4 papers
SAMRI-3D: Adapting SAM2 for 3D MRI Segmentation with Global Volume Tokens
Zhao Wang, Wei Dai, Hongfu Sun +2
Foundation models such as Segment Anything Model 2 (SAM2) have transformed natural-image and video segmentation, and recent work has begun adapting them to medical imaging. These a…
Deep Psychovisual Image Representations
Wendi Ma, Aryaman Sharma, Wei Dai +1
Psychovisual models suggest human vision decouples low-level feature extraction from higher cognition by first forming intermediate abstractions. In contrast, deep learning-based v…
SAMRI: Segment Any MRI
Zhao Wang, Wei Dai, Thuy Thanh Dao +4
Summary: SAMRI is an MRI-specialized adaptation of the Segment Anything Model achieving superior whole-body MRI segmentation, particularly for small and clinically critical structu…
Multi-scale MRI reconstruction via dilated ensemble networks
Wendi Ma, Marlon Bran Lorenzana, Wei Dai +2
As aliasing artefacts are highly structural and non-local, many MRI reconstruction networks use pooling to enlarge filter coverage and incorporate global context. However, this ina…