课程文献中心 更多>>

关键词： ConvNeXt–MaxViT fusion   Grad-CAM++ explainability   KOA severity grading   Mid–late fusion   Radiographic deep learning   Transformer–CNN hybrid  

摘要： Knee Osteoarthritis (KOA) is a progressive degenerative joint disorder and a major cause of disability worldwide. Radiographic grading using the Kellgren–Lawrence (KL) scale remains the standard diagnostic method, but inherent subjectivity and difficulty in detecting subtle structural changes reduce diagnostic reliability. Thus, an automated, robust, and explainable system is clinically essential.

关键词： Content addressable memory (CAM)   High-speed search   Hybrid MLs   Local search   Pre-charge free CAM  

摘要： This high-speed, power-efficient content addressable memory (CAM) uses parallel lookups to match quickly without sacrificing power consumption. It introduces three key contributions: i. Pre-charge free operation, which improves search speed and reduces power requirements by eliminating node charging time, ii. A Hybrid Match Line (HML) structure that strategically balances power and delay, combining the high-speed attributes of NOR with the low-power attributes of NAND, and iii. Local searching technique ascertain further improvement in search time. Performance indicators improve greatly when these methods are seamlessly integrated. Utilizing 45 nm CMOS technology, the design supports diverse process voltages, temperatures, and frequencies for a 64x32 memory array. Monte Carlo simulations verify design stability. The proposed architecture outperforms the leading benchmark in speed and power-delay-product (PDP) by 54.6% and 76.02%, respectively. This novel design can do repeated data searches at frequencies up to 2 GHz after a single write operation, enabling quicker and more energy-efficient data processing that could revolutionize consumer electronics. This development could revolutionize consumer electronics by improving efficiency and speed in high-performance computing, mobile devices, and IoT applications.

关键词： Brain medical image segmentation   CAM   Texture knowledge   Weakly supervised  

摘要： In weakly supervised learning-based medical image segmentation, the incompleteness of labels and the complexity of medical image structures often lead to under-segmentation and over-segmentation issues in practical predictions. Therefore, a weakly supervised brain image segmentation guided by texture knowledge (TKG-Net) is proposed in this paper. Its core idea is based on the interaction between the perceptual system and the rational system in the cognitive dual-path model to locate the fuzzy boundaries of the target. First, a simple and effective perceptual system, called the Stepped Class Activation Map Fusion Algorithm, is designed, which utilizes the ability of deep class activation map (CAM) to capture the localization characteristics of the target position and the ability of shallow CAM to highlight the texture characteristics of the target details, and maximally removes background noise to emphasize foreground targets. Second, a novel rational system, called the Texture Knowledge Extraction Module, is introduced into the network, through the collaborative action of fuzzy K-Means and Prewitt operator to efficiently extract the texture features of the target. Subsequently, these captured target texture structural features are effectively integrated into the texture consistency loss function. Finally, a novel Cross-guided module is constructed, which can fully exploit the correlation between texture information and semantic information, achieving more effective fusion of input vectors and thus achieving more precise segmentation of the target region. Our method is evaluated on the BraTS2019 and INSTANCE2022 datasets. Experimental results demonstrate that the proposed TKG-Net exhibits excellent segmentation performance compared to other state-of-the-art methods.

关键词： Canny edge detection   EfficientNet   Histopathological image   Multi-scale feature   Normalization   Vision Transformer  

摘要： Histopathological images are crucial for breast cancer diagnosis but suffer from variability in staining and imaging conditions, leading to poor feature extraction and misclassification. Traditional approaches often fail to capture both local and global tissue structures, impacting diagnostic accuracy.

关键词： BAMBI   Heterogeneity   Single-cell RNA sequencing   Stem cells from human exfoliated deciduous teeth   SHEDs   stem cells from human exfoliated deciduous teeth   CAM   chick embryo chorioallantoic membrane   scRNA-seq   single-cell RNA sequencing  

摘要： Identify the functional subpopulation’s surface marker of stem cells from human exfoliated deciduous teeth (SHEDs) using single-cell RNA sequencing (scRNA-seq) and isolate the subset, providing a theoretical basis for the refined application of stem cells.

