Deep learning-based positron emission tomography (PET) image denoising offers the potential to reduce radiation exposure and scanning time by transforming low-count images into high-count equivalents. However, existing methods typically blur crucial details, leading to inaccurate lesion quantification. This paper proposes a lesion-perceived and quantification-consistent modulation (LeqMod) strategy for enhanced PET image denoising, via employing downstream lesion quantification analysis as auxiliary tools. The LeqMod is a plug-and-play design adaptable to a wide range of model architectures, modulating the sampling and optimization procedures of model training without adding any computational burden to the inference phase. Specifically, the LeqMod consists of two components, the lesion-perceived modulation (LeMod) and the multiscale quantification-consistent modulation (QuMod). The LeMod enhances lesion contrast and visibility by allocating higher sampling weights and stricter loss criteria to lesion-present samples determined by an auxiliary segmentation network than lesion-absent ones. The QuMod further emphasizes quantification accuracy for both the mean and maximum standardized uptake value ( ${\mathrm {SUV}}_{{\textit {mean}}}$ and ${\mathrm {SUV}}_{{\textit {max}}}$ ) across multiscale sub-regions throughout the entire image, thereby reducing biases of denoised results relative to high-count references. Experiments conducted on large PET datasets from multiple centers and vendors, and varying noise levels demonstrated the LeqMod efficacy across various denoising frameworks. Compared to frameworks without LeqMod, the integration of LeqMod reduces the lesion ${\mathrm {SUV}}_{{\textit {max}}}$ bias by 5.92% on average and increases the peak signal-to-noise ratio (PSNR) by 0.36 on average, when denoising images across participating sites. (Code is available at https://github.com/mhxiaaa/LeqMod_PET_denoising).

Positron Emission Tomography (PET) is an important clinical imaging tool but inevitably introduces radiation exposure to patients and healthcare providers. Reducing the tracer injection dose and eliminating the CT acquisition for attenuation correction can reduce the overall radiation dose, but often results in PET with high noise and bias. Thus, it is desirable to develop 3D methods to translate the non-attenuation-corrected low-dose PET (NAC-LDPET) into attenuation-corrected standard-dose PET (AC-SDPET). Recently, diffusion models have emerged as a new state-of-the-art deep learning method for image-to-image translation, better than traditional CNN-based methods. However, due to the high computation cost and memory burden, it is largely limited to 2D applications. To address these challenges, we developed a novel 2.5D Multi-view Averaging Diffusion Model (MADM) for 3D image-to-image translation with application on NAC-LDPET to AC-SDPET translation. Specifically, MADM employs separate diffusion models for axial, coronal, and sagittal views, whose outputs are averaged in each sampling step to ensure the 3D generation quality from multiple views. To accelerate the 3D sampling process, we also proposed a strategy to use the CNN-based 3D generation as a prior for the diffusion model. Our experimental results on human patient studies suggested that MADM can generate high-quality 3D translation images, outperforming previous CNN-based and Diffusion-based baseline methods. The code is available at https://github.com/tianqic/MADM.

Low-dose PET offers a valuable means of minimizing radiation exposure in PET imaging. However, the prevalent practice of employing additional CT scans for generating attenuation maps ( -map) for PET attenuation correction significantly elevates radiation doses. To address this concern and further mitigate radiation exposure in low-dose PET exams, we propose an innovative Population-prior-aided Over-Under-Representation Network (POUR-Net) that aims for high-quality attenuation map generation from low-dose PET. First, POUR-Net incorporates an Over-Under-Representation Network (OUR-Net) to facilitate efficient feature extraction, encompassing both low-resolution abstracted and fine-detail features, for assisting deep generation on the full-resolution level. Second, complementing OUR-Net, a population prior generation machine (PPGM) utilizing a comprehensive CT-derived -map dataset, provides additional prior information to aid OUR-Net generation. The integration of OUR-Net and PPGM within a cascade framework enables iterative refinement of -map generation, resulting in the production of high-quality -maps. Experimental results underscore the effectiveness of POUR-Net, showing it as a promising solution for accurate CT-free low-count PET attenuation correction, which also surpasses the performance of previous baseline methods.

