Intracranial aneurysm (IA) is a life-threatening condition with high morbidity and mortality rates. Since preventive treatment of IA also carries inherent risks, accurate rupture risk prediction is crucial for optimizing clinical decisionmaking. However, current methods for IA rupture risk prediction remain limited in accuracy, generalization, and interpretability. To address the above issues, this study proposes PMA-Net, a novel framework based on a parallel mixed attention mechanism, to efficiently and accurately predict IA rupture risk from Computed Tomography Angiography (CTA) images. By jointly analyzing aneurysms and their surrounding regions, the model captures interdependent imaging features associated with rupture risk. A multi-branch attention module extracts both coarse-and fine-grained features, while clinical information is integrated to enhance prediction performance. In addition, interpretable visualization methods were employed to enhance the model interpretability. Experimental results show that the proposed method achieves superior accuracy, improving by 2.22 % and 1.08 % on internal and external test sets, reaching 92.22 % and 84.78 %, respectively.

Colorectal cancer (CRC) is one of the prominent causes of cancer-related morbidity and mortality worldwide. More AI-assisted methods are conducted for early polyp detection and segmentation to improve the screening efficacy. However, previous solutions generally exhibit weak segmentation performance due to irregular structures of polyps, while the model robustness suffers from background noise of homogeneous neighbors. To this end, we propose a novel Multi-Focus Attention Network (MFANet) to encode multi-dimensional information (i.e., scale, contour, and shape) as fine-grained cues for polyp segmentation. Concretely, a Scale-Residual-Aware Attention (SRAA) is designed to apply the residual operation over each layer of the feature pyramid architecture, which could minimize the feature interference among different scales. To improve the model robustness, a Geometry-Structure-Aware Attention (GSAA) is formulated to integrate and refine multi-dimensional geometric features via a Channel-Wise Enhance Attention (CWEA), which condenses the spatial information and recalibrates the channel importance for adaptive feature recalibration. Experiments on six public datasets indicate the effectiveness of the proposed method. Notably, on the more challenging BKAI dataset, which is featured by tiny polyps with serious interference of homogeneous neighboring region, our MFANet can outperform the state-of-the-art (SOTA) methods. Additionally, it is experimentally verified that our approach consistently exhibits better segmentation performance with higher robustness against different attack strategies (i.e., FGSM, WaNet and PGD).

Myocardial infarction remains a global health challenge. Accurate myocardial segmentation in late gadolinium enhancement cardiac magnetic resonance imaging (LGE-CMRI) is critical for diagnosis and treatment planning. Although deep learning architectures have demonstrated excellent segmentation performance in conventional CMRI, their accuracy significantly declines in LGE-CMRI due to low tissue contrast and complex background interference. To address these challenges, we propose a Progressive Multi-scale Vision Transformer (PMVT) for myocardial segmentation in LGE-CMRI, which enhances spatial representation capabilities and improves adaptability in complex scenarios through multi-scale feature fusion and interaction. Specifically, PMVT includes a Multi-scale Progressive Attention Decoder (MPSD) for modeling both long and short-term dependencies, and a Multi-layer Hybrid Context Purification (MHCP) that combines different combinations of four prediction heads for prediction and loss calculation, effectively suppressing background interference. Experiments demonstrate that the proposed PMVT outperforms state-of-the-art (SOTA) models, achieving a Dice score of 89.61% for myocardial segmentation (a 1.56% improvement over the current SOTA). This result highlights its considerable potential for clinical applications in automated LGE-CMRI analysis.

Hemorrhagic transformation (HT) is a time-sensitive severe complication of endovascular thrombectomy for patients with ischemic stroke, and there is an urgent need to develop deep learning models to assist doctors in making rapid preliminary diagnoses. Currently popular Transformer deep learning architectures, while superior in modeling global relationships compared to traditional CNN, it still faces quadratic complexity issues when handling long sequences of medical images due to its inherent attention mechanism. In contrast, computational complexity of the Mamba model-based method grows linearly. Based on these findings, we have developed a novel Mamba model that effectively captures long-range dependencies and the sequential relationships among slices in high-dimensional medical image sequences. We evaluated the proposed model on a multi-center dataset. Experimental results show that our method outperforms other classical architectures and current advanced methods, validating the effectiveness and generalizability of the model composed of the aforementioned modules.

