J. Michael Fitzpatrick

Genetic Algorithms in Noisy Environments

Genetic algorithms are adaptive search techniques which have been used to learn high-performance knowledge structures in reactive environments that provide information in the form of payoff. In general, payoff can be viewed as a noisy function of the structure being evaluated, and the learning task can be viewed as an optimization problem in a noisy environment. Previous studies have shown that genetic algorithms can perform effectively in the presence of noise. This work explores in detail the tradeoffs between the amount of effort spent on evaluating each structure and the number of structures evaluated during a given iteration of the genetic algorithm. Theoretical analysis shows that, in some cases, more efficient search results from less accurate evaluations. Further evidence is provided by a case study in which genetic algorithms are used to obtain good registrations of digital images.

Fiducial point placement and the accuracy of point-based, rigid body registration.

OBJECTIVETo demonstrate that the shape of the configuration of fiducial points is an important factor governing target registration error (TRE) in point-based, rigid registration. METHODSWe consider two clinical situations: cranial neurosurgery and pedicle screw placement. For cranial neurosurgery, we apply theoretical results concerning TRE prediction, which we have previously derived and validated, to three hypothetical fiducial marker configurations. We illustrate the profile of expected TRE for each configuration. For pedicle screw placement, we apply the same theory to a common anatomic landmark configuration (tips of spinous and transverse processes) used for pedicle screw placement, and we estimate the error rate expected in placement of the screw. RESULTSIn the cranial neurosurgery example, we demonstrate that relatively small values of TRE may be achieved by using widely spread fiducial markers and/or placing the centroid of the markers near the target. We also demonstrate that near-collinear marker configurations far from the target may result in large TRE values. In the pedicle screw placement example, we demonstrate that the screw must be approximately 4 mm narrower than the pedicle in which it is implanted to minimize the chance of pedicle violation during placement. CONCLUSIONThe placement of fiducial points is an important factor in minimizing the error rate for point-based, rigid registration. By using as many points as possible, avoiding near-collinear configurations, and ensuring that the centroid of the fiducial points is as near as possible to the target, TREs can be minimized.

Handbook of Medical Imaging, Volume 2. Medical Image Processing and Analysis

Wasting The Book Of MaladiesBeyond Midi The Handbook Of Musical CodesAliens Ufos And Unexplained Encounters Paranormal Investigations2012 Harley Softail Service ManualWood Design Design BooksVehicular Communications And Networks Architectures Protocols Operation And Deployment Woodhead Publishing Series In Electronic And Optical MaterialsX Teams How To Build Teams That Lead Innovate And Succeed 1st EditionCataloging And Classification An IntroductionWave Motion Physics Class 12 Th NotesByzantine Pottery100 Mistakes That Changed History Backfires And Blunders That Collapsed Empires Crashed Economies And Altered The Course Of Our World 100 Mistakes That Changed History Backfires And Blunders That Collapsed Empires Crashed Economies And Altered ThThe Free Energy Device Handbook A Compilation OfYoga Del Sole E Della Luna Per Bambini Piccoli E Grandi BambiniCambridge Business English Certificate Primary Simulation Question Book Listening Cd Romchinese EditionBorneWordpress Creating Visual Web Membership Sites Using Beaver Builder And Insta MemberCitroen Berlingo Van ManualThe Pursuit Of The Soul2018 Weekly Planner Bible Verse Quote Weekly Daily Monthly Planner 2018 8 5 X 11 Calendar Schedule Organizer Bible Verse Quote Weekly Daily 2018 2019 Journal Series Volume 203306 Cat Engine Repair ManualEdinburgh Pocket Map The Perfect Way To Explore Edinburgh MapsAutocourse 2018 Grand Prix CalendarCinese Per Bambini Vol 3 Parlo CineseA Journey Through TransportCalifornia Test Prep Writing Skills Quiz Book Star Writing Grade 2 Covers Revising Editing Vocabulary And GrammarArchbishop A NovelAerei Da Guerra Libro Da Colorare Per Gli AnzianiElementary Statistics By Bluman 7th EditionA Gentle Creature And Other Stories Fyodor DostoyevskyDiscovering Great Artists Hands On Art For Children In The Styles Of The Great Masters Bright Ideas For Learning

The existence of geometrical density—image transformations corresponding to object motion

Proofs are presented which show that under a few, easily realizable restrictions, there exists a geometrical image transformation that produces a change in a density image that is identical to the change that would be produced in the image by the motion of the objects being imaged. Both two and three-dimensional images of three-dimensional scenes are considered subject to restrictions that are appropriate to conventional radiography, computerized axial tomography, gamma-ray scintigraphy, and magnetic resonance imaging. There is no restriction on the motion of the objects being imaged except that they behave as a conserved medium. There is no restriction on formation of the image except that it include convolution with a differentiable point-function. The convolution can be the result of blurring inherent in the acquisition of the image or of explicit image processing. The results have special significance with regard to the problem of motion artifacts in digital subtraction angiography. The case of incompressible flow is considered and comparisons are made with problems in optical flow.

