Nature

Semiautomated segmentation of breast tumor on automatic breast ultrasound image using a large-scale model with customized modules

To verify the capability of the Segment Anything Model for medical images in 3D (SAM-Med3D), tailored with low-rank adaptation (LoRA) strategies, in segmenting breast tumors in Automated Breast ...
Nature

Enhanced glioma semantic segmentation using U-net and pre-trained backbone U-net architectures

Glioma tumors represent a formidable challenge in oncology, characterized by their aggressive nature and diverse clinical manifestations. These kinds of tumors originate from glial cells, which ...