Deep Learning Segmentation of the Nucleus Basalis of Meynert on 3T MRI.

BACKGROUND AND PURPOSE: The nucleus basalis of Meynert is a key subcortical structure that is important in arousal and cognition and has been explored as a deep brain stimulation target but is difficult to study due to its small size, variability among patients, and lack of contrast on 3T MR imaging. Thus, our goal was to establish and evaluate a deep learning network for automatic, accurate, and patient-specific segmentations with 3T MR imaging. MATERIALS AND METHODS: Patient-specific segmentations can be produced manually; however, the nucleus basalis of Meynert is difficult to accurately segment on 3T MR imaging, with 7T being preferred. Thus, paired 3T and 7T MR imaging data sets of 21 healthy subjects were obtained. A test data set of 6 subjects was completely withheld. The nucleus was expertly segmented on 7T, providing accurate labels for the paired 3T MR imaging. An external data set of 14 patients with temporal lobe epilepsy was used to test the model on brains with neurologic disorders. A 3D-Unet convolutional neural network was constructed, and a 5-fold cross-validation was performed. RESULTS: The novel segmentation model demonstrated significantly improved Dice coefficients over the standard probabilistic atlas for both healthy subjects (mean, 0.68 [SD, 0.10] versus 0.45 [SD, 0.11], P = .002, t test) and patients (0.64 [SD, 0.10] versus 0.37 [SD, 0.22], P < .001). Additionally, the model demonstrated significantly decreased centroid distance in patients (1.18 [SD, 0.43] mm, 3.09 [SD, 2.56] mm, P = .007). CONCLUSIONS: We developed the first model, to our knowledge, for automatic and accurate patient-specific segmentation of the nucleus basalis of Meynert. This model may enable further study into the nucleus, impacting new treatments such as deep brain stimulation.

Focused stimulation of dorsal subthalamic nucleus improves reactive inhibitory control of action impulses.

Frontal-basal ganglia circuitry dysfunction caused by Parkinson's disease impairs important executive cognitive processes, such as the ability to inhibit impulsive action tendencies. Subthalamic Nucleus Deep Brain Stimulation in Parkinson's disease improves the reactive inhibition of impulsive actions that interfere with goal-directed behavior. An unresolved question is whether this effect depends on stimulation of a particular Subthalamic Nucleus subregion. The current study aimed to 1) replicate previous findings and additionally investigate the effect of chronic versus acute Subthalamic Nucleus stimulation on inhibitory control in Parkinson's disease patients off dopaminergic medication 2) test whether stimulating Subthalamic Nucleus subregions differentially modulate proactive response control and the proficiency of reactive inhibitory control. In the first experiment, twelve Parkinson's disease patients completed three sessions of the Simon task, Off Deep brain stimulation and medication, on acute Deep Brain Stimulation and on chronic Deep Brain Stimulation. Experiment 2 consisted of 11 Parkinson's disease patients with Subthalamic Nucleus Deep Brain Stimulation (off medication) who completed two testing sessions involving of a Simon task either with stimulation of the dorsal or the ventral contact in the Subthalamic Nucleus. Our findings show that Deep Brain Stimulation improves reactive inhibitory control, regardless of medication and regardless of whether it concerns chronic or acute Subthalamic Nucleus stimulation. More importantly, selective stimulation of dorsal and ventral subregions of the Subthalamic Nucleus indicates that especially the dorsal Subthalamic Nucleus circuitries are crucial for modulating the reactive inhibitory control of motor actions.

Segmentation editing improves efficiency while reducing inter-expert variation and maintaining accuracy for normal brain tissues in the presence of space-occupying lesions.

