-
CEmb-SAM: Segment Anything Model with Condition Embedding
Automated segmentation of ultrasound images can assist medical experts with diagnostic and therapeutic procedures. Although using the common modality of ultrasound, one... -
SAM-DRIVEN WEAKLY SUPERVISED NODULE SEGMENTATION WITH UNCERTAINTY-AWARE CROSS...
Automated nodule segmentation is essential for computer-assisted diagnosis in ultrasound images. Nevertheless, most existing methods depend on precise pixel-level annotations by... -
AAU-net: An Adaptive Attention U-net for Breast Lesions Segmentation in Ultra...
Three public breast ultrasound datasets (BUSI, Dataset B, and STU) are used to evaluate the segmentation network performance.