We present a new family of active surfaces for the semiautomatic segmentation of volumetric objects in 3D biomedical images. We represent our deformable model by a subdivision surface encoded by a small set of control points and generated through a geometric refinement process. The subdivision operator confers important properties to the surface such as smoothness, reproduction of desirable shapes and interpolation of the control points. We deform the subdivision surface through the minimization of suitable gradient-based and region-based energy terms that we have designed for that purpose. In addition, we provide an easy way to combine these energies with convolutional neural networks. Our active subdivision surface satisfies the property of multiresolution, which allows us to adopt a coarse-to-fine optimization strategy. This speeds up the computations and decreases its dependence on initialization compared to singleresolution active surfaces. Performance evaluations on both synthetic and real biomedical data show that our active subdivision surface is robust in the presence of noise and outperforms current state-of-the-art methods. In addition, we provide a software that gives full control over the active subdivision surface via an intuitive manipulation of the control points.
Open Source Plugin: AC_SubdivisionSurfaces
The method is implemented as a plugin for the Icy bioimaging platform.
Distribution -- PROVIDED AFTER PUBLICATION
Test images and settings -- PROVIDED AFTER PUBLICATION
Condition of useThe software is freely available for research purposes. However, it should not be redistributed without the consent of the authors. We expect the user to include a citation of this publication whenever presenting or publishing results that are based on the Icy plugin AC_SubdivisionSurfaces.