li\",\"doi\":\"10.1109/TRPMS.2023.3347602\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Deep learning models have shown great potential in reducing low-dose (LD) positron emission tomography (PET) image noise by estimating full-dose (FD) images from the corresponding LD images. Those models, however, when trained on paired LD-FD PET images from a source scanner, fail to generalize well when applied to LD PET images from a target scanner, due to a phenomenon called “domain drift.” In this study, we present a method for cross-scanner LD PET image noise reduction. This is done via a self-ensembling framework using a limited number of paired LD-FD PET images and a large number of LD PET images from the target scanner. The self-ensembling framework leverages the paired 2-D slices from both scanners to learn a regression model. It additionally incorporates a consistency loss on the LD PET images from the target scanner to enhance the model’s generalization capability. We conduct experiments on three datasets, respectively, acquired from three different scanners, including a GE Discovery MI (DMI) scanner, a Siemens Biograph Vision 450 (Vision) scanner, and a UI uMI 780 (uMI) scanner. Results from our comprehensive experiments demonstrate the generalization capability of our method.\",\"PeriodicalId\":46807,\"journal\":{\"name\":\"IEEE Transactions on Radiation and Plasma Medical Sciences\",\"volume\":\"8 4\",\"pages\":\"391-401\"},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2023-12-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Radiation and Plasma Medical Sciences\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10375271/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Radiation and Plasma Medical Sciences","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10375271/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
摘要
深度学习模型通过从相应的低剂量(LD)图像中估计全剂量(FD)图像,在减少低剂量(LD)正电子发射断层扫描(PET)图像噪声方面显示出巨大的潜力。然而,当这些模型在来自源扫描仪的成对 LD-FD PET 图像上进行训练时,由于一种称为 "域漂移 "的现象,当应用到来自目标扫描仪的 LD PET 图像时,这些模型不能很好地泛化。在这项研究中,我们提出了一种跨扫描仪 LD PET 图像降噪方法。该方法通过一个自组装框架来实现,该框架使用数量有限的配对 LD-FD PET 图像和大量来自目标扫描仪的 LD PET 图像。自组装框架利用两台扫描仪的配对二维切片来学习回归模型。此外,它还在目标扫描仪的 LD PET 图像上加入了一致性损失,以增强模型的泛化能力。我们在三个数据集上进行了实验,这三个数据集分别来自三个不同的扫描仪,包括 GE Discovery MI(DMI)扫描仪、Siemens Biograph Vision 450(Vision)扫描仪和 UI uMI 780(uMI)扫描仪。综合实验结果证明了我们方法的通用能力。
Cross-Scanner Low-Dose Brain-PET Image Noise Reduction With Self-Ensembling
Deep learning models have shown great potential in reducing low-dose (LD) positron emission tomography (PET) image noise by estimating full-dose (FD) images from the corresponding LD images. Those models, however, when trained on paired LD-FD PET images from a source scanner, fail to generalize well when applied to LD PET images from a target scanner, due to a phenomenon called “domain drift.” In this study, we present a method for cross-scanner LD PET image noise reduction. This is done via a self-ensembling framework using a limited number of paired LD-FD PET images and a large number of LD PET images from the target scanner. The self-ensembling framework leverages the paired 2-D slices from both scanners to learn a regression model. It additionally incorporates a consistency loss on the LD PET images from the target scanner to enhance the model’s generalization capability. We conduct experiments on three datasets, respectively, acquired from three different scanners, including a GE Discovery MI (DMI) scanner, a Siemens Biograph Vision 450 (Vision) scanner, and a UI uMI 780 (uMI) scanner. Results from our comprehensive experiments demonstrate the generalization capability of our method.