http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Joint MR image reconstruction and super-resolution via mutual co-attention network
Lv Tiantong,Wu Fei,Wang Wanliang 한국CDE학회 2024 Journal of computational design and engineering Vol.11 No.1
In the realm of medical diagnosis, recent strides in deep neural network-guided magnetic resonance imaging (MRI) restoration have shown promise. Nevertheless, persistent drawbacks overshadow these advancements. Challenges persist in balancing acquisition speed and image quality, while existing methods primarily focus on singular tasks like MRI reconstruction or super-resolution (SR), neglecting the interplay between these tasks. To tackle these challenges, this paper introduces the mutual co-attention network (MCAN) specifically designed to concurrently address both MRI reconstruction and SR tasks. Comprising multiple mutual cooperation attention blocks (MCABs) in succession, MCAN is tailored to maintain consistency between local physiological details and global anatomical structures. The intricately crafted MCAB includes a feature extraction block, a local attention block and a global attention block. Additionally, to ensure data fidelity without compromising acquired data, we propose the channel-wise data consistency block. Thorough experimentation on the IXI and fastMRI dataset showcases MCAN’s superiority over existing state-of-the-art methods. Both quantitative metrics and visual quality assessments validate the enhanced performance of MCAN in MRI restoration. The findings underscore MCAN’s potential in significantly advancing therapeutic applications. By mitigating the trade-off between acquisition speed and image quality while simultaneously addressing both MRI reconstruction and SR tasks, MCAN emerges as a promising solution in the domain of magnetic resonance image restoration.
Lv Tiantong,Chen Zipeng,Wang Dengfeng,Du Xuejing 한국CDE학회 2024 Journal of computational design and engineering Vol.11 No.1
Combined application of steel, aluminum, and carbon fiber reinforcement plastic (CFRP) is the main direction of future lightweight body development. However, the anisotropy and additional lamination design variables of CFRP parts pose significant challenges for the development of multi-material bodies. This study establishes a parametric design method for the variable-thickness lamination scheme based on non-uniform rational B-splines, it can be coupled with existing parametric design methods for structural shapes to formulate a complete parametric design and modeling of CFRP components. On this basis, a homogenized intermediate material property is derived from classic laminate theory by introducing lamination assumptions, it enables a stepwise multi-material body optimization method to solve the challenge that components’ material design variables switching between CFRP and alloy will introduce/eliminate lamination design variables iteratively, posing a great optimization convergence difficulty. The proposed parametric modeling method for CFRP components was validated by experimental tests of a fabricated roof beam, and the proposed optimization method was applied to a vehicle body, achieving 15.9%, 23.9%, 18.6%, and 12.2% increase in bending and torsional stiffness and modal frequencies; 20.2%, 9.3%, and 12.7% reduction of weight and peak acceleration in frontal and side collisions. This study enables the forward design of multi-material bodies compatible with CFRP parts.