Unlocking 2D/3D+T myocardial mechanics from cine MRI: a mechanically regularized space-time finite element correlation framework [0.03%]
基于力学正则化的时空有限元相关框架提取心脏舒张收缩二维和三维时变心肌力学参数
Haizhou Liu,Xueling Qin,Zhou Liu et al.
Haizhou Liu et al.
Accurate and biomechanically consistent quantification of cardiac motion remains a major challenge in cine MRI analysis. While classical feature-tracking and recent deep learning methods have improved frame-wise strain estimation, they ofte...
Rapid spatio-temporal MR fingerprinting using physics-informed implicit neural representation [0.03%]
基于物理信息的隐式神经表示的快速时空MR指纹识别技术
Chaoguang Gong,Lixian Zou,Peng Li et al.
Chaoguang Gong et al.
The potential of Magnetic Resonance Fingerprinting (MRF), which allows for rapid and simultaneous multi-parametric quantitative MRI, is often limited by severe aliasing artifacts caused by aggressive undersampling. Conventional MRF approach...
Facial appearance prediction for orthognathic surgery with diffusion models [0.03%]
扩散模型在正颌手术面部外观预测中的应用
Jungwook Lee,Xuanang Xu,Daeseung Kim et al.
Jungwook Lee et al.
Orthognathic surgery corrects craniomaxillofacial deformities by repositioning skeletal structures to improve facial aesthetics and function. Conventional orthognathic surgical planning is largely bone-driven, where bone repositioning is fi...
UTMorph: A hybrid CNN-transformer network for weakly-supervised multimodal image registration in biopsy puncture [0.03%]
用于活检穿刺弱标注多模态图像配准的混合CNN-Transformer网络UTMorph
Xudong Guo,Peiyu Chen,Haifeng Wang et al.
Xudong Guo et al.
Accurate registration of preoperative magnetic resonance imaging (MRI) and intraoperative ultrasound (US) images is essential to enhance the precision of biopsy punctures and targeted ablation procedures using robotic systems. To improve th...
Latent diffusion autoencoders: Toward efficient and meaningful unsupervised representation learning in medical imaging - a case study on Alzheimer's disease [0.03%]
潜在扩散自动编码器：面向医学图像中的高效且意义明确的无监督表征学习-针对阿尔茨海默病案例研究
Gabriele Lozupone,Alessandro Bria,Francesco Fontanella et al.
Gabriele Lozupone et al.
This study presents Latent Diffusion Autoencoder (LDAE), a novel encoder-decoder diffusion-based framework for efficient and meaningful unsupervised learning in medical imaging, focusing on Alzheimer's disease (AD) using brain MRI from the ...
NeuroDetour: A neural pathway transformer for uncovering structural-functional coupling mechanisms in human connectome [0.03%]
基于人脑连接组的神经路径变换机制挖掘模型
Ziquan Wei,Tingting Dan,Jiaqi Ding et al.
Ziquan Wei et al.
Although modern imaging methods enable in-vivo examination of connections between distinct brain areas, we still lack a comprehensive understanding of how anatomical structure underpins brain function and how spontaneous fluctuations in neu...
SupReMix: Supervised contrastive learning for medical imaging regression with mixup [0.03%]
基于混合监督对比学习的医学影像回归方法
Yilei Wu,Zijian Dong,Chongyao Chen et al.
Yilei Wu et al.
In medical image analysis, regression plays a critical role in computer-aided diagnosis. It enables quantitative measurements such as age prediction from structural imaging, cardiac function quantification, and molecular measurement from PE...
DTG: Dual transformers-based generative adversarial networks for retinal 2D/3D OCT image classification [0.03%]
基于双变换器的生成对抗网络用于视网膜2D/3D OCT图像分类
Badr Ait Hammou,Renaud Duval,Marie-Carole Boucher et al.
Badr Ait Hammou et al.
The automated identification of retinal disorders is one of the most popular real-world computer vision applications related to ophthalmology. It has several advantages and can help ophthalmologists identify diseases more accurately. Techni...
UDV-Net: A hybrid CNN and transformer vein segmentation network with vascular prior and spatial awareness [0.03%]
一种基于血管先验和空间感知的混合CNN与Transformer静脉分割网络（UDV-Net）
Bowei Shen,Xiaoquan Huang,Yuli Li et al.
Bowei Shen et al.
CNNs handling multi-scale variations and Transformers modeling long-range dependencies are crucial for vascular segmentation. The fusion of these two models effectively combines the multi-scale local features extracted by CNNs with the glob...
DVAP-Reg: Dual-view anatomical prior-driven cross-dimensional registration for spinal surgery navigation [0.03%]
基于双视图解剖先验的脊柱手术导航中的跨维度配准方法(DVAP-Reg)
Zhengyang Wu,Wenjie Zheng,Yingjie Hao et al.
Zhengyang Wu et al.
2D-3D cross-dimensional registration serves as a critical technology in spinal surgery navigation, with profound implications for enhancing surgical precision, reducing radiation exposure and mitigating surgical risks. Its core objective is...