4 citations · 8 across the 13 of their papers we have counts for
14 papers
Benchmarking Self-Supervised 3D Medical Vision Foundation Models and Transferability Estimation
Jiaqi Tang, Yu Wang, Yang Liu +7
Self-supervised pretraining has expanded the pool of 3D medical foundation models, but published evaluations use different datasets, endpoints and fine-tuning protocols. Models als…
Topology-Driven Transferability Estimation for 3D Medical Vision Foundation Models
Jiaqi Tang, Shaoyang Zhang, Fandong Zhang +3
The growing number of medical vision foundation models highlights the need for effective model selection. However, mainstream selection methods rely on exhaustive fine-tuning, whic…
TriDP-PTM: a three-stage distortion-perception tradeoff guides the pre-training model for radar cardiac sensing
Jinye Li, Aidong Men, Yang Liu +1
Cardiovascular diseases (CVDs) remain a leading cause of death globally, necessitating continuous, accurate non-invasive cardiac monitoring. While non-contact radar-based approache…
3D MRI Image Pretraining via Controllable 2D Slice Navigation Task
Yu Wang, Qingchao Chen
Self-supervised pretraining has become the mainstream approach for learning MRI representations from unlabeled scans. However, most existing objectives still treat each scan primar…
The Texture-Shape Dilemma: Boundary-Safe Synthetic Generation for 3D Medical Transformers
Jiaqi Tang, Weixuan Xu, Shu Zhang +2
Vision Transformers (ViTs) have revolutionized medical image analysis, yet their data-hungry nature clashes with the scarcity and privacy constraints of clinical archives. Formula-…
Fake It Right: Injecting Anatomical Logic into Synthetic Supervised Pre-training for Medical Segmentation
Jiaqi Tang, Mengyan Zheng, Shu Zhang +2
Vision Transformers (ViTs) excel in 3D medical segmentation but require massive annotated datasets. While Self-Supervised Learning (SSL) mitigates this using unlabeled data, it sti…
Shaping Initial State Prevents Modality Competition in Multi-modal Fusion: A Two-stage Scheduling Framework via Fast Partial Information Decomposition
Jiaqi Tang, Yinsong Xu, Yang Liu +1
Multi-modal fusion often suffers from modality competition during joint training, where one modality dominates the learning process, leaving others under-optimized. Overlooking the…
Advancing Radar Hand Gesture Recognition: A Hybrid Spectrum Synthetic Framework Merging Simulation with Neural Networks
Jiaqi Tang, Xinbo Xu, Yinsong Xu +1
Millimeter wave (mmWave) radar sensors play a vital role in hand gesture recognition (HGR) by detecting subtle motions while preserving user privacy. However, the limited scale of…
Locating and Mitigating Gradient Conflicts in Point Cloud Domain Adaptation via Saliency Map Skewness
Jiaqi Tang, Yinsong Xu, Qingchao Chen
Object classification models utilizing point cloud data are fundamental for 3D media understanding, yet they often struggle with unseen or out-of-distribution (OOD) scenarios. Exis…
Deep Learning-Based Quantitative Assessment of Renal Chronicity Indices in Lupus Nephritis
Tianqi Tu, Hui Wang, Jiangbo Pei +7
Background: Renal chronicity indices (CI) have been identified as strong predictors of long-term outcomes in lupus nephritis (LN) patients. However, assessment by pathologists is h…
Poisson Ordinal Network for Gleason Group Estimation Using Bi-Parametric MRI
Yinsong Xu, Yipei Wang, Ziyi Shen +7
The Gleason groups serve as the primary histological grading system for prostate cancer, providing crucial insights into the cancer's potential for growth and metastasis. In clinic…
MERIT: Multi-view evidential learning for reliable and interpretable liver fibrosis staging
Yuanye Liu, Zheyao Gao, Nannan Shi +4
Accurate staging of liver fibrosis from magnetic resonance imaging (MRI) is crucial in clinical practice. While conventional methods often focus on a specific sub-region, multi-vie…
Selection, Ensemble, and Adaptation: Advancing Multi-Source-Free Domain Adaptation via Architecture Zoo
Jiangbo Pei, Ruizhe Li, Aidong Men +3
Conventional Multi-Source Free Domain Adaptation (MSFDA) assumes that each source domain provides a single source model, and all source models adopt a uniform architecture. This pa…
EviPrompt: A Training-Free Evidential Prompt Generation Method for Segment Anything Model in Medical Images
Yinsong Xu, Jiaqi Tang, Aidong Men +1
Medical image segmentation has immense clinical applicability but remains a challenge despite advancements in deep learning. The Segment Anything Model (SAM) exhibits potential in…