Simultaneous tomographic reconstruction and segmentation with class priors. Issue 8 (12th October 2016)

• Record Type: Journal Article
• Authors: Romanov, Mikhail; Dahl, Anders Bjorholm; Dong, Yiqiu; Hansen, Per Christian
• Is Part Of: Inverse problems in science and engineering. Volume 24:Issue 8(2016)
• Page Start: 1432
• Page End: 1453
• Publication Date: 2016-10-12
• Subjects: Tomographic reconstruction -- segmentation -- regularization -- numerical optimization -- Hidden Markov Measure Field Models; 65F22 -- 65K10; Engineering mathematics -- Periodicals; Inverse problems (Differential equations) -- Periodicals; 620.001515357
• DOI: 10.1080/17415977.2015.1124428
• Languages: English
• ISSNs: 1741-5977

Abstract

Abstract : We consider tomographic imaging problems where the goal is to obtain both a reconstructed image and a corresponding segmentation. A classical approach is to first reconstruct and then segment the image; more recent approaches use a discrete tomography approach where reconstruction and segmentation are combined to produce a reconstruction that is identical to the segmentation. We consider instead a hybrid approach that simultaneously produces both a reconstructed image and segmentation. We incorporate priors about the desired classes of the segmentation through a Hidden Markov Measure Field Model, and we impose a regularization term for the spatial variation of the classes across neighbouring pixels. We also present an efficient implementation of our algorithm based on state-of-the-art numerical optimization algorithms. Simulation experiments with artificial and real data demonstrate that our combined approach can produce better results than the classical two-step approach.