Perivascular spaces (PVSs) form a central component of the brain's waste clearance system, the glymphatic system. These structures are visible on MRIs when enlarged, and their morphology is associated with aging and neurological disease. Manual quantification of PVS is time consuming and subjective. Numerous deep learning methods for PVS segmentation have been developed for automated segmentation. However, the majority of these algorithms have been developed and evaluated on homogenous datasets and high resolution scans, perhaps limiting their applicability for the wide range of image qualities acquired in clinical and research settings. In this work we train a nnUNet, a top-performing task driven biomedical image segmentation deep learning algorithm, on a heterogenous training sample of manually segmented MRIs of a range of different qualities and resolutions from 7 different datasets acquired on 6 different scanners. These are compared to the two currently publicly available deep learning methods for 3D segmentation of PVS, evaluated on scans with a range of resolutions and qualities. The resulting model, PINGU (Perivascular space Identification Nnunet for Generalised Usage), achieved voxel and cluster level dice scores of 0.50(SD=0.15) and 0.63(0.17) in the white matter (WM), and 0.54 (0.11) and 0.66(0.17) in the basal ganglia (BG). Performance on unseen "external" sites' data was substantially lower for both PINGU (0.20-0.38 [WM, voxel], 0.29-0.58 [WM, cluster], 0.22-0.36 [BG, voxel], 0.46-0.60 [BG, cluster]) and the publicly available algorithms (0.18-0.30 [WM, voxel], 0.29-0.38 [WM cluster], 0.10-0.20 [BG, voxel], 0.15-0.37 [BG, cluster]). Nonetheless, PINGU strongly outperformed the publicly available algorithms, particularly in the BG. PINGU stands out as broad-use PVS segmentation tool, with particular strength in the BG, an area of PVS highly related to vascular disease and pathology.

Synthesizing high-quality images from low-field MRI holds significant potential. Low-field MRI is cheaper, more accessible, and safer, but suffers from low resolution and poor signal-to-noise ratio. This synthesis process can reduce reliance on costly acquisitions and expand data availability. However, synthesizing high-field MRI still suffers from a clinical fidelity gap. There is a need to preserve anatomical fidelity, enhance fine-grained structural details, and bridge domain gaps in image contrast. To address these issues, we propose a cyclic self-supervised diffusion (CSS-Diff) framework for high-field MRI synthesis from real low-field MRI data. Our core idea is to reformulate diffusion-based synthesis under a cycle-consistent constraint. It enforces anatomical preservation throughout the generative process rather than just relying on paired pixel-level supervision. The CSS-Diff framework further incorporates two novel processes. The slice-wise gap perception network aligns inter-slice inconsistencies via contrastive learning. The local structure correction network enhances local feature restoration through self-reconstruction of masked and perturbed patches. Extensive experiments on cross-field synthesis tasks demonstrate the effectiveness of our method, achieving state-of-the-art performance (e.g., $31.80~\pm ~2.70$ dB in PSNR, $0.943~\pm ~0.102$ in SSIM, and $0.0864~\pm ~0.0689$ in LPIPS). Beyond pixel-wise fidelity, our method also preserves fine-grained anatomical structures compared with the original low-field MRI (e.g., left cerebral white matter error drops from 12.1% to 2.1%, cortex from 4.2% to 3.7%). To conclude, our CSS-Diff can synthesize images that are both quantitatively reliable and anatomically consistent. The code is available at: https://github.com/ayanglab/CSS-Diff.

