Artificial intelligence for detecting small FDG-positive lung nodules in digital PET/CT

The authors of this study aimed to determine the diagnostic performance of a deep learning algorithm for the automated detection of small 18F-FDG-avid pulmonary nodules in positron emission tomography (PET) scans. Their findings suggest that these machine learning algorithms may be able to aid in the detection of small 18F-FDG-avid pulmonary nodules in clinical PET/CT scans, with artificial intelligence (AI) performing significantly better on images with block sequential regularized expectation maximization (BSREM) than ordered subset expectation maximization (OSEM).

Key points

• The diagnostic value of deep learning for detecting small lung nodules (≤ 2 cm) in PET images using BSREM and OSEM reconstruction was assessed.
• BSREM yields higher SUV max of small pulmonary nodules as compared to OSEM reconstruction.
• The use of BSREM translates into a higher detectability of small pulmonary nodules in PET images as assessed with artificial intelligence.

Article: Artificial intelligence for detecting small FDG-positive lung nodules in digital PET/CT: impact of image reconstructions on diagnostic performance

Authors: Moritz Schwyzer, Katharina Martini, Dominik C. Benz, Irene A. Burger, Daniela A. Ferraro, Ken Kudura, Valerie Treyer, Gustav K. von Schulthess, Philipp A. Kaufmann, Martin W. Huellner & Michael Messerli

Written by

European Radiology