Self|supervised deep learning for joint 3D low|dose PET/CT image ...

Self-supervised deep learning for joint 3D low-dose PET/CT image ...

We propose a self-supervised two-stage training framework named MAsk-then-Cycle (MAC), to achieve self-supervised joint LDPET/LDCT denoising.

Self-supervised deep learning for joint 3D low-dose PET/CT image ...

Specifically, we propose a self-supervised denoising strategy named cycle self-recombination (CSR), which enables denoising without well-aligned sample pairs.

Self-supervised deep learning for joint 3D low-dose PET/CT image ...

AbstractDeep learning (DL)-based denoising of low-dose positron emission tomography (LDPET) and low-dose computed tomography (LDCT) has been widely explored ...

Self-supervised deep learning for joint 3D low-dose PET/CT image ...

Request PDF | On Aug 1, 2023, Feixiang Zhao and others published Self-supervised deep learning for joint 3D low-dose PET/CT image denoising | Find, ...

Self-supervised deep learning for joint 3D low-dose PET/CT image ...

Self-supervised deep learning for joint 3D low-dose PET/CT image denoising · Feixiang Zhao · Dongfen Li · Rui Luo · Mingzhe Liu · Xin Jiang · Junjie Hu.

Unsupervised and Self-supervised Learning in Low-Dose ...

Self-supervised deep learning for joint 3D low-dose PET/CT image denoising. Article. Aug 2023; COMPUT BIOL MED. Feixiang Zhao · Dongfen Li · Rui ...

Full Image-Index Remainder Based Single Low-Dose DR/CT Self ...

Imaging 2018 37 6 1407-1417. Crossref · Google Scholar. Recommendations. Self-supervised deep learning for joint 3D low-dose PET/CT image ...

Deep learning-assisted ultra-fast/low-dose whole-body PET/CT ...

Moreover, the synthesis of a 3D PET image (after training) ... Supervised learning with CycleGAN for low-dose FDG PET image denoising.

The promise of artificial intelligence and deep learning in PET and ...

Ultra-low-dose chest CT imaging of COVID-19 patients using a deep residual neural network ... Supervised learning with CycleGAN for low-dose FDG PET image ...

Artificial Intelligence and Deep Learning for Advancing PET Image ...

Single-Modality Supervised Joint PET-MR Image Reconstruction. IEEE ... Supervised learning with cyclegan for low-dose FDG PET image denoising. Med ...

Self-Supervised AI/ML Techniques - ISMRM 2024

1770. 61, Enhancing Low-Count PET Image Quality via Unsupervised Deep Learning using Novel Cost Function – A PET/MRI study.

Deep learning-based PET image denoising and reconstruction

F-FDG PET images by supervised learning approaches. Sample images showing (a) CT, (b) full-count PET, (c) low-count PET, and denoised PET images ...

Deep learning for [18F]fluorodeoxyglucose-PET-CT classification in ...

However, the number of diagnostic imaging specialists, especially those trained in nuclear medicine, remains low, particularly in low-income and ...

Semi-Supervised Standard-Dose PET Image Generation via Region ...

Self-supervised deep learning for joint 3D low-dose PET/CT image denoising · Feixiang ZhaoDongfen LiRui LuoMing-Yu LiuXin JiangJunjie Hu. Medicine, Engineering.

Artificial Intelligence for PET and SPECT Image Enhancement

Supervised deep-learning models have shown great potential in reducing radiotracer dose and scan times without sacrificing image quality and ...

TR&D 2 Projects < Yale Positron Emission Tomography

The study aimed to improve PET scan image quality by reducing noise using deep learning techniques. Traditional methods struggle to work well with ...

Using domain knowledge for robust and generalizable deep ...

Despite the potential of deep learning (DL)-based methods in substituting CT-based PET attenuation and scatter correction for CT-free PET ...

Self-supervised deep learning for joint 3D low-dose PET/CT image ...

Self-supervised deep learning for joint 3D low-dose PET/CT image denoising. 自监督深度学习用于三维低剂量PET/CT图像联合去噪. 相关领域. 降噪人工智能计算机科学 ...

Deep learning-assisted ultra-fast/low-dose whole-body PET/CT ...

Study of low-dose PET image recovery using supervised learning with CycleGAN. Kui Zhao, Long Zhou, Size Gao, Xiaozhuan Wang, Yaofa Wang, Xin ...

Empowering PET: harnessing deep learning for improved clinical ...

... PET image quality. CNNs are used to predict full-dose PET images from PET/MRI or PET/CT images acquired at a quarter or less of a full dose (Fig ...