Image-guided surgery: what is the accuracy?

Purpose of review Use of image-guided surgery (IGS) systems in otolaryngology, particularly rhinology, has grown exponentially in recent years. Central to their use is the understanding of the accuracy of each system. The purpose of this review is to discuss the error inherent in all IGS systems. A standardized technique (currently used in the engineering literature) for understanding and reporting error in IGS systems is reviewed. Using this technique, the error of commercially available IGS systems is reviewed. Recent findings The most commonly used IGS systems depend on the conformation of the skin, as opposed to relying on bone-implanted devices. For these systems, mean accuracies 2 mm or less are routinely reported. This finding is independent of fiducial markers (eg, proprietary headsets, skin-affixed markers, or laser scanning of skin surfaces). Techniques of fiducial localization and registration of CT scans to intraoperative anatomy are proprietary to each company. As such, there is great variability in reporting system specifications-particularly error of IGS systems. This lack of standardization makes comparison of one system to another difficult if not impossible. Summary Image-guided surgery systems commonly used in rhinology report mean accuracies of 2 mm or less. Surgeons must be aware that this value represents a mean of a distribution of errors. As such, 95% of the time error can be expected to be less than approximately 1.7 times its mean value. However, outliers (errors much larger and much smaller than the mean) may exist for each IGS intervention. As noted, IGS systems function to complement-not replace-knowledge of surgical anatomy.

Clinical Validation of Percutaneous Cochlear Implant Surgery: Initial Report

Objective: Percutaneous cochlear implant surgery consists of a single drill path from the lateral mastoid cortex to the cochlea via the facial recess. We sought to clinically validate this technique in patients undergoing traditional cochlear implant surgery.

Phantom validation of coregistration of PET and CT for image-guided radiotherapy

Radiotherapy treatment planning integrating positron emission tomography (PET) and computerized tomography (CT) is rapidly gaining acceptance in the clinical setting. Although hybrid systems are available, often the planning CT is acquired on a dedicated system separate from the PET scanner. A limiting factor to using PET data becomes the accuracy of the CT/PET registration. In this work, we use phantom and patient validation to demonstrate a general method for assessing the accuracy of CT/PET image registration and apply it to two multi-modality image registration programs. An IAEA (International Atomic Energy Association) brain phantom and an anthropomorphic head phantom were used. Internal volumes and externally mounted fiducial markers were filled with CT contrast and 18F-fluorodeoxyglucose (FDG). CT, PET emission, and PET transmission images were acquired and registered using two different image registration algorithms. CT/PET Fusion (GE Medical Systems, Milwaukee, WI) is commercially available and uses a semi-automated initial step followed by manual adjustment. Automatic Mutual Information-based Registration (AMIR), developed at our institution, is fully automated and exhibits no variation between repeated registrations. Registration was performed using distinct phantom structures; assessment of accuracy was determined from registration of the calculated centroids of a set of fiducial markers. By comparing structure-based registration with fiducial-based registration, target registration error (TRE) was computed at each point in a three-dimensional (3D) grid that spans the image volume. Identical methods were also applied to patient data to assess CT/PET registration accuracy. Accuracy was calculated as the mean with standard deviation of the TRE for every point in the 3D grid. Overall TRE values for the IAEA brain phantom are: CT/PET Fusion = 1.71 +/- 0.62 mm, AMIR = 1.13 +/- 0.53 mm; overall TRE values for the anthropomorphic head phantom are: CT/PET Fusion = 1.66 +/- 0.53 mm, AMIR = 1.15 +/- 0.48 mm. Precision (repeatability by a single user) measured for CT/PET Fusion: IAEA phantom = 1.59 +/- 0.67 mm and anthropomorphic head phantom = 1.63 +/- 0.52 mm. (AMIR has exact precision and so no measurements are necessary.) One sample patient demonstrated the following accuracy results: CT/PET Fusion = 3.89 +/- 1.61 mm, AMIR = 2.86 +/- 0.60 mm. Semi-automatic and automatic image registration methods may be used to facilitate incorporation of PET data into radiotherapy treatment planning in relatively rigid anatomic sites, such as head and neck. The overall accuracies in phantom and patient images are < 2 mm and < 4 mm, respectively, using either registration algorithm. Registration accuracy may decrease, however, as distance from the initial registration points (CT/PET fusion) or center of the image (AMIR) increases. Additional information provided by PET may improve dose coverage to active tumor subregions and hence tumor control. This study shows that the accuracy obtained by image registration with these two methods is well suited for image-guided radiotherapy.

