Subpixel object segmentation using wavelets and multi resolution analysis
This work addresses efficient object segmentation for medical imaging, though it is incremental as it builds on existing U-Net architectures with wavelet-based modifications.
The paper tackles the problem of fast boundary prediction for two-dimensional simply connected domains in medical images, achieving up to 5x faster inference speed compared to a U-Net baseline while maintaining similar performance in Dice score and Hausdorff distance.
We propose a novel deep learning framework for fast prediction of boundaries of two-dimensional simply connected domains using wavelets and Multi Resolution Analysis (MRA). The boundaries are modelled as (piecewise) smooth closed curves using wavelets and the so-called Pyramid Algorithm. Our network architecture is a hybrid analog of the U-Net, where the down-sampling path is a two-dimensional encoder with learnable filters, and the upsampling path is a one-dimensional decoder, which builds curves up from low to high resolution levels. Any wavelet basis induced by a MRA can be used. This flexibility allows for incorporation of priors on the smoothness of curves. The effectiveness of the proposed method is demonstrated by delineating boundaries of simply connected domains (organs) in medical images using Debauches wavelets and comparing performance with a U-Net baseline. Our model demonstrates up to 5x faster inference speed compared to the U-Net, while maintaining similar performance in terms of Dice score and Hausdorff distance.