4 papers
TEAMS: Text-prompted spatiotEmporal dual-heAd Mamba Snake
Ruicheng Zhang, Jianhui Lei, Kaiwen Shen +6
Deep snake is a promising family of instance segmentation methods that accurately predicts object-level contours, thereby overcoming common pixel-level misclassification issues suc…
SGP-SAM: Self-Gated Prompting for Transferring 3D Segment Anything Models to Lesion Segmentation
Zixuan Tang, Zequan Yao, Shen Zhao +1
Large segmentation foundation models such as the Segment Anything Model (SAM) have reshaped promptable segmentation in natural images, and recent efforts have extended these models…
T-DuMpRa: Teacher-guided Dual-path Multi-prototype Retrieval Augmented framework for fine-grained medical image classification
Zixuan Tang, Shen Zhao
Fine-grained medical image classification is challenged by subtle inter-class variations and visually ambiguous cases, where confidence estimates often exhibit uncertainty rather t…
Direct detection of pixel-level myocardial infarction areas via a deep-learning algorithm
Chenchu Xu, Lei Xu, Zhifan Gao +7
Accurate detection of the myocardial infarction (MI) area is crucial for early diagnosis planning and follow-up management. In this study, we propose an end-to-end deep-learning al…