Graphics Reference
In-Depth Information
Figure
.
.
Segmentation results are displayed for a sequence of MR images of myocardium in the
space-frequency domain. he top three images display classification results and the bottom three
images show prediction results
Table
.
.
Prediction error rates for a sequence of MR images are reported, where Obj represents the
object, Bg denotes the background, and Total refers to the average error of the whole
image
Frame
Frame
Frame
Feature Obj
Bg
Total
Obj
Bg
Total
Obj
Bg
Total
Space
.
.
.
.
FFT
.
.
.
.
.
.
.
.
.
Gabor
.
.
.
.
.
.
.
.
.
.
.
.
.
.
nance images. hese represent very interesting and challenging applications of com-
putational statistics to medical and biological images in the scientific community.
Further studies of microPET, SPECT and other tomography systems along with
the image fusion of other medical modalities will be challenging topics for the future
development of computational statistics. Dynamic
-Dand
-Dimages generated by
medical imaging modalities, including different applications of tomography images,
color Doppler ultrasound images, fMRI images, molecular images and so forth, will
present special challenges to computational statistics.
Further successes in relation to the development of even more advanced medical
imaging systems in the future can be expected from interdisciplinary collaborations
between researchers in statistics, computation, biological and medical sciences. We
willthenbeabletodevelopandapplystate-of-arttechniquesincomputational statis-