Aortic dissection (AD) is a life-threatening condition caused by a tear in the aortic intima, allowing blood to enter the vessel wall and form a false lumen. Due to its high mortality rate, timely diagnosis and precise treatment are critical. Clinical diagnosis and treatment of AD rely heavily on accurate 3D vascular image segmentation. To address existing methods’ low segmentation accuracy and insufficient geometric detail preservation, this paper proposes a Transformer-based Dual-Branch Mesh Segmentation Network (TD-MSeg) for AD. This network employs a mesh-based self-attention mechanism to retain vascular geometric details while adopting a dual-branch decoder to effectively fuse features and model long-range dependencies. Specifically, TD-MSeg incorporates three key components: a Hierarchical Mesh Transformer (HMT) module that enhances feature modeling of critical anatomical structures (e.g., intimal tears), a dual-branch decoder that facilitates collaborative optimization of multi-scale local and global features, and a mesh label refinement module that uses a wide-path exploration algorithm to eliminate deformation artifacts and improve spatial label continuity. Moreover, experiments on two AD mesh segmentation datasets demonstrate that the proposed TD-MSeg achieves a 6% improvement in accuracy compared to traditional models and significantly enhances the recognition of complex vascular structures, thereby providing high-precision 3D reconstruction support for endovascular surgical planning.

Hemorrhagic transformation (HT) is a severe complication of acute ischemic stroke (AIS) that can lead to disability or death. Accurate and timely risk assessment of HT is essential for clinicians to design effective treatment strategies. Previous studies in HT prediction have largely relied on machine learning and radiomics, which demand extensive manual data preprocessing by physicians. While some HT prediction models based on convolutional neural network (CNN) have been developed, they are limited in their ability to capture the sequential relationships between image slices and often lack the focus on crucial information. This study collected non-contrast computed tomography (NCCT) images and clinical data from 512 AIS patients across six hospitals to create a multi-center dataset. Based on the dataset, we propose CM-HTNet, a novel deep learning framework designed to predict HT risk in AIS patients following intravenous thrombolysis (IVT). CM-HTNet mimics the clinical process of reviewing NCCT images by focusing on key slices and integrating information from adjacent slices. It leverages CNNs to extract features from each NCCT slice and utilizes the Selective State-Space Model (SSM) within the Mamba framework to model sequential relationships between slices while prioritizing features relevant to HT prediction. Additionally, CM-HTNet incorporates the Neighborhood Rough Set (KRS) algorithm for clinical feature selection and cross-attention mechanisms to integrate clinical and imaging data for multimodal HT risk prediction. In testing on an external dataset from independent centers, CM-HTNet achieved a prediction accuracy of 88.85% and an AUC of 95.17%, showcasing its strong performance and generalization capabilities.

This work aims to conduct a more precise and secure analysis of the competitive differences in bilateral platforms of the digital economy based on artificial intelligence (AI) and network data security. The application of AI technology on bilateral platforms can significantly enhance the level of intelligence and personalisation in services. However, it also drives continuous advancements in data security technology. This work explores the characteristics and advantages of different platforms, providing decision support and strategic guidance to relevant institutions and businesses. Based on this, this work first establishes a distributed training scheme under fog computing to counter data poisoning and safeguard privacy. This scheme is utilised for data collection, storage, and processing while incorporating stringent measures for data privacy protection, such as data encryption, identity authentication, and access control.

Most colorectal cancers originate from adenomatous polyps, which start as single asymptomatic polyps and develop into malignant tumors. In clinical practice, colonoscopy is an extremely effective method for detecting polyps, and it provides important visual information for the accurate identification and removal of polyps. However, it is highly challenging to achieve accurate segmentation of various polyps due to the complex and variable size, shape, color, number, and growth background of polyps at different periods. To address these dilemmas, we propose a multi-distance feature dissimilarity-guided encoder-decoder network for automatic polyp segmentation, mainly consisting of the Multi-Distance Differential Module (MDDM) and the Hybrid Loss Module (HLM). The former mainly utilizes the multilayer feature subtraction (MLFS) operations to extract the difference information between short-distance adjacent layer features and short-distance and long-distance cross-layer features. Given this, the pyramid-inspired MDDM obtains discriminative features continuously between adjacent/cross layers, enhancing complementary features between different layers. The latter supervises the feature maps extracted at each network level to achieve finer predictions. Experiments on four challenge datasets confirm that the proposed model outperforms most state-of-the-art methods in six evaluation metrics while yielding reasonably accurate segmentation results.

