Yimeng Dou

A Standardized Technique for Ultrasound– MRI Fusion Imaging of the Carotid Artery for Vascular Assessment

Maxwell Kiernan, Rashid Al Mukaddim, Yurim Lee, Yimeng Dou et autres

PURPOSE: To describe a reproducible ultrasound-magnetic resonance imaging (MRI) fusion imaging technique developed for quantitative assessment of carotid wall strain and plaque morphology. METHODS: MRI volumes (Oblique T2 Cube) were imported into the Sequoia ultrasound system equipped with an electromagnetic tracking module. …

us (code pays fourni par la source)

Geometry aware neural radiance fields for freehand ultrasound reconstruction

Yimeng Dou, Yin Li, Tomy Varghese

Abstract Reconstructing 3D volumes from 2D freehand ultrasound (US) is a challenging task. During reconstruction, the ensuing overlap between sweeps can cause multiple pixels to be assigned to the same voxel, so the accurate alignment of these sweeps is critical. In recent …

us (code pays fourni par la source)

3D Freehand Ultrasound Reconstruction of the Carotid Artery

Yimeng Dou, Maxwell Kiernan, Zhiwei Zhang, Carol Mitchell et autres

us (code pays fourni par la source)

Zero-shot Multi-Contrast Brain MRI Registration by Intensity Randomizing T1-weighted MRI (LUMIR25)

Hengjie Liu, Yimeng Dou, Di Xu, Xinyi Fu et autres

In this paper, we present our submission to the LUMIR25 task of Learn2Reg 2025, which ranked 1st overall on the test set. Extended from LUMIR24, this year's task focuses on zero-shot registration under domain shifts (e.g., high-field MRI, pathological brains, and various …

Zero-shot Multi-Contrast Brain MRI Registration by Intensity Randomizing T1-weighted MRI (LUMIR25)

Hengjie Liu, Yimeng Dou, Di Xu, Xinyi Fu et autres

In this paper, we present our submission to the LUMIR25 task of Learn2Reg 2025, which ranked 1st overall on the test set. Extended from LUMIR24, this year's task focuses on zero-shot registration under domain shifts (e.g., high-field MRI, pathological brains, and various …

Efficacy of BCMA CAR-T cell therapy and subsequent strategies in refractory and relapsed plasma cell leukemia: a retrospective cohort study

Yuelu Guo, Lixia Ma, Fan Yang, Zhonghua Fu et autres

Background: Plasma cell leukemia (PCL) is a rare and aggressive hematological malignancy. The long-term prognosis of relapsed/refractory plasma cell leukemia (R/R PCL) remains poor, and few treatment options are available for patients with triple-refractory disease. Chimeric antigen receptor (CAR)-T cell therapy targeting …

cn (code pays fourni par la source)

Zero-Shot Multi-Contrast Brain MRI Registration by Intensity Randomizing T1-Weighted MRI (LUMIR25)

Hengjie Liu, Yimeng Dou, D Xu, Xinyi Fu et autres

us (code pays fourni par la source)

Adaptive Hash Ring-Based Efficient Fuzzy and Over-Threshold Multi-Party PSI

Li Guan, Xiaodong Li, Ruoyun Zhao, Yimeng Dou et autres

Private Set Intersection (PSI) enables participants to compute the intersection of private data without revealing other information. Over-Threshold Multi-Party PSI (OT-MPPSI) extends this capability by revealing elements shared by at least t participants, but existing schemes only support exact matches. Fuzzy PSI …

cn (code pays fourni par la source)

A High-Precision and Scalable Location Privacy Query System Based on FHE

Lan Ma, Xiaodong Li, A.W.-C. Fu, Yuan Cui et autres

cn (code pays fourni par la source)

Geometry Aware Neural Radiance Fields for Freehand Ultrasound Reconstruction

Yimeng Dou, Yin Li, Tomy Varghese

Many freehand 3D ultrasound methods map 2D images directly into a 3D volume, but they are sensitive to transducer pose errors, leading to poor reconstructions. Implicit representation methods, such as Neural Radiance Fields (NeRF), offer an alternative by modeling the underlying 3D …

A Paillier-based k-out-of-n oblivious transfer protocol

Li Guan, Xiaodong Li, Jianyi Zhang, Yimeng Dou et autres

Oblivious Transfer (OT), a fundamental primitive in cryptography and a cornerstone of Secure Multi-Party Computation (SMPC), is widely applied in privacy-preserving domains. Constructing efficient and secure OT protocols remains an active research area. To address the limitations of existing OT protocols, such …

cn (code pays fourni par la source)

FL-KAN: A Federated Learning Framework with Kolmogorov-Arnold Networks and Confused Modulo Projection Homomorphic Encryption

Yimeng Dou, Lin Yang, Xiaodong Li, X.H. An et autres

With the growing adoption of federated learning (FL) in privacy-sensitive applications, current methods continue to face critical challenges of suboptimal model efficiency and potential privacy leakage. Conventional neural architectures such as multilayer perceptrons (MLPs) often suffer from low parameter efficiency and limited …

cn (code pays fourni par la source)