Share Email Print

Proceedings Paper

Dental non-linear image registration and collection method with 3D reconstruction and change detection
Author(s): Mark Rahmes; Dean Fagan; George Lemieux
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The capability of a software algorithm to automatically align same-patient dental bitewing and panoramic x-rays over time is complicated by differences in collection perspectives. We successfully used image correlation with an affine transform for each pixel to discover common image borders, followed by a non-linear homography perspective adjustment to closely align the images. However, significant improvements in image registration could be realized if images were collected from the same perspective, thus facilitating change analysis. The perspective differences due to current dental image collection devices are so significant that straightforward change analysis is not possible. To address this, a new custom dental tray could be used to provide the standard reference needed for consistent positioning of a patient’s mouth. Similar to sports mouth guards, the dental tray could be fabricated in standard sizes from plastic and use integrated electronics that have been miniaturized. In addition, the x-ray source needs to be consistently positioned in order to collect images with similar angles and scales. Solving this pose correction is similar to solving for collection angle in aerial imagery for change detection. A standard collection system would provide a method for consistent source positioning using real-time sensor position feedback from a digital x-ray image reference. Automated, robotic sensor positioning could replace manual adjustments. Given an image set from a standard collection, a disparity map between images can be created using parallax from overlapping viewpoints to enable change detection. This perspective data can be rectified and used to create a three-dimensional dental model reconstruction.

Paper Details

Date Published: 9 March 2017
PDF: 8 pages
Proc. SPIE 10132, Medical Imaging 2017: Physics of Medical Imaging, 101325W (9 March 2017); doi: 10.1117/12.2254817
Show Author Affiliations
Mark Rahmes, Harris Corp. (United States)
Dean Fagan, Harris Corp. (United States)
George Lemieux, Harris Corp. (United States)

Published in SPIE Proceedings Vol. 10132:
Medical Imaging 2017: Physics of Medical Imaging
Thomas G. Flohr; Joseph Y. Lo; Taly Gilat Schmidt, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?