OBJECTIVE: Intracranial aneurysms (IA) are lethal, with high morbidity and mortality rates. Reliable, rapid, and accurate segmentation of IAs and their adjacent vasculature from medical imaging data is important to improve the clinical management of patients with IAs. However, due to the blurred boundaries and complex structure of IAs and overlapping with brain tissue or other cerebral arteries, image segmentation of IAs remains challenging. This study aimed to develop an attention residual U-Net (ARU-Net) architecture with differential preprocessing and geometric postprocessing for automatic segmentation of IAs and their adjacent arteries in conjunction with 3D rotational angiography (3DRA) images. METHODS: The proposed ARU-Net followed the classic U-Net framework with the following key enhancements. First, we preprocessed the 3DRA images based on boundary enhancement to capture more contour information and enhance the presence of small vessels. Second, we introduced the long skip connections of the attention gate at each layer of the fully convolutional decoder-encoder structure to emphasize the field of view (FOV) for IAs. Third, residual-based short skip connections were also embedded in each layer to implement in-depth supervision to help the network converge. Fourth, we devised a multiscale supervision strategy for independent prediction at different levels of the decoding path, integrating multiscale semantic information to facilitate the segmentation of small vessels. Fifth, the 3D conditional random field (3DCRF) and 3D connected component optimization (3DCCO) were exploited as postprocessing to optimize the segmentation results. RESULTS: Comprehensive experimental assessments validated the effectiveness of our ARU-Net. The proposed ARU-Net model achieved comparable or superior performance to the state-of-the-art methods through quantitative and qualitative evaluations. Notably, we found that ARU-Net improved the identification of arteries connecting to an IA, including small arteries that were hard to recognize by other methods. Consequently, IA geometries segmented by the proposed ARU-Net model yielded superior performance during subsequent computational hemodynamic studies (also known as "patient-specific" computational fluid dynamics [CFD] simulations). Furthermore, in an ablation study, the five key enhancements mentioned above were confirmed. CONCLUSIONS: The proposed ARU-Net model can automatically segment the IAs in 3DRA images with relatively high accuracy and potentially has significant value for clinical computational hemodynamic analysis.

Medical imaging is widely used in hospital clinical workflows. Assisting physicians in diagnosis by automatically generating reports from radiological images is an unmet clinical demand and requires urgent attention. However, this task suffers from two significant problems: 1) visual and textual data biases, and 2) the Transformer decoder makes no distinction between visual and non-visual words. We propose a novel multi-task approach combining natural language processing with machine learning techniques to meet this clinical need, i.e., creating fluent and accurate radiology reports. We name our system as Multi-modal Adaptive Transformer (MATNet), which consists of three key modules. First, Multi-Modal Encoder (MME) explores the relationship between radiology images and clinical notes. Second, Disease Classifier (DC) classifies the states of each disease topic and provides state-aware disease embeddings to alleviate visual data bias. Last, Adaptive Decoder (AD) dynamically measures the contribution of source signals and target signals when generating the next word. Based on our evaluations using benchmark IU-XRay and MIMIC-CXR datasets, the proposed MATNet outperformed previous state-of-the-art models on language fluency and clinical accuracy metrics such as BLEU scores.

Accurately tracking large tissue motion over a sequence of ultrasound images is critically important to several clinical applications including, but not limited to, elastography, flow imaging, and ultrasound-guided motion compensation. However, tracking in vivo large tissue deformation in 3D is a challenging problem and requires further developments. In this study, we explore a novel tracking strategy that combines Bayesian inference with local polynomial fitting. Since this strategy is incorporated into a region-growing block-matching motion tracking framework we call this strategy a Bayesian region-growing motion tracking with local polynomial fitting (BRGMTLPF) algorithm. More specifically, unlike a conventional block-matching algorithm, we use a maximum posterior probability density function to determine the “correct” three-dimensional displacement vector.The proposed BRGMT-LPF algorithm was evaluated using a tissue-mimicking phantom and ultrasound data acquired from a pathologically-confirmed human breast tumor. The in vivo ultrasound data was acquired using a 3D whole breast ultrasound scanner, while the tissue-mimicking phantom was acquired using an experimental CMUT ultrasound transducer. To demonstrate the effectiveness of combining Bayesian inference with local Polynomial fitting, the proposed method was compared to the original region-growing motion tracking algorithm (RGMT), region-growing with Bayesian interference only (BRGMT), and region-growing with local polynomial fitting (RGMT-LPF). Our preliminary data demonstrate that the proposed BRGMT-LPF algorithm can improve the accuracy of motion tracking.

