Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation
This work addresses segmentation challenges in medical imaging and real-world scenarios, offering an incremental improvement by integrating deep learning with traditional level set methods.
The paper tackles the limitations of Variational Level Set methods in medical segmentation, such as sensitivity to initial settings and multi-instance handling, by proposing Recurrent Level Set (RLS) and Contextual RLS (CRLS) approaches, resulting in improved computational time and segmentation accuracy compared to classic methods, with CRLS achieving competitive performance against state-of-the-art semantic segmentation methods.
Variational Level Set (LS) has been a widely used method in medical segmentation. However, it is limited when dealing with multi-instance objects in the real world. In addition, its segmentation results are quite sensitive to initial settings and highly depend on the number of iterations. To address these issues and boost the classic variational LS methods to a new level of the learnable deep learning approaches, we propose a novel definition of contour evolution named Recurrent Level Set (RLS)} to employ Gated Recurrent Unit under the energy minimization of a variational LS functional. The curve deformation process in RLS is formed as a hidden state evolution procedure and updated by minimizing an energy functional composed of fitting forces and contour length. By sharing the convolutional features in a fully end-to-end trainable framework, we extend RLS to Contextual RLS (CRLS) to address semantic segmentation in the wild. The experimental results have shown that our proposed RLS improves both computational time and segmentation accuracy against the classic variations LS-based method, whereas the fully end-to-end system CRLS achieves competitive performance compared to the state-of-the-art semantic segmentation approaches.