4.3 Article

Ultra high speed SPECT bone imaging enabled by a deep learning enhancement method: a proof of concept

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Mathematical & Computational Biology

LU-Net: combining LSTM and U-Net for sinogram synthesis in sparse-view SPECT reconstruction

Si Li et al.

Summary: Reducing the radiation dose in single-photon emission computed tomography (SPECT) imaging is crucial. This study proposes a neural network architecture that considers the sequence feature of projection data to reduce ray artifacts in the reconstructed image. The proposed network achieves significant improvement in both global and local quality metrics at various simulated view levels.

MATHEMATICAL BIOSCIENCES AND ENGINEERING (2022)

Article Cardiac & Cardiovascular Systems

Standard SPECT myocardial perfusion estimation from half-time acquisitions using deep convolutional residual neural networks

Isaac Shiri et al.

Summary: This study aimed to assess the feasibility of reducing acquisition time in MPI-SPECT imaging using deep learning techniques. The results showed that predicted full time images had better quality than predicted full projections, with significant increase in error metrics when reducing acquisition time per projection. The deep neural network effectively recovered image quality and reduced bias in quantification metrics.

JOURNAL OF NUCLEAR CARDIOLOGY (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Deep learning with noise-to-noise training for denoising in SPECT myocardial perfusion imaging

Junchi Liu et al.

Summary: The study demonstrates the effectiveness of using deep learning for denoising in SPECT-MPI images, improving the detection of perfusion defects compared to traditional postfiltering methods. The coupled U-Net structure shows superior performance in noise suppression and defect detection compared to other denoising networks. Additionally, the deep learning approach results in improved signal-to-noise ratios and reduced inter-subject variability, showcasing its potential for clinical applications.

MEDICAL PHYSICS (2021)

Article Computer Science, Artificial Intelligence

ROSNet: Robust one-stage network for CT lesion detection *

Kuan-Yu Lung et al.

Summary: Automatic lesion detection from CT scans is crucial in medical diagnosis, but is challenging due to scale variance, imbalanced data, and prediction stability. To tackle these challenges, a novel network structure ROSNet is proposed, which outperforms the best performance in MICCAI 2019.

PATTERN RECOGNITION LETTERS (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Post-reconstruction enhancement of [18F]FDG PET images with a convolutional neural network

John Ly et al.

Summary: The study introduced an AI-based method to enhance [F-18]FDG-PET images, improving image quality by reducing noise and increasing contrast. Results showed that the AI-enhanced images performed better in terms of noise and contrast, while maintaining stability in maximum and peak standardized uptake values compared to standard images. The method has the potential to provide better images to nuclear medicine physicians or reduce acquisition time/administered activity.

EJNMMI RESEARCH (2021)

Article Computer Science, Information Systems

Deep learning based diagnosis of Parkinson's disease using convolutional neural network

S. Sivaranjini et al.

MULTIMEDIA TOOLS AND APPLICATIONS (2020)

Article Computer Science, Interdisciplinary Applications

Improving Diagnostic Accuracy in Low-Dose SPECT Myocardial Perfusion Imaging With Convolutional Denoising Networks

Albert Juan Ramon et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2020)

Article Computer Science, Artificial Intelligence

U-2-Net: Going deeper with nested U-structure for salient object detection

Xuebin Qin et al.

PATTERN RECOGNITION (2020)

Article Computer Science, Interdisciplinary Applications

Deep Generative Adversarial Neural Networks for Compressive Sensing MRI

Morteza Mardani et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2019)

Article Radiology, Nuclear Medicine & Medical Imaging

Accelerated SPECT image reconstruction with FBP and an image enhancement convolutional neural network

Martijn M. A. Dietze et al.

EJNMMI PHYSICS (2019)

Article Radiology, Nuclear Medicine & Medical Imaging

PET image denoising using unsupervised deep learning

Jianan Cui et al.

EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING (2019)

Article Radiology, Nuclear Medicine & Medical Imaging

Ultra-Low-Dose 18F-Florbetaben Amyloid PET Imaging Using Deep Learning with Multi-Contrast MRI Inputs

Kevin T. Chen et al.

RADIOLOGY (2019)

Proceedings Paper Engineering, Biomedical

LOW-DOSE CARDIAC-GATED SPECT STUDIES USING A RESIDUAL CONVOLUTIONAL NEURAL NETWORK

Chao Song et al.

2019 IEEE 16TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2019) (2019)

Article Computer Science, Interdisciplinary Applications

Enhancing the Image Quality via Transferred Deep Residual Learning of Coarse PET Sinograms

Xiang Hong et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2018)

Article Computer Science, Interdisciplinary Applications

Multi-Modality Cascaded Convolutional Neural Networks for Alzheimer's Disease Diagnosis

Manhua Liu et al.

NEUROINFORMATICS (2018)

Article Computer Science, Interdisciplinary Applications

Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network

Hu Chen et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Densely Connected Convolutional Networks

Gao Huang et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Article Radiology, Nuclear Medicine & Medical Imaging

PSMA-Based [18F]DCFPyL PET/CT Is Superior to Conventional Imaging for Lesion Detection in Patients with Metastatic Prostate Cancer

Steven P. Rowe et al.

MOLECULAR IMAGING AND BIOLOGY (2016)

Article Radiology, Nuclear Medicine & Medical Imaging

Non-invasive assessment of coronary artery disease with CT coronary angiography and SPECT: a novel dose-saving fast-track algorithm

Aju P. Pazhenkottil et al.

EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING (2010)