Tissue motion tracking is a critically important step for many ultrasound elastography applications. In this study, we are particularly interested in evaluating motion tracking strategies for large deformation quasi-static elastography. In this study, Bayesian inference is incorporated into a region-growing motion estimation framework and we named the proposed tracking algorithm as a region-growing Bayesian motion tracking (RGBMT) algorithm. Basically, we replace signal correlation by a maximum posterior probability density function to perform motion tracking. Using a computer-simulated phantom and one set of human subject ultrasound data with pathologically-confirmed breast cancer, the proposed RGBMT algorithm was compared to the original region-growing motion tracking algorithm. Our preliminary data suggested that the addition of Bayesian inference is useful in terms of improving the accuracy of motion tracking. Results from both the numerical phantom and in vivo ultrasound data set showed that there are fewer tracking errors in axial displacement and strain images obtained from the proposed RGBMT algorithms. That explained why the contrast-to-noise (CNR) values were higher and the breast tumor on the reconstructed modulus image was better visualized.

Ultrasound elastography is a modality that is uniquely suited to augment conventional B-mode ultrasound for various clinical applications. Motion tracking plays a critically important role during image formation for ultrasound elastography. In this study, the accuracy of four motion tracking methods tailored for acoustic radiation force-based elastography (e.g. acoustic radiation force imaging, shear wave elastography) is compared. In these elastography methods, external mechanical excitation results in small tissue displacements (i.e. 5-10 micrometers). This paper compares four published motion tracking methods: a quadratic sub-sample estimation method, a coupled sub-sample estimation method, a 2-D spline-based estimator, and a 2-D autocorrelation-based motion estimator. Those four methods are evaluated using computer-simulated and tissue-mimicking phantom data. Based on our preliminary data, we find that the autocorrelation-based method is the preferred estimator without considering the lateral displacement. Overall, the spline-based estimator is superior to the other two competitors when both axial and lateral displacements are estimated. Since the spline-based estimation algorithm is considerably time-intensive, the coupled sub-sample estimation method becomes a practical alternative.

Monte-Carlo ray tracing, which enables realistic simulation of ultrasound-tissue interactions such as soft shadows and fuzzy reflections, has been used to simulate ultrasound images. The main technical challenge presented with Monte-Carlo ray tracing is its computational efficiency. In this study, we investigated the use of a commercially-available ray-tracing engine (NVIDIA's Optix 6.0), which provides a simple, recursive, and flexible pipeline for accelerating ray tracing algorithms. Our preliminary results show that our ultrasound simulation algorithm accelerated by the Optix engine can achieve a frame of 25 frames/second using an Nvidia RTX 2060 card. Furthermore, we compare ultrasound simulations built on the proposed Monte-Carlo ray-tracing algorithm with a deep-learning generative adversarial network (GANs)-based ultrasound simulator and a physics-based ultrasound simulator (Field II). The proposed ultrasound simulator was able to better visualize small-sized structures while the other two above-mentioned simulators could not. Our future work includes integration of our proposed simulator with a virtual reality platform and expansion to other ultrasound modalities such as elastography and flow imaging.

This paper presents an artificial intelligence-based ultrasound simulator suitable for medical simulation and clinical training. Particularly, we propose a machine learning approach to realistically simulate ultrasound images based on generative adversarial networks (GANs). Using B-mode ultrasound images simulated by a known ultrasound simulator, Field II, an "image-to-image" ultrasound simulator was trained. Then, through evaluations, we found that the GAN-based simulator can generate B-mode images following Rayleigh scattering. Our preliminary study demonstrated that ultrasound B-mode images from anatomies inferred from magnetic resonance imaging (MRI) data were feasible. While some image blurring was observed, ultrasound B- mode images obtained were both visually and quantitatively comparable to those obtained using the Field II simulator. It is also important to note that the GAN-based ultrasound simulator was computationally efficient and could achieve a frame rate of 15 frames/second using a regular laptop computer. In the future, the proposed GAN-based simulator will be used to synthesize more realistic looking ultrasound images with artifacts such as shadowing.

Visual exploration of large and complex 3D steady and unsteady flow fields is critically important in many areas of science and engineering. In this paper, we introduce FlowGraph, a novel compound graph representation that organizes field line clusters and spatiotemporal regions hierarchically for occlusion-free and controllable visual exploration. It works with any seeding strategy as long as the domain is well covered and important flow features are captured. By transforming a flow field to a graph representation, we enable observation and exploration of the relationships among field line clusters, spatiotemporal regions and their interconnection in the transformed space. FlowGraph not only provides a visual mapping that abstracts field line clusters and spatiotemporal regions in various levels of detail, but also serves as a navigation tool that guides flow field exploration and understanding. Through brushing and linking in conjunction with the standard field line view, we demonstrate the effectiveness of FlowGraph with several visual exploration and comparison tasks that cannot be well accomplished using the field line view alone. We also perform an empirical expert evaluation to confirm the usefulness of this graph-based technique.

