skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Automated detection of a prostate Ni-Ti stent in electronic portal images

Abstract

Planning target volumes (PTV) in fractionated radiotherapy still have to be outlined with wide margins to the clinical target volume due to uncertainties arising from daily shift of the prostate position. A recently proposed new method of visualization of the prostate is based on insertion of a thermo-expandable Ni-Ti stent. The current study proposes a new detection algorithm for automated detection of the Ni-Ti stent in electronic portal images. The algorithm is based on the Ni-Ti stent having a cylindrical shape with a fixed diameter, which was used as the basis for an automated detection algorithm. The automated method uses enhancement of lines combined with a grayscale morphology operation that looks for enhanced pixels separated with a distance similar to the diameter of the stent. The images in this study are all from prostate cancer patients treated with radiotherapy in a previous study. Images of a stent inserted in a humanoid phantom demonstrated a localization accuracy of 0.4-0.7 mm which equals the pixel size in the image. The automated detection of the stent was compared to manual detection in 71 pairs of orthogonal images taken in nine patients. The algorithm was successful in 67 of 71 pairs of images. Themore » method is fast, has a high success rate, good accuracy, and has a potential for unsupervised localization of the prostate before radiotherapy, which would enable automated repositioning before treatment and allow for the use of very tight PTV margins.« less

Authors:
; ; ; ;  [1];  [2];  [3];  [3];  [3]
  1. Department of Medical Physics, Aalborg Hospital, University of Aarhus, Aalborg (Denmark)
  2. (CVMT), Aalborg University, Aalborg (Denmark)
  3. (Denmark)
Publication Date:
OSTI Identifier:
20853828
Resource Type:
Journal Article
Resource Relation:
Journal Name: Medical Physics; Journal Volume: 33; Journal Issue: 12; Other Information: DOI: 10.1118/1.2369466; (c) 2006 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
62 RADIOLOGY AND NUCLEAR MEDICINE; ACCURACY; ALGORITHMS; CARCINOMAS; IMAGES; MORPHOLOGY; NICKEL ALLOYS; PHANTOMS; PROSTATE; RADIOTHERAPY; TITANIUM ALLOYS

