OIF-Net: An Optical Flow Registration-Based PET/MR Cross-Modal Interactive Fusion Network for Low-Count Brain PET Image Denoising

作者：Minghan Fu, Na Zhang, Zhenxing Huang, Chao Zhou, Xu Zhang, Jianmin Yuan, Qiang He, Yongfeng Yang, Hairong Zheng, Dong Liang, Fang‐Xiang Wu, Wei Fan, Zhanli Hu · 发表于：IEEE Transactions on Medical Imaging · 年份：2023 · DOI：10.1109/tmi.2023.3342809 · 被引用次数：24 · 研究领域：Medical Imaging Techniques and Applications、Medical Image Segmentation Techniques、Cell Image Analysis Techniques

The short frames of low-count positron emission tomography (PET) images generally cause high levels of statistical noise. Thus, improving the quality of low-count images by using image postprocessing algorithms to achieve better clinical diagnoses has attracted widespread attention in the medical imaging community. Most existing deep learning-based low-count PET image enhancement methods have achieved satisfying results, however, few of them focus on denoising low-count PET images with the magnetic resonance (MR) image modality as guidance. The prior context features contained in MR images can provide abundant and complementary information for single low-count PET image denoising, especially in ultralow-count (2.5%) cases. To this end, we propose a novel two-stream dual PET/MR cross-modal interactive fusion network with an optical flow pre-alignment module, namely, OIF-Net. Specifically, the learnable optical flow registration module enables the spatial manipulation of MR imaging inputs within the network without any extra training supervision. Registered MR images fundamentally solve the problem of feature misalignment in the multimodal fusion stage, which greatly benefits the subsequent denoising process. In addition, we design a spatial-channel feature enhancement module (SC-FEM) that considers the interactive impacts of multiple modalities and provides additional information flexibility in both the spatial and channel dimensions. Furthermore, instead of simply concatenati...