SAM-DRIVEN WEAKLY SUPERVISED NODULE SEGMENTATION WITH UNCERTAINTY-AWARE CROSS TEACHING

doi:doi:10.57702/bu3064p0

SAM-DRIVEN WEAKLY SUPERVISED NODULE SEGMENTATION WITH UNCERTAINTY-AWARE CROSS TEACHING

Automated nodule segmentation is essential for computer-assisted diagnosis in ultrasound images. Nevertheless, most existing methods depend on precise pixel-level annotations by medical professionals, a process that is both costly and labor-intensive. Recently, segmentation foundation models like SAM have shown impressive generalizability on natural images, suggesting their potential as pseudo-labelers.

BibTex:

@dataset{Xingyue_Zhao_and_Peiqi_Li_and_Xiangde_Luo_and_Meng_Yang_and_Shi_Chang_and_Zhongyu_Li_2024,
    abstract = {Automated nodule segmentation is essential for computer-assisted diagnosis in ultrasound images. Nevertheless, most existing methods depend on precise pixel-level annotations by medical professionals, a process that is both costly and labor-intensive. Recently, segmentation foundation models like SAM have shown impressive generalizability on natural images, suggesting their potential as pseudo-labelers.},
    author = {Xingyue Zhao and Peiqi Li and Xiangde Luo and Meng Yang and Shi Chang and Zhongyu Li},
    doi = {10.57702/bu3064p0},
    institution = {No Organization},
    keyword = {'nodule segmentation', 'ultrasound images', 'uncertainty-aware cross teaching', 'weakly supervised learning'},
    month = {dec},
    publisher = {TIB},
    title = {SAM-DRIVEN WEAKLY SUPERVISED NODULE SEGMENTATION WITH UNCERTAINTY-AWARE CROSS TEACHING},
    url = {https://service.tib.eu/ldmservice/dataset/sam-driven-weakly-supervised-nodule-segmentation-with-uncertainty-aware-cross-teaching},
    year = {2024}
}