2000 character limit reached
U-net for spectral quantitative microwave breast imaging
Published 4 Feb 2025 in physics.med-ph and physics.app-ph | (2502.02476v1)
Abstract: A spectral approach based on the Fourier diffraction theorem is combined with a pair of U-NETs to perform quantitative microwave imaging of an anthropomorphic breast phantom. The U-NET pair is trained on a spectral database constructed from combinations of different realistic parts of the breast. Some preliminary numerical results are presented to show the major improvement brought by the U-NET.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.