Artificial Intelligence-Based Image Enhancement in PET Imaging : Noise Reduction and Resolution Enhancement - 16/09/21

Doi : 10.1016/j.cpet.2021.06.005

Juan Liu, PhD ^a,^{^{1
Equal contribution.}}, Masoud Malekzadeh, MS ^b,^{^{1
Equal contribution.}}, Niloufar Mirian, MSc ^a, Tzu-An Song, MS ^b, Chi Liu, PhD ^a,^⁎ , Joyita Dutta, PhD ^b,^c,^⁎
^a Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA
^b Department of Electrical and Computer Engineering, University of Massachusetts Lowell, 1 University Avenue, Ball 301, Lowell, MA 01854, USA
^c Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA

^∗Corresponding authors.

Resumen

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 highlight emerging areas in this field that are quickly gaining popularity, identify barriers to large-scale adoption of artificial intelligence models for PET image enhancement, and discuss future directions.

El texto completo de este artículo está disponible en PDF.

Keywords : PET, Artificial intelligence, Deep learning, Denoising, Deblurring, Super-resolution

Esquema

Key points

Introduction

Summary of existing methods

Supervised Learning Models and Network Architectures

Unsupervised, Weakly Supervised, and Self-Supervised Learning Models and Network Architectures

Evaluation Metrics

Loss Functions

Emerging approaches and novel applications

Transfer Learning

Federated Learning

Data Harmonization

Reinforcement Learning

Interpretability

Summary

Exportación

Vol 16 - N° 4

P. 553-576 - octobre 2021 Regresar al número

Artículo precedente

Artificial Intelligence–Based Data Corrections for Attenuation and Scatter in Position Emission Tomography and Single-Photon Emission Computed Tomography
Alan B. McMillan, Tyler J. Bradshaw

| Artículo siguiente

Toward High-Throughput Artificial Intelligence-Based Segmentation in Oncological PET Imaging
Fereshteh Yousefirizi, Abhinav K. Jha, Julia Brosch-Lenz, Babak Saboury, Arman Rahmim

Bienvenido a EM-consulte, la referencia de los profesionales de la salud.
El acceso al texto completo de este artículo requiere una suscripción.

¿Ya suscrito a @@106933@@ revista ?

conectar o crear una cuenta

Artificial Intelligence-Based Image Enhancement in PET Imaging : Noise Reduction and Resolution Enhancement - 16/09/21

Resumen

Esquema

Exportación citas

Fichero

Contenido

Mi cuenta

Aide & support

Declaración CNIL