Tree-like structures are fundamental in nature, and it is often useful to reconstruct the topology of a tree - what connects to what - from a two-dimensional image of it. However, the projected branches often cross in the image: the tree projects to a planar graph, and the inverse problem of reconstructing the topology of the tree from that of the graph is ill-posed. We regularize this problem with a generative, parametric tree-growth model. Under this model, reconstruction is possible in linear time if one knows the direction of each edge in the graph - which edge endpoint is closer to the root of the tree - but becomes NP-hard if the directions are not known. For the latter case, we present a heuristic search algorithm to estimate the most likely topology of a rooted, three-dimensional tree from a single two-dimensional image. Experimental results on retinal vessel, plant root, and synthetic tree data sets show that our methodology is both accurate and efficient.
Tree-like structures are fundamental in nature, and it is often useful to reconstruct the topology of a tree - what connects to what - from a two-dimensional image of it. However, the projected bpan class="Gene">ranches often cross in the image: the tree projects to a planar graph, and the inverse problem of reconstructing the topology of the tree from that of the graph is ill-posed. We regularize this problem with a generative, parametric tree-growth model. Under this model, reconstruction is possible in linear time if one knows the direction of each edge in the graph - which edge endpoint is closer to the root of the tree - but becomes NP-hard if the directions are not known. For the latter case, we present a heuristic search algorithm to estimate the most likely topology of a rooted, three-dimensional tree from a single two-dimensional image. Experimental results on retinal vessel, plant root, and synthetic tree data sets show that our methodology is both accurate and efficient.
Authors: João V B Soares; Jorge J G Leandro; Roberto M Cesar Júnior; Herbert F Jelinek; Michael J Cree Journal: IEEE Trans Med Imaging Date: 2006-09 Impact factor: 10.048
Authors: Changyan Xiao; Marius Staring; Yaonan Wang; Denis P Shamonin; Berend C Stoel Journal: IEEE Trans Image Process Date: 2012-08-30 Impact factor: 10.856
Authors: Rolando Estrada; Carlo Tomasi; Michelle T Cabrera; David K Wallace; Sharon F Freedman; Sina Farsiu Journal: Biomed Opt Express Date: 2011-09-29 Impact factor: 3.732
Authors: Holger Perfahl; Helen M Byrne; Tingan Chen; Veronica Estrella; Tomás Alarcón; Alexei Lapin; Robert A Gatenby; Robert J Gillies; Mark C Lloyd; Philip K Maini; Matthias Reuss; Markus R Owen Journal: PLoS One Date: 2011-04-13 Impact factor: 3.240
Authors: Rolando Estrada; Michael J Allingham; Priyatham S Mettu; Scott W Cousins; Carlo Tomasi; Sina Farsiu Journal: IEEE Trans Med Imaging Date: 2015-06-10 Impact factor: 10.048
Authors: Victor T T Chan; Tiffany H K Tso; Fangyao Tang; Clement Tham; Vincent Mok; Christopher Chen; Tien Y Wong; Carol Y Cheung Journal: J Vis Exp Date: 2017-11-06 Impact factor: 1.355
Authors: Monalisa Patel; Dibyendu Mukherjee; Sina Farsiu; Breda Munoz; Arlin B Blood; Christopher G Wilson; Jennifer B Griffin Journal: Front Pediatr Date: 2019-02-20 Impact factor: 3.418
Authors: Janan Arslan; Gihan Samarasinghe; Kurt K Benke; Arcot Sowmya; Zhichao Wu; Robyn H Guymer; Paul N Baird Journal: Transl Vis Sci Technol Date: 2020-10-26 Impact factor: 3.283