Fig. 1: Visual comparison of segmentation results on representative IVUS images. | npj Digital Medicine

Fig. 1: Visual comparison of segmentation results on representative IVUS images.

From: PlaqueCap: lesion-centered captioning of atherosclerotic plaques in intravascular ultrasound using vision-language models and prompt injection

Fig. 1

From left to right: original image (Image), ground-truth (GT), our model’s prediction (Ours), U-Net’s prediction, and UNETR's prediction. Our model’s segmentation (red overlay) aligns more closely with the ground-truth (blue overlay) across various plaque morphologies. Rows (A−E) show representative cases with different plaque morphologies.

Back to article page