Premium
TH‐A‐WAB‐06: Joint Segmentation and Sequential Registration Based Approach for Computing Artifact‐Free ADC Maps From Multiple DWI‐MRI Sequences in Liver
Author(s) -
Veeraraghavan H,
Do K
Publication year - 2013
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 - 10.1118/1.4815700
Subject(s) - artificial intelligence , centroid , artifact (error) , computer vision , computer science , segmentation , image registration , pattern recognition (psychology) , nuclear medicine , image (mathematics) , medicine
Purpose: To develop an automatic method for motion correction and alignment of multiple DWI‐MRI image sequences in the liver for computing repeatable, artifact‐free ADC maps. Methods: We developed an automatic method that computes artifact‐free, repeatable ADC maps by registering multiple b‐valued DWI‐MRI images of liver. First, various structures of interest are segmented on an arbitrary reference image starting from user drawn lines on those structures. Next, the remaining images are sequentially aligned to the reference by propagating the segmentations from the reference to these images using a mean shift tracking procedure. Sequential alignment registers the closest image to the current reference using B‐spline deformable registration. The closest image is the one that minimizes the centroid distance of the individual structures from itself to those in the reference. Following alignment, the closest image is made the new reference and the process repeated until all images are aligned. The ADC map is computed for the aligned images using least squares fitting. Results: We tested our approach on DWI‐MRI image sequences of the liver for different patients by aligning and computing ADC maps. Each scan contained 5 different DWI sequences (b=0,50,250,350,500). Regardless of the chosen reference, we found that the motion corrected ADC maps removed artifacts particularly on the boundary of tumors in comparison to conventionally computed ADC maps. Furthermore, we also found that the mean ADC values for the tumors computed using motion correction exhibited significantly less variation compared to the mean ADC values of the same tumors computed without motion correction. Finally, our approach also automatically segments the relevant tumors. Conclusion: Our joint segmentation and motion correction based approach generates artifact‐free ADC maps as well as repeatable ADC maps for structures of interest such as tumors located in liver.