Recent developments in medical imaging and advanced computer modeling simulations) now enable studies designed to correlate either simulated or measured "patient-specific" parameters with the natural history of intracranial aneurysm i.e., ruptured or unruptured. To achieve significance, however, these studies require rigorous comparison of large amounts of data from large numbers of aneurysms, many of which are quite dissimilar anatomically. In this study, we present a method that can likely facilitate such studies as its application could potentially simplify an objective comparison of surface-based parameters of interest such as wall shear stress and blood pressure using large multi-patient, multi-institutional data sets. Based on the concept of harmonic function/field, we present a unified and simple approach for mapping the surface of an aneurysm onto a unit disc. Requiring minimal human interactions the algorithm first decomposes the vessel geometry into 1) target aneurysm and 2) parent artery and any adjacent branches; it, then, maps the segmented aneurysm surface onto a unit disk. In particular, the decomposition of the vessel geometry quantitatively exploits the unique combination of three sets of information regarding the shape of the relevant vasculature: 1) a distance metric defining the spatially varying deviation from a tubular characteristic (i.e., cylindrical structure) of a normal parent artery, 2) local curvatures and 3) local concavities at the junction/interface between an aneurysm and its parent artery. These three sets of resultant shape/geometrical data are then combined to construct a linear system of the Laplacian equation with a novel shape-sensitive weighting scheme. The solution to such a linear system is a shape-sensitive harmonic function/field whose iso-lines will densely gather at the border between the normal parent artery and the aneurysm. Finally, a simple ranking system is utilized to select the best candidate among all possible iso-lines. Quantitative analysis using “patient-specific” aneurysm geometries taken from our internal database demonstrated that the technique is robust. Similar results were obtained from aneurysms having widely different geometries (bifurcation, terminal and lateral aneurysms). Application of our method should allow for meaningful, reliable and reproducible model-to-model comparisons of surface-based physiological and hemodynamic parameters.

We reconstruct the in vivo spatial distribution of linear and nonlinear elastic parameters in ten patients with benign (five) and malignant (five) tumors. The mechanical behavior of breast tissue is represented by a modified Veronda-Westmann model with one linear and one nonlinear elastic parameter. The spatial distribution of these elastic parameters is determined by solving an inverse problem within the region of interest (ROI). This inverse problem solution requires the knowledge of the displacement fields at small and large strains. The displacement fields are measured using a free-hand ultrasound strain imaging technique wherein, a linear array ultrasound transducer is positioned on the breast and radio frequency echo signals are recorded within the ROI while the tissue is slowly deformed with the transducer. Incremental displacement fields are determined from successive radio-frequency frames by employing cross-correlation techniques. The rectangular regions of interest were subjectively selected to obtain low noise displacement estimates and therefore were variables that ranged from 346 to 849.6 mm2 . It is observed that malignant tumors stiffen at a faster rate than benign tumors and based on this criterion nine out of ten tumors were correctly classified as being either benign or malignant.

Radio-frequency (RF) ablation is a minimally invasive treatment for tumors in various abdominal organs. It is effective if good tumor localization and intraprocedural monitoring can be done. In this paper, we investigate the feasibility of using an ultrasound-based Young's modulus reconstruction algorithm to image an ablated region whose stiffness is elevated due to tissue coagulation. To obtain controllable tissue deformations for abdominal organs during and/or intermediately after the RF ablation, the proposed modulus imaging method is specifically designed for using tissue deformation fields induced by the RF electrode. We have developed a new scheme under which the reconstruction problem is simplified to a 2-D problem. Based on this scheme, an iterative Young's modulus reconstruction technique with edge-preserving regularization was developed to estimate the Young's modulus distribution. The method was tested in experiments using a tissue-mimicking phantom and on ex vivo bovine liver tissues. Our preliminary results suggest that high contrast modulus images can be successfully reconstructed. In both experiments, the geometries of the reconstructed modulus images of thermal ablation zones match well with the phantom design and the gross pathology image, respectively.

Modulus imaging has great potential in soft-tissue characterization since it reveals intrinsic mechanical properties. A novel Young's modulus reconstruction algorithm that is based on finite-element analysis is reported here. This new method overcomes some limitations in other Young's modulus reconstruction methods. Specifically, it relaxes the force boundary condition requirements so that only the force distribution at the compression surface is necessary, thus making the new method more practical. The validity of the new method is demonstrated and the performance of the algorithm with noise in the input data is tested using numerical simulations. Details of how to apply this method under clinical conditions is also discussed.