About this document

AAWS-Net for Breast Mass Segmentation by kookmindoo is a document available to read on EtoBox.

The document presents AAWS-Net, an Anatomy-Aware Weakly-Supervised Learning Network designed for accurate breast mass segmentation using mammograms with weak annotations. By leveraging a teacher-student model, the network extracts anatomical structures and employs knowledge distillation to enhance segmentation performance, particularly distinguishing between benign and malignant masses. Experimental results demonstrate that AAWS-Net outperforms existing state-of-the-art methods in segmentation accuracy on t

Author

kookmindoo

Language

EN