Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: The VESSEL12 study Articles uri icon

authors

  • Rudyanto, R.D.
  • Kerkstra, S.
  • Van Rikxoort, E.M.
  • Fetita, C.
  • Brillet, P.-Y.
  • Lefevre, C.
  • Xue, W.
  • Zhu, X.
  • Liang, J.
  • Öksüz, T.
  • Ünay, D.
  • Kadipaşaogˇlu, K.
  • Estépar, R.S.J.
  • Ross, J.C.
  • Washko, G.R.
  • Prieto, J.-C.
  • Hoyos, M.H.
  • Orkisz, M.
  • Meine, H.
  • Hüllebrand, M.
  • Stöcker, C.
  • Mir, F.L.
  • Naranjo, V.
  • Villanueva, E.
  • Staring, M.
  • Xiao, C.
  • Stoel, B.C.
  • Fabijanska, A.
  • Smistad, E.
  • Elster, A.C.
  • Lindseth, F.
  • Foruzan, A.H.
  • Kiros, R.
  • Popuri, K.
  • Cobzas, D.
  • Jimenez-Carretero, D.
  • Santos, Andrés
  • Ledesma-Carbayo, María J.
  • Helmberger, M.
  • Urschler, M.
  • Pienn, M.
  • Bosboom, D.G.H.
  • Campo, A.
  • Prokop, M.
  • De Jong, P.A.
  • ORTIZ DE SOLÓRZANO, CARLOS
  • MUÑOZ BARRUTIA, MARIA ARRATE
  • Van Ginneken, B.

publication date

  • October 2014

start page

  • 1217

end page

  • 1232

issue

  • 7

volume

  • 18

International Standard Serial Number (ISSN)

  • 1361-8415

Electronic International Standard Serial Number (EISSN)

  • 1361-8423

abstract

  • Abstract: The VESSEL12 (VESsel SEgmentation in the Lung) challenge objectively compares the performance of dif-ferent algorithms to identify vessels in thoracic computed tomography (CT) scans. Vessel segmentation is fundamental in computer aided processing of data generated by 3D imaging modalities. As manual vesselsegmentation is prohibitively time consuming, any real world application requires some form of automa-tion. Several approaches exist for automated vessel segmentation, but judging their relative merits is dif-ficult due to a lack of standardized evaluation. We present an annotated reference dataset containing 20CT scans and propose nine categories to perform a comprehensive evaluation of vessel segmentationalgorithms from both academia and industry.

keywords

  • thoracic computed tomography; lung vessels; algorithm comparison; algorithms; automation; biological organs; medical imaging; algorithm comparison; comparing algorithm; comprehensive evaluation; computed tomography scan; lung vessels; performance analysis; quantitative scoring; vessel segmentation; computerized tomography; algorithm; article; computer aided design; computer assisted tomography; human; image analysis; lung; priority journal; three dimensional imaging; automated pattern recognition; clinical trial; comparative study; computer assisted diagnosis; computer assisted tomography; diagnostic use; multicenter study; netherlands; procedures; radiography; sensitivity; specificity; spain; vascularization; contrast medium; contrast media; humans; pattern recognition; automated; radiographic image interpretation; computer-assisted; tomography; x-ray computed