Related Experiment Video
Updated: Jul 10, 2025
05:41
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
Published on: February 6, 2020
9.4K
Artificial Intelligence and Deep Learning for Advancing PET Image Reconstruction: State-of-the-Art and Future
Dirk Hellwig1,2,3, Nils Constantin Hellwig1,3, Steven Boehner1,2,3
1Department of Nuclear Medicine, University Hospital Regensburg, Regensburg, Germany.
Nuklearmedizin. Nuclear Medicine
|November 23, 2023
Summary
Artificial intelligence (AI) and deep learning (DL) are revolutionizing Positron Emission Tomography (PET) image reconstruction (IR). These advanced AI methods enhance image quality, reduce artifacts, and promise improved diagnostic accuracy in clinical settings.
Area of Science:
- Nuclear Medicine
- Medical Imaging
- Artificial Intelligence
Background:
- Positron Emission Tomography (PET) is crucial for disease diagnosis and treatment monitoring.
- Conventional image reconstruction (IR) methods have limitations in PET imaging.
- PET IR can be conceptualized as an image-to-image translation task.
Conclusions:
- AI-based PET IR offers significant advantages but faces challenges like data availability and scanner compatibility.
- Rigorous validation and regulatory considerations are essential for clinical adoption.
- AI integration into routine PET protocols is foreseeable, with emerging trends like multimodal imaging.