关键词： ChatGPT   Large language model   S-Detect   Thyroid nodule   Ultrasound  

摘要： Recent advances in multimodal large language models (LLMs) have demonstrated promising potential for medical image analysis, yet their diagnostic capability in thyroid ultrasound remains unverified. This study explored the feasibility of ChatGPT-5, the latest multimodal LLM, for thyroid nodule classification and contextualized its diagnostic performance against S-Detect, an FDA-approved commercial computer-aided diagnosis system.

关键词： Aortic stenosis   Transcatheter aortic valve implantation   TAVI   Atherosclerosis   Coronary artery disease   Peripheral artery disease   Stroke   AS   Aortic stenosis   AVA   Aortic valve area   APG   Aortic valve pressure gradient   AV   Aortic velocity   ASCVD   Atherosclerotic vascular disease   BMI   Body mass index   CABG   Coronary artery bypass graft   CAD   Coronary artery disease   CI   Confidence interval   CVE   Cerebrovascular event   eGFR   Estimated glomerular filtration rate   HR   Hazard ratio   LVEF   Left ventricular ejection fraction   MI   Myocardial infarction   PAD   Peripheral artery disease   SAVR   Surgical aortic valve replacement   STS   Society of Thoracic Surgeons   TAVI   Transcatheter aortic valve implantation   TIA   Transient ischemic attack  

摘要： Degenerative aortic valve disease and atherosclerotic vascular disease (ASCVD) frequently coexist. ASCVD may impact pre-procedural planning and patient outcomes.

关键词： CAM   ECC   In-memory computing   Logic  

摘要： Most In-memory computing (IMC) work implements only columnar operations. Examples include logic operation and content-addressable memory (CAM) operation. It is not compatible with the traditional SRAM mode. Error correcting codes are widely used to improve data reliability. However, conventional error detection and correction (ECC) methods result in significant area and power overhead due to additional codec circuits. In this paper, we propose a novel 12T SRAM cell that supports four operations (SRAM read/write and matrix transpose, logic operation, CAM operation, and ECC operation). It realizes row- and column-compatible IMC architecture and does not require an external codec module. Simulations show that the frequency and power consumption of the logic operation of the SRAM cell are 641 MHz and 15.4fJ/bit (1V), respectively. The frequency and power consumption of the BCAM operation are 312.5 MHz and 0.61fJ/bit (0.8V), respectively. The coding/decoding frequency and power consumption for ECC operation are 384.6 MHz and 571.4 MHz, 0.141pJ/bit and 0.089pJ/bit (1V), respectively.

关键词： High-order mesh   High-Order Methods   Mesh adaptation   Mesh Generation  

摘要： The present article studies the problem of approximating 3D surface models with meshes composed of curved triangles of arbitrary order. The considered process derives from a high-order solution-based mesh adaptation method called log-simplex method. In this case, it is locally applied on a specific 2D high-order solution, which is built from the features of the model and is defined on the tangent plane to the surface. This way, for a given mesh complexity, an optimal metric field is computed, which then drives the mesh adaptation procedure.

关键词： AUC   Area under the curve   AS   Area stenosis percentage   CABG   Coronary artery bypass grafting   CAD   Coronary artery disease   CCTA   Coronary CT angiography   CT-μFR   Residual quantitative flow ratio derived from coronary CT angiography   DS   Diameter stenosis percentage   FFR   Fractional flow reserve   ICA   Invasive coronary angiography   ICC   Intraclass correlation coefficient   MLA   Minimal luminal area   MLD   Minimal lumen diameter   MI   Myocardial infarction   μQFR   Murray law-based quantitative flow ratio   PCI   Percutaneous coronary intervention   ROC   Receiver operating characteristic   ID-TVR   Ischemia-driven target vessel revascularization   VOCE   Vessel-oriented composite endpoint   coronary artery disease   coronary CT angiography   residual CT-μFR   post-PCI μQFR   percutaneous coronary intervention  

摘要： This study investigates the concordance between residual quantitative flow ratio derived from coronary CT angiography (CCTA) (residual CT-μFR) and post-percutaneous coronary intervention (post-PCI) Murray law-based quantitative flow ratio (μQFR) values, and evaluates the prognostic value of residual CT-μFR for post-PCI outcomes.