Transformers have revolutionized medical image restoration, but the quadratic complexity still poses limitations for their application to high-resolution medical images. The recent advent of the Receptance Weighted Key Value (RWKV) model in the natural language processing field has attracted much attention due to its ability to process long sequences efficiently. To leverage its advanced design, we propose Restore-RWKV, the first RWKV-based model for medical image restoration. Since the original RWKV model is designed for 1D sequences, we make two necessary modifications for modeling spatial relations in 2D medical images. First, we present a recurrent WKV (Re-WKV) attention mechanism that captures global dependencies with linear computational complexity. Re-WKV incorporates bidirectional attention as basic for a global receptive field and recurrent attention to effectively model 2D dependencies from various scan directions. Second, we develop an omnidirectional token shift (Omni-Shift) layer that enhances local dependencies by shifting tokens from all directions and across a wide context range. These adaptations make the proposed Restore-RWKV an efficient and effective model for medical image restoration. Even a lightweight variant of Restore-RWKV, with only 1.16 million parameters, achieves comparable or even superior results compared to existing state-of-the-art (SOTA) methods. Extensive experiments demonstrate that the resulting Restore-RWKV achieves SOTA performance across a range of medical image restoration tasks, including PET image synthesis, CT image denoising, MRI image super-resolution, and all-in-one medical image restoration.

Positron emission tomography (PET) image synthesis is a highly ill-posed problem that requires auxiliary priors to 1) alleviate the loss of high-quality (HQ) information in low-quality (LQ) inputs, and 2) impose additional constraints to reduce mapping uncertainty. However, existing auxiliary priors in PET image synthesis often provide inadequate guidance due to inaccurate prior information or limited prior expressiveness. To overcome the aforementioned limitations, the vector-quantized (VQ) codebook prior is employed as a promising solution. By learning discrete latent feature representations of HQ images through deep models, the VQ codebook prior encompasses accurate HQ information and possesses great expressiveness. Building upon this, we propose a novel two-stage framework, VQPET, that introduces the VQ codebook prior for PET image synthesis. In the first stage, it pretrains a VQGAN on an additional large-scale HQ PET dataset, encoding intrinsic HQ features as code items in the VQ codebook. The VQ codebook prior is thus derived from the high-level features obtained from the pretrained VQGAN and serves as an additional constraint for downstream synthesis. In the second stage, it develops a codebook-prior-guided network (CPGNet) that effectively exploits the VQ codebook prior to produce realistic outputs. Specifically, CPGNet progressively incorporates the VQ codebook prior at multiple decoding levels, providing reliable guidance for HQ synthesis. Compared to previous works, VQPET innovatively leverages additional large-scale HQ datasets to transfer pretrained prior knowledge for enhanced synthesis and functions as a general framework applicable to any encoder-decoder network. Extensive experiments demonstrate the substantial effect and robust generalizability of VQPET.

Potential radioactive hazards in full-dose positron emission tomography (PET) imaging remain a concern, whereas the quality of low-dose images is never desirable for clinical use. So it is of great interest to translate low-dose PET images into full-dose. Previous studies based on deep learning methods usually directly extract hierarchical features for reconstruction. We notice that the importance of each feature is different and they should be weighted dissimilarly so that tiny information can be captured by the neural network. Furthermore, the synthesis on some regions of interest is important in some applications. Here we propose a novel segmentation guided style-based generative adversarial network (SGSGAN) for PET synthesis. (1) We put forward a style-based generator employing style modulation, which specifically controls the hierarchical features in the translation process, to generate images with more realistic textures. (2) We adopt a task-driven strategy that couples a segmentation task with a generative adversarial network (GAN) framework to improve the translation performance. Extensive experiments show the superiority of our overall framework in PET synthesis, especially on those regions of interest.