Search papers, labs, and topics across Lattice.
5
0
6
Forget reconstructing images: this method directly extracts clinically relevant information from undersampled k-space MRI data, matching state-of-the-art image-based analysis.
Multi-view Echo data can be used to train ECG encoders that are 18x smaller yet outperform larger models at predicting cardiac morphology.
Ditch the patches: Implicit Neural Representations can now segment highly variable pathological lesions in whole-slide images, even outperforming standard methods at lower resolutions.
Attachment anchors, a novel representation of tissue-attachment relationships, significantly boost grasping point prediction in colorectal surgery, particularly when generalizing to new surgical scenarios and surgeons.
VariViT lets you train vision transformers on variable-sized images without resizing, boosting accuracy on medical imaging tasks by better preserving irregularly shaped structures.
