Multiple Myeloma Lesion Segmentation on Whole-Body Diffusion-Weighted Imaging via Efficient Anatomical Anticipation and Multimodal Confirmation
本文针对多发性骨髓瘤病灶在全身扩散加权成像上自动分割的难题，提出了一种结合高效解剖预测和多模态确认的两阶段框架。
0 citationsRead paper
Selected work
Representative Papers
A multicenter benchmark and clinically structured metric for coronary CTA report generation
研究建立了多中心基准和临床结构化指标CSM_CCTA，用于评估冠状动脉CTA报告自动生成的准确性与解剖特异性。
0 citationsRead paper
Coronary Mask Guided Registration for Continuous Time 4D Cardiac CT Dataset Construction
本文提出冠状动脉掩模引导配准(CMGR)方法，旨在通过减少运动伪影和保持时间连续性来构建适用于作为伪真值的4D心脏CT数据集。
0 citationsRead paper
Multi-Feature Riemannian Hypergraph for Online Test-Time Adaptation of Motor Imagery Brain-Computer Interface
This study addresses the challenges of poor cross-day transferability and online decoding in motor imagery brain-computer interfaces (MI-BCI) by proposing the MRieHy framework. Integrating Riemannian geometry with dual hypergraph learning, this method employs covariance alignment and feature hypergraph-weighted fusion, combined with a sliding buffer mechanism to enable test-time adaptation and real-time distribution alignment. Extensive validation on ECoG and EEG datasets demonstrates that MRieHy significantly outperforms state-of-the-art methods, effectively enhancing both cross-session transfer performance and online recognition accuracy. These findings establish a novel paradigm for developing highly robust BCI systems capable of maintaining reliable performance across varying temporal conditions and non-stationary neural signals.
0 citationsRead paper
CMCNet: Aligning Ultrasound Image Embeddings with Textual TI-RADS Representations for Fine-Grained Thyroid Classification
This study addresses the underutilization of feature-level supervision in multi-class thyroid nodule ultrasound classification by proposing CMCNet. The method employs text embeddings as stable proxy representations for risk stratification, achieving cross-modal alignment between ultrasound images and TI-RADS textual descriptions via a Center-Margin Contrastive loss to guide image-only fine-grained grading with structured features. Experimental results demonstrate that CMCNet significantly outperforms InfoNCE and multi-task baselines in data efficiency and robustness. Notably, it exhibits superior performance under class-imbalanced conditions, effectively enhancing the accuracy of nodule risk stratification.
0 citationsRead paper
Recent publications
Latest Papers
Multiple Myeloma Lesion Segmentation on Whole-Body Diffusion-Weighted Imaging via Efficient Anatomical Anticipation and Multimodal Confirmation
本文针对多发性骨髓瘤病灶在全身扩散加权成像上自动分割的难题，提出了一种结合高效解剖预测和多模态确认的两阶段框架。
0 citationsRead paper
A multicenter benchmark and clinically structured metric for coronary CTA report generation
研究建立了多中心基准和临床结构化指标CSM_CCTA，用于评估冠状动脉CTA报告自动生成的准确性与解剖特异性。
0 citationsRead paper
Coronary Mask Guided Registration for Continuous Time 4D Cardiac CT Dataset Construction
本文提出冠状动脉掩模引导配准(CMGR)方法，旨在通过减少运动伪影和保持时间连续性来构建适用于作为伪真值的4D心脏CT数据集。
0 citationsRead paper
Multi-Feature Riemannian Hypergraph for Online Test-Time Adaptation of Motor Imagery Brain-Computer Interface
This study addresses the challenges of poor cross-day transferability and online decoding in motor imagery brain-computer interfaces (MI-BCI) by proposing the MRieHy framework. Integrating Riemannian geometry with dual hypergraph learning, this method employs covariance alignment and feature hypergraph-weighted fusion, combined with a sliding buffer mechanism to enable test-time adaptation and real-time distribution alignment. Extensive validation on ECoG and EEG datasets demonstrates that MRieHy significantly outperforms state-of-the-art methods, effectively enhancing both cross-session transfer performance and online recognition accuracy. These findings establish a novel paradigm for developing highly robust BCI systems capable of maintaining reliable performance across varying temporal conditions and non-stationary neural signals.
0 citationsRead paper
CMCNet: Aligning Ultrasound Image Embeddings with Textual TI-RADS Representations for Fine-Grained Thyroid Classification
This study addresses the underutilization of feature-level supervision in multi-class thyroid nodule ultrasound classification by proposing CMCNet. The method employs text embeddings as stable proxy representations for risk stratification, achieving cross-modal alignment between ultrasound images and TI-RADS textual descriptions via a Center-Margin Contrastive loss to guide image-only fine-grained grading with structured features. Experimental results demonstrate that CMCNet significantly outperforms InfoNCE and multi-task baselines in data efficiency and robustness. Notably, it exhibits superior performance under class-imbalanced conditions, effectively enhancing the accuracy of nodule risk stratification.
0 citationsRead paper