What’s New in PET/CT

AI in PET/CT: Detecting Multiple Cancers with Whole-Body Imaging

Research presented at the 2024 Society of Nuclear Medicine and Molecular Imaging (SNMMI) Annual Meeting explored AI-assisted detection of six cancer types using PET/CT images. The findings describe a research setting and do not establish that the tool is available on SMS systems or suitable for every clinical setting.

Why AI is needed in PET/CT cancer detection

Traditional AI cancer models have been limited by small datasets and narrow clinical focus, typically detecting just one malignancy type at a time, using a single radiotracer. According to Kevin H. Leung, PhD, research associate at Johns Hopkins University School of Medicine, this presents a serious limitation:

“Automatic detection and characterization of cancer are important clinical needs to enable early treatment.”

To overcome these boundaries, researchers developed a deep transfer learning model trained on whole-body PET/CT scans. The goal was to deliver fully automated tumor segmentation and outcome prediction across a wide range of cancer types.

Read the full study in the Journal of Nuclear Medicine.

How the AI model works with PET/CT imaging

The study analyzed two large datasets:

    • 611 FDG PET/CT scans from patients with:
    • Lung cancer
    • Melanoma
    • Lymphoma
    • Head and neck cancer
    • Breast cancer
    • 408 PSMA PET/CT scans focused on prostate cancer

The AI system extracted radiomic features and quantified tumor burden, enabling it to:

    • Stratify patients by risk level
    • Predict treatment response
    • Estimate survival rates based on tumor activity and spread

These insights move PET/CT from being a diagnostic tool to a powerful predictive imaging platform.

If you’re expanding oncology services, our Mobile PET/CT Solutions offer flexible deployment without fixed infrastructure costs.

Improving outcomes through AI-enhanced imaging

AI in PET/CT now extends far beyond simple detection. The technology supports personalized care by identifying tumor subtypes and mapping the entire disease landscape in a single scan. Notable benefits include:

    • Predictive Biomarkers, Identify high-risk patients and tailor treatment
    • Earlier Detection, Improve outcomes through timely intervention
    • Therapy Optimization, Support late-stage care with accurate radiopharmaceutical dosing

Dr. Leung adds:

“This approach provides a framework that will help improve patient outcomes and survival by identifying robust predictive biomarkers, characterizing tumor subtypes, and enabling early cancer detection.”

What’s next for AI in PET/CT imaging?

The integration of AI into PET/CT workflows promises a new era of diagnostic precision and efficiency. Looking ahead, these tools will help:

  • Automate and enhance scan interpretation
  • Uncover molecular insights into complex disease pathways
  • Improve imaging center efficiency and resource allocation

For imaging centers seeking next-generation diagnostics, our Mobile Imaging Solutions bring current-generation PET/CT directly to your facility.

Stay ahead in PET/CT innovation

Shared Medical Services continues to lead the industry in delivering mobile PET/CT systems designed to support high-precision cancer imaging. As AI transforms the diagnostic landscape, we remain committed to helping providers adapt, scale, and grow, without capital barriers.

Media Contact:
Blake Kenney
Senior Marketing Specialist
Shared Medical Services, Inc.
Phone: (608) 910-1332
Email: contactsms@sharedmed.com

We deliver what’s next.

For more than 45 years, Shared Medical Services has been a trusted partner in mobile and interim imaging, giving hospitals, clinics, and health systems access to CT, MRI, PET/CT, and Cardiac PET/CT. From routed and parked solutions to flexible interim rentals, we bring the expertise, reliability, and service that keep imaging running.