D C Yoon1. 1. UCLA School of Dentistry, Section of Oral Radiology, PO Box 951668, Los Angeles, California 90095-1668, USA.
Abstract
OBJECTIVES: To provide a robust and convenient method by which radiographic images can be spatially aligned for digital radiographic subtraction without the use of manually selected reference points. METHODS: An automated method for image alignment is described which begins with the extraction of a large number of edge features (1500 or more pixels) from each of two radiographic images taken of the same anatomical region of a given patient. The features in the first radiograph are paired, pixel by pixel, with those in the second radiograph using a nearest neighbor criterion. The edge features in the first radiograph are aligned with those in the second radiograph by performing an affine transformation that is consistent with the projection geometry for a plantar parallel X-ray beam. Transformation parameters are determined which provide the smallest spatial alignment error between the two sets of equivalent features. These parameters are found by a closed-form analytic solution, thus enabling a computationally efficient implementation. The final transformation is then applied to the entire first image resulting in a close spatial match to the second image. The performance of three dentists using the automatic method was compared with their performance using a manual method of alignment for eight pairs of images. RESULTS: The root mean squared error in image alignment for the automatic method was 14% lower than that with manual alignment. The variability for the automatic method was half that of the maximal method as measured by the residual error. The automatic method was also three times faster than the manual method. CONCLUSIONS: This method could make digital subtraction more accessible to researchers and practising dentists. Batch mode implementation could enable the processing of large volumes of data. Restriction to a region of interest and improved feature extraction could further improve performance.
OBJECTIVES: To provide a robust and convenient method by which radiographic images can be spatially aligned for digital radiographic subtraction without the use of manually selected reference points. METHODS: An automated method for image alignment is described which begins with the extraction of a large number of edge features (1500 or more pixels) from each of two radiographic images taken of the same anatomical region of a given patient. The features in the first radiograph are paired, pixel by pixel, with those in the second radiograph using a nearest neighbor criterion. The edge features in the first radiograph are aligned with those in the second radiograph by performing an affine transformation that is consistent with the projection geometry for a plantar parallel X-ray beam. Transformation parameters are determined which provide the smallest spatial alignment error between the two sets of equivalent features. These parameters are found by a closed-form analytic solution, thus enabling a computationally efficient implementation. The final transformation is then applied to the entire first image resulting in a close spatial match to the second image. The performance of three dentists using the automatic method was compared with their performance using a manual method of alignment for eight pairs of images. RESULTS: The root mean squared error in image alignment for the automatic method was 14% lower than that with manual alignment. The variability for the automatic method was half that of the maximal method as measured by the residual error. The automatic method was also three times faster than the manual method. CONCLUSIONS: This method could make digital subtraction more accessible to researchers and practising dentists. Batch mode implementation could enable the processing of large volumes of data. Restriction to a region of interest and improved feature extraction could further improve performance.
Authors: Polyane M Queiroz; Matheus L Oliveira; Jefferson L O Tanaka; Milton G Soares; Francisco Haiter-Neto; Evelise Ono Journal: Dentomaxillofac Radiol Date: 2016-07-19 Impact factor: 2.419