Owen Carmichael, Ph.D.
Associate Professor and Director of Biomedical Imaging
Associate Professor and Director of Biomedical Imaging
During my postdoctoral fellowship, I focused on automatically localizing two parts of the brain—the hippocampus and the lateral ventricles.
I completed an empirical study of several competing methods for this problem, all of which were unified by the general theme of aligning a patient’s image with a reference image on which the hippocampus has been traced by an expert. One way to distinguish the different methods is by the degree to which they geometrically deform the patient image while aligning it to the reference image. This figure shows how three different techniques deform the patient image:
Note that some of the methods (like “Chen Fully-deformable”) deform the image in a more complicated, irregular way, while some of the other ones (like “AIR Semi-deformable”) deform the image more smoothly and gradually. Our experiments showed that techniques that use the more complicated deformations tend to do a better job at localizing the hippocampus.
Web Site: The University of Pittsburgh Alzheimer Disease Research Center
Publication:
O. Carmichael, H. J. Aizenstein, S. W. Davis, J. T. Becker, P. M. Thompson, C. C. Meltzer, Y. Liu. Atlas-Based Hippocampus Segmentation In Alzheimer’s Disease and Mild Cognitive Impairment. NeuroImage, 27 (4), pg. 979-990, October 1, 2005. DOI ,eScholarship PDF (Much longer version appears as Carnegie Mellon University Robotics Institute Technical Report CMU-RI-TR-04-53, [PDF]).
------------------------------------------------------------------------------------------------------------------
It turns out that these irregular, fully-deformable alignment techniques are useful for other medical image analysis problems related to geriatric imaging. I helped Dr. Michael Gach and his grad student, Weiying Dai, use fully-deformable alignment techniques to align a set of elderly structural/functional images to a common coordinate frame so that atrophy effects are cancelled out. They are using the approach to analyze continuous arterial spin labeling (CASL) images of populations of elderly patients with AD and Mild Cognitive Impairment (MCI).
Web Site: Weiying Dai’s profile page
Publications:
W. Dai, O. L. Lopez, O. T. Carmichael, J. T. Becker, Lewis H. Kuller, H. M. Gach. Mild cognitive impairment and Alzheimer Disease: Patterns of altered cerebral blood flow at MR imaging. Radiology 2009;250:856-866. DOI
W. Dai, O. T. Carmichael, O. L. Lopez, J. T. Becker, L. H. Kuller, H. M. Gach. Effects of image normalization on the statistical analysis of perfusion MRI in elderly brains. J Magn Reson Imaging. 2008 Dec;28(6):1351-60. DOI
W. Dai, O. L. Lopez, O. T. Carmichael, J. T. Becker, Lewis H. Kuller, H. M. Gach. Abnormal regional cerebral blood flow in cognitively normal elderly subjects with hypertension. Stroke, 39(2):349-354, July 2007. DOI
------------------------------------------------------------------------------------------------------------------
Also, I helped Dr. Howard Aizenstein and his grad student, Minjie Wu, use fully-deformable alignment to localize structures and do group-wise analysis in functional MRI (fMRI) images of depressed elderly subjects doing learning tasks.
Web Site: Howard Aizenstein’s web page, Minjie Wu’s web page
Publication:
M. Wu, O. Carmichael, C. S. Carter, J. L. Figurski, P. Lopez-Garcia, & H. J. Aizenstein. Quantitative comparison of neuroimage registration by air, spm, and a fully deformable model. Human Brain Mapping, 27(9), pp. 747-54, September 2006. DOI
------------------------------------------------------------------------------------------------------------------
Fully-deformable image alignment is helpful for a variety of problems, but the problem of how to estimate the deformation is important. That is, what information do you pull out of the two images that gives you a good guess at how to line them up? I helped Leonid Teverovskiy, Dr. Yanxi Liu’s grad student, on a technique for automatically determining which aspects of images (which features) should be used as cues for how to align them. Also, we worked on automatically determining which features are useful for automatically classifying whether images correspond to healthy subjects or those with MCI or AD.
Publication:
Y. Liu, L. Teverovskiy, O. Carmichael, R. Kikinis, M. Shenton, C. Carter, A. Stenger, S. Davis, H. Aizenstein, J. Baker. Discriminative MR Image Feature Analysis for Automatic Schizophrenia and Alzheimer's Disease Classification. CMU RI Technical Report CMU-RI-TR-04-15. Similar version appears in Proceedings of Medical Image Computing and Computer Assisted Intervention (MICCAI) 2004. DOI