Remarkable progress has been achieved in the detection and segmentation of the baseline; however, for high-level visual tasks in complex scenes (e.g., dense, occlusion, scale diversity, high background noise, etc.), existing frameworks often fail to provide satisfactory performance. To further improve the object recognition ability, this article introduces a leader-based multiexpert mechanism into the detection and segmentation tasks. In this work, we first design a leader-based attention learning layer to fully integrate multilevel features from the backbone network, which can effectively obtain global semantics and assign instructions to detection experts. Then, we propose multiple feature pyramids with dual fusion paths to replace the traditional single pipeline using semantic and spatial allocators. With this strategy, we can further establish deep supervision for multiple experts during training and sufficiently utilize the multiexpert detection results from leaders' assignments during reasoning, thereby comprehensively improving the performance of the model in complex scenarios. In the experiment, we established ablation studies and performance comparisons on COCO 2017 detection and segmentation tasks. Finally, we demonstrated the model's performance in three complex application scenarios (remote sensing, autonomous driving, and industrial fields), and the results showed our advantages.

Implicit Neural Representations (INRs) have recently advanced the field of deep learning due to their ability to learn continuous representations of signals without the need for large training datasets. Although INR methods have been studied for medical image super-resolution, their adaptability to localized priors in medical images has not been extensively explored. Medical images contain rich anatomical divisions that could provide valuable local prior information to enhance the accuracy and robustness of INRs. In this work, we propose a novel framework, referred to as the Semantically Conditioned INR (SeCo-INR), that conditions an INR using local priors from a medical image, enabling accurate model fitting and interpolation capabilities to achieve super-resolution. Our framework learns a continuous representation of the semantic segmentation features of a medical image and utilizes it to derive the optimal INR for each semantic region of the image. We tested our framework using several medical imaging modalities and achieved higher quantitative scores and more realistic super-resolution outputs compared to state-of-the-art methods.

In this study, we investigate jointly learning Hyperbolic and Euclidean space representations and match the consistency for semi-supervised medical image segmentation. We argue that for complex medical volumetric data, hyperbolic spaces are beneficial to model data inductive biases. We propose an approach incorporating the two geometries to co-train a variational encoder–decoder model with a Hyperbolic probabilistic latent space and a separate variational encoder–decoder model with a Euclidean probabilistic latent space with complementary representations, thereby bridging the gap of co-training across manifolds (Co-Manifold learning) in a principled manner. To capture complementary information and hierarchical relationships, we propose a Latent Space Loss aimed at maximizing disagreement between embeddings across manifolds. Additionally, we employ adversarial learning to enhance segmentation performance by guiding the network in hyperbolic latent space using confident regions identified by the network in Euclidean space. Conversely, the network in Euclidean space is informed by hyperbolic uncertainty, creating a dual uncertainty-aware framework that enables the two spaces to collaboratively learn confident regions from each other. Our proposed method achieves competitive results on two benchmarks for semi-supervised medical image segmentation on medical scans. The code is publicly available at: https://github.com/himashi92/Co-Manifold . • A novel co-training approach based on two different geometrical spaces. • Introduces bijective functions to enforce prediction consistency. • Develops a knowledge distillation method with dual uncertainty-aware loss.

Medical image synthesis represents a critical area of research in clinical decision-making, aiming to overcome the challenges associated with acquiring multiple image modalities for an accurate clinical workflow. This approach proves beneficial in estimating an image of a desired modality from a given source modality among the most common medical imaging contrasts, such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and Positron Emission Tomography (PET). However, translating between two image modalities presents difficulties due to the complex and non-linear domain mappings. Deep learning-based generative modelling has exhibited superior performance in synthetic image contrast applications compared to conventional image synthesis methods. This survey comprehensively reviews deep learning-based medical imaging translation from 2018 to 2023 on pseudo-CT, synthetic MR, and synthetic PET. We provide an overview of synthetic contrasts in medical imaging and the most frequently employed deep learning networks for medical image synthesis. Additionally, we conduct a detailed analysis of each synthesis method, focusing on their diverse model designs based on input domains and network architectures. We also analyse novel network architectures, ranging from conventional CNNs to the recent Transformer and Diffusion models. This analysis includes comparing loss functions, available datasets and anatomical regions, and image quality assessments and performance in other downstream tasks. Finally, we discuss the challenges and identify solutions within the literature, suggesting possible future directions. We hope that the insights offered in this survey paper will serve as a valuable roadmap for researchers in the field of medical image synthesis.

