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).

Deep learning has been extensively applied in medical image reconstruction, where Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) represent the predominant paradigms, each possessing distinct advantages and inherent limitations: CNNs exhibit linear complexity with local sensitivity, whereas ViTs demonstrate quadratic complexity with global sensitivity. The emerging Mamba has shown superiority in learning visual representation, which combines the advantages of linear scalability and global sensitivity. In this study, we introduce MambaMIR, an Arbitrary-Masked Mamba-based model with wavelet decomposition for joint medical image reconstruction and uncertainty estimation. A novel Arbitrary Scan Masking (ASM) mechanism "masks out" redundant information to introduce randomness for further uncertainty estimation. Compared to the commonly used Monte Carlo (MC) dropout, our proposed MC-ASM provides an uncertainty map without the need for hyperparameter tuning and mitigates the performance drop typically observed when applying dropout to low-level tasks. For further texture preservation and better perceptual quality, we employ the wavelet transformation into MambaMIR and explore its variant based on the Generative Adversarial Network, namely MambaMIR-GAN. Comprehensive experiments have been conducted for multiple representative medical image reconstruction tasks, demonstrating that the proposed MambaMIR and MambaMIR-GAN outperform other baseline and state-of-the-art methods in different reconstruction tasks, where MambaMIR achieves the best reconstruction fidelity and MambaMIR-GAN has the best perceptual quality. In addition, our MC-ASM provides uncertainty maps as an additional tool for clinicians, while mitigating the typical performance drop caused by the commonly used dropout.

Anomaly detection (AD) in medical applications is a promising field, offering a cost-effective alternative to labor-intensive abnormal data collection and labeling. However, the success of feature reconstruction-based methods in AD is often hindered by two critical factors: the domain gap of pre-trained encoders and the exploration of decoder potential. The EA2D method we propose overcomes these challenges, paving the way for more effective AD in medical imaging. In this paper, we present encoder-attention-2decoder (EA2D), a novel method tailored for medical AD. Firstly, EA2D is optimized through two tasks: a primary feature reconstruction task between the encoder and decoder, which detects anomalies based on reconstruction errors, and an auxiliary transformation-consistency contrastive learning task that explicitly optimizes the encoder to reduce the domain gap between natural images and medical images. Furthermore, EA2D intensely exploits the decoder's capabilities to improve AD performance. We introduce a self-attention skip connection to augment the reconstruction quality of normal cases, thereby magnifying the distinction between normal and abnormal samples. Additionally, we propose using dual decoders to reconstruct dual views of an image, leveraging diverse perspectives while mitigating the over-reconstruction issue of anomalies in AD. Extensive experiments across four medical image modalities demonstrates the superiority of our EA2D in various medical scenarios. Our method's code will be released at https://github.com/TumCCC/E2AD.

Positron Emission Tomography (PET)-based molecular imaging represents one of the most powerful tools to measure tumor biology variations and tumor microenvironment heterogeneity, which are major factors impacting cancer treatment failure. In this respect, Spatiotemporal Distribution Models based on Partial Differential Equations can provide an informative picture of in vivo cancer biology, ultimately improving clinical decision-making. In fact, PET tracer diffusion simulations can be used to optimize imaging protocols and interpret PET cancer data for staging purposes, enabling an accurate assessment of the tumor burden and thus informing optimal therapeutic strategies. In this study, we propose a spatiotemporal convection-diffusion model to simulate F18-fluorothymidine ($[^{18}$F]FLT) uptake in pancreatic ductal adenocarcinoma (PDAC) tissues. We develop a tissue-aware diffusivity map to generate a more realistic estimation of the tracer concentration. We correlate the dynamic spatial estimates of the $[^{18}$F] FLT uptake with the tumor proliferation map enabling the investigation of the relationship between the dynamic changes in $[^{18}$F] FLT uptake and the rate of cellular proliferation in PDAC tissues. These results could serve as guidance for optimizing the imaging process and inform the research on the effectiveness of novel tracers.

Deep learning based approaches have achieved great success on the automatic cardiac image segmentation task. However, the achieved segmentation performance remains limited due to the significant difference across image domains, which is referred to as domain shift. Unsupervised domain adaptation (UDA), as a promising method to mitigate this effect, trains a model to reduce the domain discrepancy between the source (with labels) and the target (without labels) domains in a common latent feature space. In this work, we propose a novel framework, named Partial Unbalanced Feature Transport (PUFT), for cross-modality cardiac image segmentation. Our model facilities UDA leveraging two Continuous Normalizing Flow-based Variational Auto-Encoders (CNF-VAE) and a Partial Unbalanced Optimal Transport (PUOT) strategy. Instead of directly using VAE for UDA in previous works where the latent features from both domains are approximated by a parameterized variational form, we introduce continuous normalizing flows (CNF) into the extended VAE to estimate the probabilistic posterior and alleviate the inference bias. To remove the remaining domain shift, PUOT exploits the label information in the source domain to constrain the OT plan and extracts structural information of both domains, which are often neglected in classical OT for UDA. We evaluate our proposed model on two cardiac datasets and an abdominal dataset. The experimental results demonstrate that PUFT achieves superior performance compared with state-of-the-art segmentation methods for most structural segmentation.

