eprintid: 1561200
rev_number: 26
eprint_status: archive
userid: 608
dir: disk0/01/56/12/00
datestamp: 2017-12-14 12:16:57
lastmod: 2021-11-23 00:54:53
status_changed: 2017-12-14 12:16:57
type: proceedings_section
metadata_visibility: show
creators_name: Iglesias, JE
title: Globally Optimal Coupled Surfaces for Semi-automatic Segmentation of Medical Images
ispublished: pub
divisions: UCL
divisions: B04
divisions: C05
divisions: F42
note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
abstract: Manual delineations are of paramount importance in medical imaging, for instance to train supervised methods and evaluate automatic segmentation algorithms. In volumetric images, manually tracing regions of interest is an excruciating process in which much time is wasted labeling neighboring 2D slices that are similar to each other. Here we present a method to compute a set of discrete minimal surfaces whose boundaries are specified by user-provided segmentations on one or more planes. Using this method, the user can for example manually delineate one slice every n and let the algorithm complete the segmentation for the slices in between. Using a discrete framework, this method globally minimizes a cost function that combines a regularizer with a data term based on image intensities, while ensuring that the surfaces do not intersect each other or leave holes in between. While the resulting optimization problem is an integer program and thus NP-hard, we show that the equality constraint matrix is totally unimodular, which enables us to solve the linear program (LP) relaxation instead. We can then capitalize on the existence of efficient LP solvers to compute a globally optimal solution in practical times. Experiments on two different datasets illustrate the superiority of the proposed method over the use of independent, label-wise optimal surfaces (∼ 5% mean increase in Dice when one every six slices is labeled, with some structures improving up to ∼ 10% in Dice).
date: 2017-05-23
date_type: published
publisher: Springer
official_url: http://dx.doi.org/10.1007/978-3-319-59050-9_48
oa_status: green
full_text_type: other
language: eng
primo: open
primo_central: open_green
verified: verified_manual
elements_id: 1300473
doi: 10.1007/978-3-319-59050-9_48
lyricists_name: Iglesias Gonzalez, Juan
lyricists_id: JEIGL66
actors_name: Allington-Smith, Dominic
actors_id: DAALL44
actors_role: owner
full_text_status: public
series: Lecture Notes in Computer Science
publication: IPMI 2017: Information Processing in Medical Imaging
volume: 10265
place_of_pub: Cham, Switzerland
pagerange: 610-621
event_title: International Conference on Information Processing in Medical Imaging
event_location: Boone, NC, USA
event_dates: 25 June 2017 - 30 June 2017
institution: International Conference on Information Processing in Medical Imaging
book_title: Information Processing in Medical Imaging: 25th International Conference, IPMI 2017, Boone, NC, USA, June 25-30, 2017, Proceedings
editors_name: Niethammer, M
editors_name: Styner, M
editors_name: Aylward, S
editors_name: Zhu, H
editors_name: Oguz, I
editors_name: Yap, PT
editors_name: Shen, D
citation:        Iglesias, JE;      (2017)    Globally Optimal Coupled Surfaces for Semi-automatic Segmentation of Medical Images.                     In: Niethammer, M and Styner, M and Aylward, S and Zhu, H and Oguz, I and Yap, PT and Shen, D, (eds.) Information Processing in Medical Imaging: 25th International Conference, IPMI 2017, Boone, NC, USA, June 25-30, 2017, Proceedings.  (pp. pp. 610-621).  Springer: Cham, Switzerland.       Green open access   
 
document_url: https://discovery.ucl.ac.uk/id/eprint/1561200/1/Paper_23_Iglesias.pdf