IVCVApr 15, 2020

Image Segmentation Using Hybrid Representations

arXiv:2004.07071v16 citations
AI Analysis

This work addresses segmentation challenges in medical imaging by offering a more efficient approach, though it is incremental as it builds on existing U-Net architectures.

The paper tackles medical image segmentation by introducing DU-Net, a hybrid U-Net that incorporates Scattering Coefficients for frequency-preserving features, achieving competitive performance with state-of-the-art methods on four datasets for optic disc, optic cup, and fetal head segmentation, using a lighter network trained on fewer images without augmentation.

This work explores a hybrid approach to segmentation as an alternative to a purely data-driven approach. We introduce an end-to-end U-Net based network called DU-Net, which uses additional frequency preserving features, namely the Scattering Coefficients (SC), for medical image segmentation. SC are translation invariant and Lipschitz continuous to deformations which help DU-Net outperform other conventional CNN counterparts on four datasets and two segmentation tasks: Optic Disc and Optic Cup in color fundus images and fetal Head in ultrasound images. The proposed method shows remarkable improvement over the basic U-Net with performance competitive to state-of-the-art methods. The results indicate that it is possible to use a lighter network trained with fewer images (without any augmentation) to attain good segmentation results.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes