Artificial Intelligence-Based Image Enhancement in PET Imaging: Noise Reduction and Resolution Enhancement.

  title={Artificial Intelligence-Based Image Enhancement in PET Imaging: Noise Reduction and Resolution Enhancement.},
  author={Juan Liu and Masoud Malekzadeh and Niloufar Mirian and Tzu-An Song and Chi Liu and Joyita Dutta},
  journal={PET clinics},
  volume={16 4},
High noise and low spatial resolution are two key confounding factors that limit the qualitative and quantitative accuracy of PET images. Artificial intelligence models for image denoising and deblurring are becoming increasingly popular for the postreconstruction enhancement of PET images. We present a detailed review of recent efforts for artificial intelligence-based PET image enhancement with a focus on network architectures, data types, loss functions, and evaluation metrics. We also… Expand

Figures from this paper


Micro-Networks for Robust MR-Guided Low Count PET Imaging
This article proposes the use of a relatively low-complexity CNN (micro-net) as a post-reconstruction MR-guided image processing step to reduce noise and reconstruction artefacts while also improving resolution in low count PET scans. Expand
PET Image Super Resolution using Convolutional Neural Networks
A convolutional neural network trained on PET images which can estimate a high resolution PET image from its input low resolution image is proposed. Expand
Super-Resolution PET Imaging Using Convolutional Neural Networks
A super-resolution (SR) imaging technique for PET based on convolutional neural networks (CNNs) is presented and high-resolution anatomical information based on magnetic resonance (MR) imaging is incorporated to facilitate the resolution recovery process. Expand
Dynamic PET Image Denoising With Deep Learning-Based Joint Filtering
A deep learning-based joint filtering framework for simultaneously incorporating information from longer acquisition PET frames and high-resolution magnetic resonance (MR) images into the short frames is developed and shown to have great potential for dynamic PET image denoising. Expand
An investigation of quantitative accuracy for deep learning based denoising in oncological PET.
Full 3D U-net is superior to several existing denoising methods, including Gaussian filter, anatomical-guided non-local mean (NLM) filter, and MAP reconstruction with Quadratic prior and relative difference prior, in terms of superior image quality and trade-off between noise and bias. Expand
Convolutional micro-networks for MR-guided low-count PET image processing
A deliberately small network (µ-net) is proposed which can be trained with comparatively little data and is demonstrated to reduce normalised root mean squared error (NRMSE) and to be comparable to a full count reconstruction, suppressing noise and recovering resolution without introducing ringing artefacts. Expand
Convolutional neural networks for improving image quality with noisy PET data
Significant improvements were found for CNN-denoising for very noisy images, and to some degree for all noise levels, but limited benefit for detection performance for images at the count levels routinely encountered in the clinic is offered. Expand
PET Image Deblurring and Super-Resolution With an MR-Based Joint Entropy Prior
An image deblurring and super-resolution framework for PET using anatomical guidance provided by high-resolution magnetic resonance (MR) images is presented, relying on image-domain postprocessing of already-reconstructed PET images by means of spatially variant deconvolution stabilized by an MR-based joint entropy penalty function. Expand
Denoising of PET images by combining wavelets and curvelets for improved preservation of resolution and quantitation
A strategy combining the complementary wavelet and curvelet transforms to address the issue of resolution loss associated with standard denoising and could become an alternative solution to filters currently used after image reconstruction in clinical systems such as the Gaussian filter. Expand
PET image super-resolution using generative adversarial networks
This paper presents a self-supervised SR technique for PET based on dual generative adversarial networks (GANs), which precludes the need for paired training data, ensuring wider applicability and adoptability and demonstrates that SSSR is promising in terms of image quality, peak signal-to-noise ratio, structural similarity index, contrast- to-noISE ratio, and an additional no-reference metric developed specifically for SR image quality assessment. Expand