Citation Formats

Carl, Jesper, Nielsen, Henning, Nielsen, Jane, Lund, Bente, Larsen, Erik Hoejkjaer, Computer Vision and Media Technology Laboratory, Department of Medical Physics, Aalborg Hospital, University of Aarhus, Aalborg, Department of Oncology, Aalborg Hospital, Aalborg, and Department of Urology, Aalborg Hospital, Aalborg. Automated detection of a prostate Ni-Ti stent in electronic portal images. United States: N. p., 2006. Web. doi:10.1118/1.2369466.
Carl, Jesper, Nielsen, Henning, Nielsen, Jane, Lund, Bente, Larsen, Erik Hoejkjaer, Computer Vision and Media Technology Laboratory, Department of Medical Physics, Aalborg Hospital, University of Aarhus, Aalborg, Department of Oncology, Aalborg Hospital, Aalborg, & Department of Urology, Aalborg Hospital, Aalborg. Automated detection of a prostate Ni-Ti stent in electronic portal images. United States. doi:10.1118/1.2369466.
Carl, Jesper, Nielsen, Henning, Nielsen, Jane, Lund, Bente, Larsen, Erik Hoejkjaer, Computer Vision and Media Technology Laboratory, Department of Medical Physics, Aalborg Hospital, University of Aarhus, Aalborg, Department of Oncology, Aalborg Hospital, Aalborg, and Department of Urology, Aalborg Hospital, Aalborg. Fri . "Automated detection of a prostate Ni-Ti stent in electronic portal images". United States. doi:10.1118/1.2369466.
@article{osti_20853828,
title = {Automated detection of a prostate Ni-Ti stent in electronic portal images},
author = {Carl, Jesper and Nielsen, Henning and Nielsen, Jane and Lund, Bente and Larsen, Erik Hoejkjaer and Computer Vision and Media Technology Laboratory and Department of Medical Physics, Aalborg Hospital, University of Aarhus, Aalborg and Department of Oncology, Aalborg Hospital, Aalborg and Department of Urology, Aalborg Hospital, Aalborg},
abstractNote = {Planning target volumes (PTV) in fractionated radiotherapy still have to be outlined with wide margins to the clinical target volume due to uncertainties arising from daily shift of the prostate position. A recently proposed new method of visualization of the prostate is based on insertion of a thermo-expandable Ni-Ti stent. The current study proposes a new detection algorithm for automated detection of the Ni-Ti stent in electronic portal images. The algorithm is based on the Ni-Ti stent having a cylindrical shape with a fixed diameter, which was used as the basis for an automated detection algorithm. The automated method uses enhancement of lines combined with a grayscale morphology operation that looks for enhanced pixels separated with a distance similar to the diameter of the stent. The images in this study are all from prostate cancer patients treated with radiotherapy in a previous study. Images of a stent inserted in a humanoid phantom demonstrated a localization accuracy of 0.4-0.7 mm which equals the pixel size in the image. The automated detection of the stent was compared to manual detection in 71 pairs of orthogonal images taken in nine patients. The algorithm was successful in 67 of 71 pairs of images. The method is fast, has a high success rate, good accuracy, and has a potential for unsupervised localization of the prostate before radiotherapy, which would enable automated repositioning before treatment and allow for the use of very tight PTV margins.},
doi = {10.1118/1.2369466},
journal = {Medical Physics},
number = 12,
volume = 33,
place = {United States},
year = {Fri Dec 15 00:00:00 EST 2006},
month = {Fri Dec 15 00:00:00 EST 2006}
}
  • Purpose: To investigate the feasibility of fully automated detection of fiducial markers implanted into the prostate using portal images acquired with an electronic portal imaging device. Methods and Materials: We have made a direct comparison of 4 different methods (2 template matching-based methods, a method incorporating attenuation and constellation analyses and a cross correlation method) that have been published in the literature for the automatic detection of fiducial markers. The cross-correlation technique requires a-priory information from the portal images, therefore the technique is not fully automated for the first treatment fraction. Images of 7 patients implanted with gold fiducial markersmore » (8 mm in length and 1 mm in diameter) were acquired before treatment (set-up images) and during treatment (movie images) using 1MU and 15MU per image respectively. Images included: 75 anterior (AP) and 69 lateral (LAT) set-up images and 51 AP and 83 LAT movie images. Using the different methods described in the literature, marker positions were automatically identified. Results: The method based upon cross correlation techniques gave the highest percentage detection success rate of 99% (AP) and 83% (LAT) set-up (1MU) images. The methods gave detection success rates of less than 91% (AP) and 42% (LAT) set-up images. The amount of a-priory information used and how it affects the way the techniques are implemented, is discussed. Conclusions: Fully automated marker detection in set-up images for the first treatment fraction is unachievable using these methods and that using cross-correlation is the best technique for automatic detection on subsequent radiotherapy treatment fractions.« less
  • Purpose: In image-guided radiotherapy of prostate cancer defining the clinical target volume often relies on magnetic resonance (MR). The task of transferring the clinical target volume from MR to standard planning computed tomography (CT) is not trivial due to prostate mobility. In this paper, an automatic local registration approach is proposed based on a newly developed removable Ni-Ti prostate stent.Methods: The registration uses the voxel similarity measure mutual information in a two-step approach where the pelvic bones are used to establish an initial registration for the local registration.Results: In a phantom study, the accuracy was measured to 0.97 mm andmore » visual inspection showed accurate registration of all 30 data sets. The consistency of the registration was examined where translation and rotation displacements yield a rotation error of 0.41 Degree-Sign {+-} 0.45 Degree-Sign and a translation error of 1.67 {+-} 2.24 mm.Conclusions: This study demonstrated the feasibility for an automatic local MR-CT registration using the prostate stent.« less
