Evaluation of cost functions for gray value matching of two-dimensional images in radiotherapy

Abstract

In external beam radiotherapy, portal imaging is applied for verification of the patient setup. Current automatic methods for portal image registration, which are often based on segmentation of anatomical structures, are especially successful for images of the pelvic region. For portal images of more complicated anatomical structures, e.g., lung, these techniques are less successful. It is desirable to have a method for image registration that is applicable for a wide range of treatment sites. In this study, a registration method for two-dimensional (2D) registration of portal and reference images based on intensity values was tested on portal images of various anatomical sites. Tests were performed with and without preprocessing (unsharp mask filtering followed by histogram equalization) for 96 image pairs and six cost functions. The images were obtained from treatments of the rectum, salivary gland, brain, prostate, and lung. To get insight into the behavior of the various cost functions, cost function values were computed for each portal image for 20,000 transformations of the corresponding reference image, translating the reference image in a range of +/- 1 cm and rotating +/- 10 degrees with respect to the clinical match. The automatic match was defined as the transformation associated with the global minimum (found by an exhaustive search). Without preprocessing, the registration reliability was low (less than 27%). With preprocessing, about 90% of the matches were successful, with a difference with our gold standard (manual registration) of about 1 mm and 1 degree SD. All tested cost functions performed similarly. However, the number of local minima using mutual information was larger than for the other tested cost functions. A cost function based on the mean product of the corresponding pixel values had the least number of local minima. In conclusion, gray value based registration of portal images is applicable for a wide range of treatment sites. However, pre-processing of the images is essential.

Binary Segmentation Masks Can Improve Intrasubject Registration Accuracy of Bone Structures in CT Images

“…Our objective was to compare different registration approaches and therefore we used existing quality criteria, that are scrutinized and discussed elsewhere. 5,17,18 Based on a simple simulation with a sphere, we chose SSD, SAD, and XOR, which were most appropriate for our monomodality case and which showed the superiority of reg2 over reg1 for the CT images. It should further be pointed out that MMI and SSD were also used as cost functions of the optimization algorithms, i.e., we did not evaluate the registration quality with a potentially inadequate criterion.…”

A frequency‐based approach to locate common structure for 2D‐3D intensity‐based registration of setup images in prostate radiotherapy

“…A number of 2D-2D [14][15][16][17][18][19][20][21][22][23][24][25] and 2D-3D 12,13,26-35 registration methods have been proposed for the determination of setup errors in pelvic sites. Other 2D-3D registration methods developed for sites other than the pelvis but which use the correlation coefficient or mutual information include the work by Refs.…”

Use of image registration and fusion algorithms and techniques in radiotherapy: Report of the AAPM Radiation Therapy Committee Task Group No. 132

“…One such metric that has proven very effective for registering image data from different modalities is called mutual information (MI). [24][25][26][27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42][43] Mutual information seeks to align voxels whose values have common probabilities of being present in their respective image sets. In Eq.…”