Multimodal analysis of placental ultrasound (US) and microflow imaging (MFI) could greatly aid in the early diagnosis and interventional treatment of placental insufficiency (PI), ensuring a normal pregnancy. Existing multimodal analysis methods have weaknesses in multimodal feature representation and modal knowledge definitions and fail on incomplete datasets with unpaired multimodal samples. To address these challenges and efficiently leverage the incomplete multimodal dataset for accurate PI diagnosis, we propose a novel graph-based manifold regularization learning (MRL) framework named GMRLNet. It takes US and MFI images as input and exploits their modality-shared and modality-specific information for optimal multimodal feature representation. Specifically, a graph convolutional-based shared and specific transfer network (GSSTN) is designed to explore intra-modal feature associations, thus decoupling each modal input into interpretable shared and specific spaces. For unimodal knowledge definitions, graph-based manifold knowledge is introduced to describe the sample-level feature representation, local inter-sample relations, and global data distribution of each modality. Then, an MRL paradigm is designed for inter-modal manifold knowledge transfer to obtain effective cross-modal feature representations. Furthermore, MRL transfers the knowledge between both paired and unpaired data for robust learning on incomplete datasets. Experiments were conducted on two clinical datasets to validate the PI classification performance and generalization of GMRLNet. State-of-the-art comparisons show the higher accuracy of GMRLNet on incomplete datasets. Our method achieves 0.913 AUC and 0.904 balanced accuracy (bACC) for paired US and MFI images, as well as 0.906 AUC and 0.888 bACC for unimodal US images, illustrating its application potential in PI CAD systems.

3D coronary artery reconstruction (3D-CAR) in intravascular ultrasound (IVUS) sequences allows quantitative analyses of vessel properties. Existing methods treat two main tasks of the 3D-CAR separately, including the cardiac phase retrieval (CPR) and the membrane border extraction (MBE). They ignore the CPR-MBE connection that could achieve mutual promotions to both tasks. In this paper, we pioneer to achieve one-step 3D-CAR via a collaborative constraint generative adversarial network (GAN) named the AwCPM-Net. The AwCPM-Net consists of a dual-task collaborative generator and a dual-task constraint discriminator. The generator combines a self-supervised CPR branch with a semi-supervised MBE branch via a warming-up connection. The discriminator promotes dual-branch predictions simultaneously. The CPR branch requires no annotations and outputs inter-frame deformation fields used for identifying cardiac phases. Deformation fields are additionally constrained by the MBE branch and the discriminator. The MBE branch predicts membrane boundaries for each frame. Two aspects assist the semi-supervised segmentation: annotation augmentation by deformation fields of the CPR branch; information exploitation on unlabeled images enabled by GAN design. Trained and tested on an IVUS dataset acquired from atherosclerosis patients, the AwCPM-Net is effective in both CPR and MBE tasks, superior to state-of-the-art IVUS CPR or MBE methods. Hence, the AwCPM-Net reconstructs reliable 3D artery anatomy in the IVUS modality.

Supervised convolutional neural networks (CNNs) have demonstrated state-of-art performance in medical image segmentation tasks. However, the performance of a well-trained CNN on an independent dataset (e.g., different vendors, sequences) relies strongly on the distribution similarity, and may drop unexpectedly in case of distribution shift. To obtain a large amount of annotation from each new dataset for re-training the CNN is expensive and impractical. Adaptation algorithms to improve the CNN generalizability from source domain to target domain has significant practical value. In this work, we propose a highly efficient end-to-end domain adaptation approach, with left ventricle segmentation from cine MRI sequences as an example. We propose to perform domain adaptation in the output space where different domains share the strongest similarities. The core of this algorithm is a flexible and light output adaption module based on adversarial learning. Moreover, Canny edge detector is introduced to enhance model's attention to edges during adversarial learning. Comparative experiments were carried out using images from three major MR vendors (Philips, Siemens, and GE) as three domains. Our results demonstrated that the proposed method substantially improved the generalization of the trained CNN model from one vendor to other vendors without any additional annotation. Moreover, the ablation study proved that introducing Canny edge detector further refined the edge detection in segmentation. The proposed adaption is generic can be extended to other medical image segmentation problems.