  • The purpose of this report was to evaluate the magnitude of the error that would be introduced if only a lateral (LAT) portal image, as opposed to a pair of orthogonal images, was used to verify and correct daily setup errors and organ motion in external beam radiation therapy (EBRT) of prostate cancer. The 3-dimensional (3D) coordinates of gold markers from 12 consecutive prostate patients were reconstructed using a pair of orthogonal images. The data were re-analyzed using only the LAT images. Couch moves from the 2-dimensional (2D)-only data were compared with the complete 3D data set. The 2D-only datamore » provided couch moves that differed on average from the 3D data by 2.3 {+-} 3.0, 0.0 {+-} 0.0, and 0.8 {+-} 1.0 mm in the Lat, AP, and SI directions, respectively. Along AP and SI axes, the LAT image provided positional information similar to the orthogonal pair. The error along the LAT axis may be acceptable provided lateral margins are large enough. A LAT-only setup protocol reduces patient treatment times and increases patient throughput. In most circumstances, with exceptions such as morbidly obese patients, acquisition of only a LAT image for daily targeting of the prostate will provide adequate positional precision.« less
  • Purpose: Intravascular optical coherence tomography (IV-OCT) is a high-resolution imaging method used to visualize the microstructure of arterial walls in vivo. IV-OCT enables the clinician to clearly observe and accurately measure stent apposition and neointimal coverage of coronary stents, which are associated with side effects such as in-stent thrombosis. In this study, the authors present an algorithm for quantifying stent apposition and neointimal coverage by automatically detecting lumen contours and stent struts in IV-OCT images. Methods: The algorithm utilizes OCT intensity images and their first and second gradient images along the axial direction to detect lumen contours and stent strutmore » candidates. These stent strut candidates are classified into true and false stent struts based on their features, using an artificial neural network with one hidden layer and ten nodes. After segmentation, either the protrusion distance (PD) or neointimal thickness (NT) for each strut is measured automatically. In randomly selected image sets covering a large variety of clinical scenarios, the results of the algorithm were compared to those of manual segmentation by IV-OCT readers. Results: Stent strut detection showed a 96.5% positive predictive value and a 92.9% true positive rate. In addition, case-by-case validation also showed comparable accuracy for most cases. High correlation coefficients (R > 0.99) were observed for PD and NT between the algorithmic and the manual results, showing little bias (0.20 and 0.46 μm, respectively) and a narrow range of limits of agreement (36 and 54 μm, respectively). In addition, the algorithm worked well in various clinical scenarios and even in cases with a low level of stent malapposition and neointimal coverage. Conclusions: The presented automatic algorithm enables robust and fast detection of lumen contours and stent struts and provides quantitative measurements of PD and NT. In addition, the algorithm was validated using various clinical cases to demonstrate its reliability. Therefore, this technique can be effectively utilized for clinical trials on stent-related side effects, including in-stent thrombosis and in-stent restenosis.« less
  • Purpose: To compare the accuracy of imaging modalities, immobilization, localization, and positioning techniques in patients with prostate cancer. Methods and Materials: Thirty-five patients with prostate cancer had gold marker seeds implanted transrectally and were treated with fractionated radiotherapy. Twenty of the 35 patients had limited immobilization; the remaining had a vacuum-based immobilization. Patient positioning consisted of alignment with lasers to skin marks, ultrasound or kilovoltage X-ray imaging, optical guidance using infrared reflectors, and megavoltage electronic portal imaging (EPI). The variance of each positioning technique was compared to the patient position determined from the pretreatment EPI. Results: With limited immobilization, themore » average difference between the skin marks' laser position and EPI pretreatment position is 9.1 {+-} 5.3 mm, the average difference between the skin marks' infrared position and EPI pretreatment position is 11.8 {+-} 7.2 mm, the average difference between the ultrasound position and EPI pretreatment position is 7.0 {+-} 4.6 mm, the average difference between kV imaging and EPI pretreatment position is 3.5 {+-} 3.1 mm, and the average intrafraction movement during treatment is 3.4 {+-} 2.7 mm. For the patients with the vacuum-style immobilization, the average difference between the skin marks' laser position and EPI pretreatment position is 10.7 {+-} 4.6 mm, the average difference between kV imaging and EPI pretreatment position is 1.9 {+-} 1.5 mm, and the average intrafraction movement during treatment is 2.1 {+-} 1.5 mm. Conclusions: Compared with use of skin marks, ultrasound imaging for positioning provides an increased degree of agreement to EPI-based positioning, though not as favorable as kV imaging fiducial seeds. Intrafraction movement during treatment decreases with improved immobilization.« less