Cross noise level PET denoising with continuous adversarial domain generalization

作者：Xiaofeng Liu, Samira Vafay Eslahi, Thibault Marin, Amal Tiss, Yanis Chemli, Yongsong Huang, Keith A. Johnson, Georges El Fakhri, Jinsong Ouyang · 发表于：Physics in Medicine and Biology · 年份：2024 · DOI：10.1088/1361-6560/ad341a · 被引用次数：8 · 研究领域：Medical Imaging Techniques and Applications、Image and Signal Denoising Methods、Cell Image Analysis Techniques

Abstract Objective. Performing positron emission tomography (PET) denoising within the image space proves effective in reducing the variance in PET images. In recent years, deep learning has demonstrated superior denoising performance, but models trained on a specific noise level typically fail to generalize well on different noise levels, due to inherent distribution shifts between inputs. The distribution shift usually results in bias in the denoised images. Our goal is to tackle such a problem using a domain generalization technique. Approach. We propose to utilize the domain generalization technique with a novel feature space continuous discriminator (CD) for adversarial training, using the fraction of events as a continuous domain label. The core idea is to enforce the extraction of noise-level invariant features. Thus minimizing the distribution divergence of latent feature representation for different continuous noise levels, and making the model general for arbitrary noise levels. We created three sets of 10%, 13%–22% (uniformly randomly selected), or 25% fractions of events from 97 18 F-MK6240 tau PET studies of 60 subjects. For each set, we generated 20 noise realizations. Training, validation, and testing were implemented using 1400, 120, and 420 pairs of 3D image volumes from the same or different sets. We used 3D UNet as the baseline and implemented CD to the continuous noise level training data of 13%–22% set. Main results. The proposed CD improves the denoising...