Summary: A novel AI approach accurately detects six types of cancer in whole-body PET/CT scans, quantifies tumor burden, and helps predict patient outcomes, according to research presented at the 2024 Society of Nuclear Medicine and Molecular Imaging Annual Meeting.

Key Takeaways:

  1. The novel AI approach can accurately detect six types of cancer in whole-body PET/CT scans, aiding in the assessment of patient risk, prediction of treatment response, and estimation of survival.
  2. Researchers addressed the limitations of current AI models by developing a deep transfer learning approach for fully automated tumor segmentation and prognosis, analyzing data from over a thousand PET/CT scans of various cancer types.
  3. The AI tool not only improves cancer prognosis and patient outcomes by identifying predictive biomarkers and characterizing tumor subtypes but also holds potential for enhancing early detection, treatment, and management of advanced-stage diseases.

———————————————————————————————————————————————————————

A novel AI approach can accurately detect six types of cancer in whole-body PET/CT scans, according to research presented at the 2024 Society of Nuclear Medicine and Molecular Imaging Annual Meeting. By automatically quantifying tumor burden, this tool helps assess patient risk, predict treatment response, and estimate survival.

Enhancing Early Cancer Treatment

“Automatic detection and characterization of cancer are important clinical needs to enable early treatment,” says Kevin H. Leung, PhD, research associate at Johns Hopkins University School of Medicine in Baltimore. “Most AI models that aim to detect cancer are built on small to moderately sized datasets that usually encompass a single malignancy and/or radiotracer. This represents a critical bottleneck in the current training and evaluation paradigm for AI applications in medical imaging and radiology.”

To address this issue, researchers developed a deep transfer learning approach (a type of AI) for fully automated, whole-body tumor segmentation and prognosis on PET/CT scans. Data from 611 FDG PET/CT scans of patients with lung cancer, melanoma, lymphoma, head and neck cancer, and breast cancer, as well as 408 PSMA PET/CT scans of prostate cancer patients were analyzed in the study.

Identifying Early Cancer Biomarkers

The AI approach automatically extracted radiomic features and whole-body imaging measures from the predicted tumor segmentations to quantify molecular tumor burden and uptake across all cancer types. Quantitative features and imaging measures were used to build predictive models to demonstrate prognostic value for risk stratification, survival estimation, and prediction of treatment response in patients with cancer.

“In addition to performing cancer prognosis, the approach provides a framework that will help improve patient outcomes and survival by identifying robust predictive biomarkers, characterizing tumor subtypes, and enabling the early detection and treatment of cancer,” says Leung. “The approach may also assist in the early management of patients with advanced, end-stage disease by identifying appropriate treatment regimens and predicting response to therapies, such as radiopharmaceutical therapy.”

AI to Revolutionize Cancer Imaging

Leung notes that in the future generalizable, fully automated AI tools will play a major role in imaging centers by assisting physicians in interpreting PET/CT scans of patients with cancer. The deep learning approach may also lead to the discovery of important molecular insights about the underlying biological processes that may be currently understudied in large-scale patient populations.