The non-invasive quantification of the cerebral metabolic rate for glucose (CMRGlc) and the characterization of cerebral metabolism in the cerebrovascular territories are helpful in understanding ischemic cerebrovascular disease (ICVD). Firstly, we investigated a non-invasive quantification approach based on an image-derived input function (IDIF) in ICVD. Second, we studied the metabolic changes in CMRGlc after surgical intervention. We evaluated the hypothesis that the IDIF method based on the unilateral internal carotid artery could address challenges in ICVD quantification. The CMRGlc and standardized uptake value ratio (SUVR) were used to measure glucose metabolism activity. Healthy controls showed no significant differences in CMRGlc values between bilateral and unilateral IDIF measurements (intraclass correlation coefficient [ICC]: 0.91-0.98). Patients with ICVD showed significantly increased CMRGlc values after surgical intervention for all territories (percentage changes: 7.4%-22.5%). In contrast, SUVR showed minor differences between postoperative and preoperative patients, indicating that it was a poor biomarker for the diagnosis of ICVD. A significant association between CMRGlc and the National Institutes of Health Stroke Scale (NIHSS) scores was observed (r=-0.54). Our findings suggested that IDIF could be a valuable tool for CMRGlc quantification in patients with ICVD and may advance personalized precision interventions.

Extranodal natural killer/T cell lymphoma (ENKL), nasal type is a kind of rare disease with a low survival rate that primarily affects Asian and South American populations. Segmentation of ENKL lesions is crucial for clinical decision support and treatment planning. This paper is the first study on computer-aided diagnosis systems for the ENKL segmentation problem. We propose an automatic, coarse-to-fine approach for ENKL segmentation using adversarial networks. In the coarse stage, we extract the region of interest bounding the lesions utilizing a segmentation neural network. In the fine stage, we use an adversarial segmentation network and further introduce a multi-scale L1loss function to drive the network to learn both global and local features. The generator and discriminator are alternately trained by backpropagation in an adversarial fashion in a min-max game. Furthermore, we present the first exploration of zone-based uncertainty estimates based on Monte Carlo dropout technique in the context of deep networks for medical image segmentation. Specifically, we propose the uncertainty criteria based on the lesion and the background, and then linearly normalize them to a specific interval. This is not only the crucial criterion for evaluating the superiority of the algorithm, but also permits subsequent optimization by engineers and revision by clinicians after quantitatively understanding the main source of uncertainty from the background or the lesion zone. Experimental results demonstrate that the proposed method is more effective and lesion-zone stable than state-of-the-art deep-learning based segmentation model.

The separation of multiple PET tracers within an overlapping scan based on intrinsic differences of tracer pharmacokinetics is challenging, due to limited signal-to-noise ratio (SNR) of PET measurements and high complexity of fitting models. In this study, we developed a direct parametric image reconstruction (DPIR) method for estimating kinetic parameters and recovering single tracer information from rapid multi-tracer PET measurements. This is achieved by integrating a multi-tracer model in a reduced parameter space (RPS) into dynamic image reconstruction. This new RPS model is reformulated from an existing multi-tracer model and contains fewer parameters for kinetic fitting. Ordered-subsets expectation-maximization (OSEM) was employed to approximate log-likelihood function with respect to kinetic parameters. To incorporate the multi-tracer model, an iterative weighted nonlinear least square (WNLS) method was employed. The proposed multi-tracer DPIR (MT-DPIR) algorithm was evaluated on dual-tracer PET simulations ([18F]FDG and [11C]MET) as well as on preclinical PET measurements ([18F]FLT and [18F]FDG). The performance of the proposed algorithm was compared to the indirect parameter estimation method with the original dual-tracer model. The respective contributions of the RPS technique and the DPIR method to the performance of the new algorithm were analyzed in detail. For the preclinical evaluation, the tracer separation results were compared with single [18F]FDG scans of the same subjects measured two days before the dual-tracer scan. The results of the simulation and preclinical studies demonstrate that the proposed MT-DPIR method can improve the separation of multiple tracers for PET image quantification and kinetic parameter estimations.

Modern experimental and computational fluid mechanics are increasingly concerned with the structure nature of fluid motion. Recent research has highlighted the analysis of one transport structure which is called Lagrangian coherent structure. However, the quantity nature of the flow transport is still unclear. In this paper, we focus on the transport characteristics of physical quantities and propose an approach to visualize the finite-time transport structure of quantity advection. This is similar to an integral convolution over a scalar field along path-lines of a flow field. Applied to a well-chosen set of physical quantity fields this yields structures giving insights into the dynamical processes of the underlying flow. We demonstrate our approach on a number of test data sets.

This paper presents an approach to extracting a path line oriented topological segmentation for periodic 2D timedependent vector fields. Topological methods aiming in capturing the asymptotic behavior of path lines rarely exist because path lines are usually only defined over a fixed time-interval, making statements about their asymptotic behavior impossible. For the data class of periodic vector fields, this restriction does not apply any more. Our approach detects critical path lines as well as basins from which the path lines converge to the critical ones. We demonstrate our approach on a number of test data sets.

This paper presents an approach to extracting and classifying higher order critical points of 3D vector fields. To do so, we place a closed convex surface s around the area of interest. Then we show that the complete 3D classification of a critical point into areas of different flow behavior is equivalent to extracting the topological skeleton of an appropriate 2D vector field on s, if each critical point is equipped with an additional bit of information. Out of this skeleton, we create an icon which replaces the complete topological structure inside s for the visualization. We apply our method to find a simplified visual representation of clusters of critical points, leading to expressive visualizations of topologically complex 3D vector fields.