Deep learning has demonstrated remarkable efficacy in reconstructing low-count PET (Positron EmissionTomography) images, attracting considerable attention in the medical imaging community. However, most existing deep learning approaches have not fully exploited the unique physical characteristics of PET imaging in the design of fidelity and prior regularization terms, resulting in constrained model performance and interpretability. In light of these considerations, we introduce an unrolled deep network based on maximum likelihood estimation for the Poisson distribution and a Generalized domain transformation for Sparsity learning, dubbed GS-Net. To address this complex optimization challenge, we employ the Alternating Direction Method of Multipliers (ADMM) framework, integrating a modified Expectation Maximization (EM) approach to address the primary objective and utilize the shrinkage thresholding approach to optimize the L1 norm term. Additionally, within this unrolled deep network, all hyperparameters are adaptively adjusted through end-to-end learning to eliminate the need for manual parameter tuning. Through extensive experiments on simulated patient brain datasets and real patient whole-body clinical datasets with multiple count levels, our method has demonstrated advanced performance compared to traditional non-iterative and iterative reconstruction, deep learning-based direct reconstruction, and hybrid unrolled methods, as demonstrated by qualitative and quantitative evaluations.

The learning rate is a critical hyperparameter for deep learning tasks since it determines the extent to which the model parameters are adjusted during the learning course. However, the choice of learning rates typically depends on empirical judgment, which may not result in satisfactory outcomes without intensive try-and-error experiments. In this study, we propose a novel learning rate adaptation scheme called QLABGrad. Without any user-specified hyperparameter, QLABGrad automatically determines the learning rate by optimizing the quadratic loss approximation-based (QLAB) function for a given gradient descent direction, where only one extra forward propagation is required. We theoretically prove the convergence of QLABGrad under the smooth Lipschitz condition on the loss function. Experiment results on multiple architectures, including MLP, CNN, and ResNet, on MNIST, CIFAR10, and ImageNet datasets, demonstrate that QLABGrad outperforms widely adopted schemes for deep learning.

The integration of morphological attributes extracted from histopathological images and genomic data holds significant importance in advancing tumor diagnosis, prognosis, and grading. Histopathological images are acquired through microscopic examination of tissue slices, providing valuable insights into cellular structures and pathological features. On the other hand, genomic data provides information about tumor gene expression and functionality. The fusion of these two distinct data types is crucial for gaining a more comprehensive understanding of tumor characteristics and progression. In the past, many studies relied on single-modal approaches for tumor diagnosis. However, these approaches had limitations as they were unable to fully harness the information from multiple data sources. To address these limitations, researchers have turned to multi-modal methods that concurrently leverage both histopathological images and genomic data. These methods better capture the multifaceted nature of tumors and enhance diagnostic accuracy. Nonetheless, existing multi-modal methods have, to some extent, oversimplified the extraction processes for both modalities and the fusion process. In this study, we presented a dual-branch neural network, namely SG-Fusion. Specifically, for the histopathological modality, we utilize the Swin-Transformer structure to capture both local and global features and incorporate contrastive learning to encourage the model to discern commonalities and differences in the representation space. For the genomic modality, we developed a graph convolutional network based on gene functional and expression level similarities. Additionally, our model integrates a cross-attention module to enhance information interaction and employs divergence-based regularization to enhance the model's generalization performance. Validation conducted on glioma datasets from the Cancer Genome Atlas unequivocally demonstrates that our SG-Fusion model outperforms both single-modal methods and existing multi-modal approaches in both survival analysis and tumor grading.

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 concatenating two extracted features from these two modalities as an intermediate fusion method, the proposed cross-modal feature fusion module (CM-FFM) adopts cross-attention at multiple feature levels and greatly improves the two modalities' feature fusion procedure. Extensive experimental assessments conducted on real clinical datasets, as well as an independent clinical testing dataset, demonstrate that the proposed OIF-Net outperforms the state-of-the-art methods.

The axial field of view (FOV) is a key factor that affects the quality of PET images. Due to hardware FOV restrictions, conventional short-axis PET scanners with FOVs of 20 to 35 cm can acquire only low-quality PET (LQ-PET) images in fast scanning times (2-3 minutes). To overcome hardware restrictions and improve PET image quality for better clinical diagnoses, several deep learning-based algorithms have been proposed. However, these approaches use simple convolution layers with residual learning and local attention, which insufficiently extract and fuse long-range contextual information. To this end, we propose a novel two-branch network architecture with swin transformer units and graph convolution operation, namely SW-GCN. The proposed SW-GCN provides additional spatial- and channel-wise flexibility to handle different types of input information flow. Specifically, considering the high computational cost of calculating self-attention weights in full-size PET images, in our designed spatial adaptive branch, we take the self-attention mechanism within each local partition window and introduce global information interactions between nonoverlapping windows by shifting operations to prevent the aforementioned problem. In addition, the convolutional network structure considers the information in each channel equally during the feature extraction process. In our designed channel adaptive branch, we use a Watts Strogatz topology structure to connect each feature map to only its most relevant features in each graph convolutional layer, substantially reducing information redundancy. Moreover, ensemble learning is adopted in our SW-GCN for mapping distinct features from the two well-designed branches to the enhanced PET images. We carried out extensive experiments on three single-bed position scans for 386 patients. The test results demonstrate that our proposed SW-GCN approach outperforms state-of-the-art methods in both quantitative and qualitative evaluations.

We characterize delay minimal power scheduling policies in energy harvesting communication systems. We consider a continuous-time system, where the delay experienced by each bit is given by the time spent by the bit in the queue waiting to be transmitted to its receiver. We first consider a single-user channel, where the transmitter has a finite-sized battery to save its harvested energy. Data arrives during the course of communication and are saved in a finite data buffer as well. We find the optimal power policy that minimizes the average delay experienced by the bits subject to energy and data causality constraints. We characterize the optimal solution in terms of Lagrange multipliers, and calculate their values in a recursive manner. We show that, different from the existing literature, the optimum transmission power is not constant between the energy and data arrival events; the transmission power starts high, decreases linearly, and potentially reaches zero between energy and data arrivals. Intuitively, untransmitted bits experience cumulative delay due to the bits to be transmitted ahead of them, and hence the reason for transmission power starting high and decreasing over time. Next, we study a multiuser version of this problem, namely, a two-user broadcast channel, and characterize the optimal transmission policies that minimize the sum delay. For this setting, we consider the case, where the transmitter has an infinite-sized battery, and that all data packets intended for the receivers are available at the beginning of the communication session. We characterize the optimal solution in terms of Lagrange multipliers, and present an iterative solution that calculates their values. Our results show that in the optimal policy, both users may not be served simultaneously all the time; there may be times, where only one of the two users is served alone. We also show that the optimal policy may have gaps in transmission in between energy arrivals, where none of the users is served, echoing the results of the single-user setting.

We consider a two-user energy harvesting broadcast channel, and characterize the delay minimal transmission policies that minimize the total delay experienced by the data packets in the system. We consider a continuous time system where the delay experienced by each bit is given by the time spent by the bit in the queue waiting to be transmitted to its receiver. We consider the case where all data packets are available at the transmitter at the beginning of the communication session. We characterize the optimal solution in terms of the Lagrange multipliers, and present an iterative algorithm that optimally calculates their values. Our results show that in the optimal policy, both users may not be served simultaneously all the time; there may be times where only the strong user or only the weak user is served alone. We also show that the optimal policy may have gaps in transmission where none of the users is served until the next energy arrival.