4.3 Article

Combining deep learning with a kinetic model to predict dynamic PET images and generate parametric images

Related references

Note: Only part of the references are listed.
Article Radiology, Nuclear Medicine & Medical Imaging

A deep neural network for parametric image reconstruction on a large axial field-of-view PET

Y. Li et al.

Summary: In this study, a deep learning framework based on DeepPET was used to reconstruct high-quality direct Patlak Ki images from five-frame sinograms without input function. The results show the potential of artificial intelligence in reducing acquisition time and the dependence of input function in parametric imaging.

EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING (2023)

Review Radiology, Nuclear Medicine & Medical Imaging

Parametric Imaging With Dynamic PET for Oncological Applications: Protocols, Interpretation, Current Applications and Limitations for Clinical Use

Antonia Dimitrakopoulou-Strauss et al.

Summary: Nuclear medicine imaging modalities, particularly positron emission tomography (PET), can provide functional images that show the distribution of radioactivity at a specific time point. By using mathematical models, specific parameters of radiotracer pharmacokinetics can be depicted and visualized. These parametric images offer additional information about the distribution of the tracer over time and space compared to conventional PET images. Although PET parametric imaging has been mainly used for research purposes, advancements in PET-CT scanners and evaluation software may lead to its implementation in clinical practice.

SEMINARS IN NUCLEAR MEDICINE (2022)

Article Computer Science, Artificial Intelligence

Unsupervised PET logan parametric image estimation using conditional deep image prior

Jianan Cui et al.

Summary: In this study, a method combining conditional deep image prior (CDIP) with Logan parametric image estimation was proposed to generate high-quality parametric images. The proposed method achieved higher contrast-to-noise improvement ratios compared to Gaussian filtered and nonlocal mean (NLM) denoised results.

MEDICAL IMAGE ANALYSIS (2022)

Review Radiology, Nuclear Medicine & Medical Imaging

Kinetic modeling and parametric imaging with dynamic PET for oncological applications: general considerations, current clinical applications, and future perspectives

Antonia Dimitrakopoulou-Strauss et al.

Summary: Dynamic PET studies are primarily used for research purposes, but limitations such as complex data evaluation and restricted axial field of view have hindered its clinical implementation. However, with the development of new-generation PET/CT scanners and advanced evaluation software packages, the wider use of dynamic PET is expected to improve oncological diagnostics and therapy assessment.

EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Direct and indirect parameter imaging methods for dynamic PET

Xin Mao et al.

Summary: This study introduces a method for parametric image reconstruction using guided kernel means (GKM) and dynamic PET image information, which has higher signal-to-noise ratio and better retention of detailed information compared to traditional methods. Computer simulations show that the proposed method outperforms conventional methods in direct reconstruction.

BIOMEDICAL PHYSICS & ENGINEERING EXPRESS (2021)

Review Computer Science, Artificial Intelligence

Imbalance Problems in Object Detection: A Review

Kemal Oksuz et al.

Summary: This paper provides a comprehensive review of imbalance problems in object detection, presenting a problem-based taxonomy to systematically analyze and discuss solutions. Major open issues regarding existing and new imbalance problems are identified, with a webpage cataloging relevant papers for researchers to access.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Article Neurosciences

Rapid high-quality PET Patlak parametric image generation based on direct reconstruction and temporal nonlocal neural network

Nuobei Xie et al.

Summary: Parametric imaging based on dynamic PET is widely used in neurology. Direct reconstruction methods can produce superior image quality by reconstructing parametric images directly from raw PET data, particularly in low-dose scenarios. However, the widespread adoption of direct methods is hindered by excessive computational demand and limited access to raw data.

NEUROIMAGE (2021)

Article Oncology

Metabolomics in cancer research and emerging applications in clinical oncology

Daniel R. Schmidt et al.

Summary: Cancer has complex effects on cellular and systemic metabolism, with metabolomics playing a crucial role in providing insights for cancer diagnosis, monitoring, and therapy. Advances in technology have expanded the applications of metabolomics in clinical research, with the potential to further enhance cancer patient management in the future.

CA-A CANCER JOURNAL FOR CLINICIANS (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Total-Body PET Kinetic Modeling and Potential Opportunities Using Deep Learning

Yiran Wang et al.

PET CLINICS (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Parametric Imaging With PET and SPECT

Jean-Dominique Gallezot et al.

IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES (2020)

Proceedings Paper Computer Science, Artificial Intelligence

Dynamic PET Image Reconstruction Using Nonnegative Matrix Factorization Incorporated With Deep Image Prior

Tatsuya Yokota et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Proceedings Paper Engineering, Biomedical

Direct Patlak Reconstruction from Dynamic PET Using Unsupervised Deep Learning

Kuang Gong et al.

15TH INTERNATIONAL MEETING ON FULLY THREE-DIMENSIONAL IMAGE RECONSTRUCTION IN RADIOLOGY AND NUCLEAR MEDICINE (2019)

Proceedings Paper Engineering, Biomedical

CT-guided PET parametric image reconstruction using deep neural network without prior training data

Jianan Cui et al.

MEDICAL IMAGING 2019: PHYSICS OF MEDICAL IMAGING (2019)

Article Engineering, Electrical & Electronic

A Haar wavelet-based perceptual similarity index for image quality assessment

Rafael Reisenhofer et al.

SIGNAL PROCESSING-IMAGE COMMUNICATION (2018)

Proceedings Paper Optics

Nonlinear PET Parametric Image Reconstruction with MRI Information Using Kernel Method

Kuang Gong et al.

MEDICAL IMAGING 2017: PHYSICS OF MEDICAL IMAGING (2017)

Review Radiology, Nuclear Medicine & Medical Imaging

History and future technical innovation in positron emission tomography

Terry Jones et al.

JOURNAL OF MEDICAL IMAGING (2017)

Article Radiology, Nuclear Medicine & Medical Imaging

FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0

Ronald Boellaard et al.

EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING (2015)

Article Computer Science, Artificial Intelligence

VSI: A Visual Saliency-Induced Index for Perceptual Image Quality Assessment

Lin Zhang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2014)

Article Computer Science, Artificial Intelligence

Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index

Wufeng Xue et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2014)

Article Radiology, Nuclear Medicine & Medical Imaging

The quantification with FDG as seen by a physician

Guido Galli et al.

NUCLEAR MEDICINE AND BIOLOGY (2013)

Review Radiology, Nuclear Medicine & Medical Imaging

Importance of Quantification for the Analysis of PET Data in Oncology: Review of Current Methods and Trends for the Future

Giampaolo Tomasi et al.

MOLECULAR IMAGING AND BIOLOGY (2012)

Article Computer Science, Artificial Intelligence

FSIM: A Feature Similarity Index for Image Quality Assessment

Lin Zhang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2011)

Article Computer Science, Artificial Intelligence

Information Content Weighting for Perceptual Image Quality Assessment

Zhou Wang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2011)

Article Engineering, Electrical & Electronic

Most apparent distortion: full-reference image quality assessment and the role of strategy

Eric C. Larson et al.

JOURNAL OF ELECTRONIC IMAGING (2010)