Premium
A regional registration method to find corresponding mass lesions in temporal mammogram pairs
Author(s) -
Timp Sheila,
van Engeland Saskia,
Karssemeijer Nico
Publication year - 2005
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.1984323
Subject(s) - artificial intelligence , computer science , image registration , measure (data warehouse) , pattern recognition (psychology) , computer vision , medical imaging , mass/lesion , current (fluid) , computed tomography , data mining , radiology , medicine , image (mathematics) , physics , thermodynamics
In this paper we develop an automatic regional registration method to find corresponding masses on prior and current mammograms. The method contains three steps. In the first, we globally align both images. Then, for each mass lesion on the current view, we define a search area on the prior view, which is likely to contain the same mass lesion. Third, at each location in this search area we calculate a registration measure to quantify how well this location matches the mass lesion on the current view. Finally we select the best location. To determine the performance of our method we compare it to several other registration methods. On a dataset of 389 temporal mass pairs our method correctly links 82% of prior and current mass lesions, whereas other methods achieve at most 72%.