My recent work on joint segmentation of anatomical and functional images has been accepted for presentation and publication in MICCAI 2012. In this study, I have developed a novel co-segmentation tool which automatically identify significant uptake regions from PET images and simultaneously segment the PET and corresponding CT images in seconds, and with high accuracy. My algorithm is extended from random walk image segmentation in 3D images and synergistically combine the anatomical and functional information in a fully automated way. Joint random walk segmentation has some special properties, which we found it very useful in routine clinics and demonstrated it in the paper. Acceptance rate of the articles submitted to MICCAI this year is around 30%.
Here is the title and the authorship of our article:
Ulas Bagci, Jayaram K. Udupa, Jianhua Yao, Daniel J. Mollura. Co-Segmentation of Functional and Anatomical Images, MICCAI 2012, Accepted. [PDF]
MICCAI 2012, the 15th International Conference on Medical Image Computing and Computer Assisted Intervention, will be held from 1st to 5th October 2012 in Nice, France, organised by Inria (French Institute for Research in Computer Science and Applied Mathematics). MICCAI attracts annually world leading scientists, engineers and clinicians from a wide range of disciplines associated with medical imaging and computer assisted surgery.