Accuracy of customized miniature stereotactic platforms.

In this study, a new system was evaluated for implanting deep-brain stimulators based on a one-piece platform for each trajectory customized from a preoperative planning image. During surgery, the platform is attached to skull-implanted posts that extend through the scalp. The platform acts as a miniature stereotactic frame to provide guidance for parallel cannulas as they are advanced through a burr hole to the target. Accuracy is determined from a postoperative CT. For each implantation, the distance between the position observed in the postoperative image and the position calculated relative to the platform from the preoperative image is our measure of error. Because this measure incorporates the surgical error of electrode anchoring, brain shift between preoperative and postoperative scanning, and error in the measurement of the position of the electrode in CT, it will tend to overestimate the true error. The mean error was 2.8 mm for 20 implantations. These data reflect favorably the accuracy of this system when compared with others.

Fiducial registration error and target registration error are uncorrelated

Image-guidance systems based on fiducial registration typically display some measure of registration accuracy based on the goodness of fit of the fiducials. A common measure is fiducial registration error (FRE), which equals the root-meansquare error in fiducial alignment between image space and physical space. It is natural for the surgeon to regard the displayed estimate of error as an indication of the accuracy of the systems ability to provide guidance to surgical targets for a given case. Thus, when the estimate is smaller than usual, it may be assumed that the target registration error (TRE) is likely to be smaller than usual. We show that this assumption, while intuitively convincing, is in fact wrong. We show it in two ways. First, we prove to first order that for a given system with a given level of normally distributed fiducial localization error, all measures of goodness of fit are statistically independent of TRE, and therefore FRE and TRE are uncorrelated. Second, we demonstrate by means of computer simulations that they are uncorrelated for the exact problem as well. Since TRE is the true measure of registration accuracy of importance to the success of the surgery, our results show that no estimate of accuracy for a given patient that is based on goodness of fiducial fit for that patient gives any information whatever about true registration accuracy for that patient. Therefore surgeons should stop using such measures as indicators of registration quality for the patients on whom they are about to operate.

Percutaneous cochlear access using bone-mounted, customized drill guides: demonstration of concept in vitro.

Hypothesis: Percutaneous cochlear access can be performed using bone-mounted drill guides that are custom made on the basis of preintervention computed tomographic scans. Background: We have previously demonstrated the ability to use image guidance based on fiducial markers to obtain percutaneous cochlear access in vitro. A simpler approach that has far less room for application error is to constrict the path of the drill to pass in a predetermined trajectory using a drill guide. Methods: Cadaveric temporal bone specimens (n = 8) were affixed with three bone-implanted fiducial markers. The temporal bone computed tomographic scans were obtained and used in planning a straight trajectory from the mastoid surface to the cochlea without violating the boundaries of the facial recess, namely, the chorda tympani, the incus buttress, and the facial nerve. These surgical plans were used to manufacture a customized drill guide by means of rapid prototyping (MicroTargeting Platform; FHC Inc.; Bowdoinham, ME, U.S.A.) that mounts onto anchor pins previously used to mount fiducial markers. The specimens then underwent traditional mastoidectomy with facial recess. The drill guide was mounted, and a 1-mm drill bit was passed through the guide across the mastoid and the facial recess. The course of the drill bit and its relationship to the boundaries of the facial recess were photographed and measured. Results: Eight cadaveric specimens were subjected to the study protocol. In seven of eight specimens, the drill bit trajectory was accurate; it passed from the lateral cortex to the lateral wall of the cochlea without compromise of any critical structures. In one specimen, the access to the middle ear was achieved, but the incus was hit by the drill. The average shortest distance ± standard deviation from the edge of the drill bit to the boundaries of the facial recess was 0.78 ± 0.56 mm (chorda tympani), 2.00 ± 1.06 mm (incus buttress), and 1.27 ± 0.54 mm (facial nerve). Conclusion: Our study demonstrates the ability to obtain percutaneous cochlear access in vitro using customized drill guides manufactured on the basis of preintervention radiographic studies.