In this paper, we present a new method for three-dimensional (3-D) medical image fusion for assisting the diagnosis or treatment of kidney disorders, especially acute pyelonephritis. This method consists of three steps: boundary detection, shape analysis and 3-D registration. The boundary detection of the organs was achieved by analyzing texture and intensity variation from SPECT and ultrasound images. A binary shape analysis technique was designed to detect lesion areas. Subsequently, we utilized surface fitting over the boundaries with fast initial pose estimation to integrate images from two different modalities. Experimental results show that the proposed method successfully visualized the functional distribution onto anatomical structure of kidney and assisting physicians to accurately locate the lesion of acute pyelonephritis.
|Number of pages||5|
|Journal||Journal of Medical and Biological Engineering|
|Publication status||Published - 2006 Jun|
All Science Journal Classification (ASJC) codes
- Biomedical Engineering