This article proposes a practical and generalizable object detector, termed feature extraction-fusion-prediction network (FEFP-Net) for real-world application scenarios. The existing object detection methods have recently achieved excellent performance, however they still face three major challenges for real-world applications, i.e., feature similarity between classes, object size variability, and inconsistent localization and classification predictions. In order to effectively alleviate the current difficulties, the FEFP-Net with three key components is proposed, and the improved detection accuracy is proved in various applications: 1) Extraction Phase: an adaptive fine-grained feature extraction network is proposed to capture features of interest from coarse to fine details, which effectively avoids misclassification due to feature similarity; 2) Fusion Phase: a bidirectional neighbor connection network is designed to identify objects with different sizes by aggregating multilevel features and 3) Prediction Phase: in order to improve the accuracy of object localization and classification, a task specific prediction network is presented, which sufficiently exploits both the spatial and channel information of features. Compared with the State-of-the-Art methods, we achieved competitive results in the MS-COCO dataset. Further, we demonstrated the performance of FEFP-Net in different application fields, such as medical imaging, industry, agriculture, transportation, and remote sensing. These comprehensive experiments indicate that FEFP-Net has satisfactory accuracy and generalizability as a basic object detector.

Automatic defect detection plays an important role in industrial production. Deep learning-based defect detection methods have achieved promising results. However, there are still two challenges in the current defect detection methods: 1) high-precision detection of weak defects is limited and 2) it is difficult for current defect detection methods to achieve satisfactory results dealing with strong background noise. This article proposes a dynamic weights-based wavelet attention neural network (DWWA-Net) to address these issues, which can enhance the feature representation of defects and simultaneously denoise the image, thereby improving the detection accuracy of weak defects and defects under strong background noise. First, wavelet neural networks and dynamic wavelet convolution networks (DWCNets) are presented, which can effectively filter background noise and improve model convergence. Second, a multiview attention module is designed, which can direct the network attention toward potential targets, thereby guaranteeing the accuracy for detecting weak defects. Finally, a feature feedback module is proposed, which can enhance the feature information of defects to further improve the weak defect detection accuracy. The DWWA-Net can be used for defect detection in multiple industrial fields. Experiment results illustrate that the proposed method outperforms the state-of-the-art methods (mean precision: GC10-DET: 6.0%; NEU: 4.3%). The code is made in https://github.com/781458112/DWWA.

Summary Clusters based on hybrid architectures combining ARM CPUs and FPGA fabric, such as the Xilinx Zynq SoC, not only are energy‐efficient platforms with strong processing power but also have the advantages of distributed computing systems balancing the workload between cores, processors, and nodes. This paper employs a 48‐node cluster infrastructure based on the Xilinx Zynq SoC to accelerate classical cryptographic algorithms, including hash functions, AES, and RSA. In this design, we leverage the flexibility of the software to implement node‐to‐node communication through the message passing interface (MPI), and we offload the compute‐intensive tasks to the FPGA to accelerate complex calculations with the parallelizability of specific reconfigurable coprocessors. In addition, we study several parallel cryptography optimizations based on FPGA to evaluate this cluster. Finally, using a comparison with a multi‐core desktop (Intel i7‐3770) and a many‐core server (288 cores), the efficiency of the implementations of the selected data encryption and decryption algorithms is presented to illustrate the performance of our system; we also gain up to 3.6× increase in energy efficiency.

This paper presents a filter bank (FB) analysis of parallel magnetic resonance imaging (PMRI). The underlying image reconstruction strategies of the most widely used PMRI reconstruction methods are unified within the framework and their fundamental perfect reconstruction (PR) constraints are analyzed. Based on this analysis, an improved reconstruction method, called H∞optimal sense, is developed and its advantage is demonstrated by an example.