Kevin L. Berger, MD
Radiologist
Medical Imaging Network / RadNet
Recently, deep convolutional neural networks (DCNNs) have emerged as a promising approach for PET image denoising. In this study, we performed a clinical evaluation of Advanced intelligent Clear-IQ Engine (AiCE-i), a second-generation DCNN-based deep learning reconstruction method for PET developed by Canon Medical. AiCE-i provides clinicians with the flexibility to select one of three levels that best matches their preferred balance between image noise and image sharpness while maintaining high overall image quality. The three available levels, Smooth, Standard, and Sharp, correspond to three independently pre-trained neural networks. Clinical PET datasets acquired on the Cartesion Prime SP PET/CT (Canon Medical) system were reconstructed using both the standard clinical reconstruction method, ordered-subset expectation maximization (OSEM) with point spread function (PSF) modeling and Gaussian post-filtering, and the three levels of AiCE-i. Qualitative image assessment and quantitative performance analyses were performed, and the results of the clinical evaluation are presented herein.
Timothy McCue, MD
Radiologist-in-Chief
Montana Imaging Center
This talk explores real-world clinical applications of AI in musculoskeletal MRI, highlighting deep-learning reconstructions with AiCE and PIQE to improve image quality while reducing scan time, and Auto Scan Assist to streamline acquisition and optimize workflow efficiency. Attendees will gain practical insights into Canon’s solution integrating AI seamlessly from image acquisition to clinical impact.
Dheeraj Gopireddy, MD, MPH, MBA
Professor, Chair
UF Health Jacksonville
AI is reshaping CT imaging by enhancing image quality, streamlining workflows, and improving diagnostic performance. The session will discuss how integrated AI solutions deliver meaningful advances in productivity, image quality, and patient care across a broad range of CT applications. This presentation highlights AI-enabled imaging ecosystem, including advanced workflows, AI reconstructions and AI motion-compensation technologies. Through clinical examples, attendees will learn how these innovations impact patient care, departmental operations, and support clinical decision-making.