Image segmentation has become a vital and often rate-limiting step in modern radiotherapy treatment planning. In recent years, the pace and scope of algorithm development, and even introduction into the clinic, have far exceeded evaluative studies. In this work we build upon our previous evaluation of a registration driven segmentation algorithm in the context of 8 expert raters and 20 patients who underwent radiotherapy for large space-occupying tumours in the brain. In this work we tested four hypotheses concerning the impact of manual segmentation editing in a randomized single-blinded study. We tested these hypotheses on the normal structures of the brainstem, optic chiasm, eyes and optic nerves using the Dice similarity coefficient, volume, and signed Euclidean distance error to evaluate the impact of editing on inter-rater variance and accuracy. Accuracy analyses relied on two simulated ground truth estimation methods: simultaneous truth and performance level estimation and a novel implementation of probability maps. The experts were presented with automatic, their own, and their peers' segmentations from our previous study to edit. We found, independent of source, editing reduced inter-rater variance while maintaining or improving accuracy and improving efficiency with at least 60% reduction in contouring time. In areas where raters performed poorly contouring from scratch, editing of the automatic segmentations reduced the prevalence of total anatomical miss from approximately 16% to 8% of the total slices contained within the ground truth estimations. These findings suggest that contour editing could be useful for consensus building such as in developing delineation standards, and that both automated methods and even perhaps less sophisticated atlases could improve efficiency, inter-rater variance, and accuracy.

Evaluation of multiple-atlas-based strategies for segmentation of the thyroid gland in head and neck CT images for IMRT.

Segmenting the thyroid gland in head and neck CT images is of vital clinical significance in designing intensity-modulated radiation therapy (IMRT) treatment plans. In this work, we evaluate and compare several multiple-atlas-based methods to segment this structure. Using the most robust method, we generate automatic segmentations for the thyroid gland and study their clinical applicability. The various methods we evaluate range from selecting a single atlas based on one of three similarity measures, to combining the segmentation results obtained with several atlases and weighting their contribution using techniques including a simple majority vote rule, a technique called STAPLE that is widely used in the medical imaging literature, and the similarity between the atlas and the volume to be segmented. We show that the best results are obtained when several atlases are combined and their contributions are weighted with a measure of similarity between each atlas and the volume to be segmented. We also show that with our data set, STAPLE does not always lead to the best results. Automatic segmentations generated by the combination method using the correlation coefficient (CC) between the deformed atlas and the patient volume, which is the most accurate and robust method we evaluated, are presented to a physician as 2D contours and modified to meet clinical requirements. It is shown that about 40% of the contours of the left thyroid and about 42% of the right thyroid can be used directly. An additional 21% on the left and 24% on the right require only minimal modification. The amount and the location of the modifications are qualitatively and quantitatively assessed. We demonstrate that, although challenged by large inter-subject anatomical discrepancy, atlas-based segmentation of the thyroid gland in IMRT CT images is feasible by involving multiple atlases. The results show that a weighted combination of segmentations by atlases using the CC as the similarity measure slightly outperforms standard combination methods, e.g. the majority vote rule and STAPLE, as well as methods selecting a single most similar atlas. The results we have obtained suggest that using our contours as initial contours to be edited has clinical value.

Comparison of manual and automatic segmentation methods for brain structures in the presence of space-occupying lesions: a multi-expert study.

The purpose of this work was to characterize expert variation in segmentation of intracranial structures pertinent to radiation therapy, and to assess a registration-driven atlas-based segmentation algorithm in that context. Eight experts were recruited to segment the brainstem, optic chiasm, optic nerves, and eyes, of 20 patients who underwent therapy for large space-occupying tumors. Performance variability was assessed through three geometric measures: volume, Dice similarity coefficient, and Euclidean distance. In addition, two simulated ground truth segmentations were calculated via the simultaneous truth and performance level estimation algorithm and a novel application of probability maps. The experts and automatic system were found to generate structures of similar volume, though the experts exhibited higher variation with respect to tubular structures. No difference was found between the mean Dice similarity coefficient (DSC) of the automatic and expert delineations as a group at a 5% significance level over all cases and organs. The larger structures of the brainstem and eyes exhibited mean DSC of approximately 0.8-0.9, whereas the tubular chiasm and nerves were lower, approximately 0.4-0.5. Similarly low DSCs have been reported previously without the context of several experts and patient volumes. This study, however, provides evidence that experts are similarly challenged. The average maximum distances (maximum inside, maximum outside) from a simulated ground truth ranged from (-4.3, +5.4) mm for the automatic system to (-3.9, +7.5) mm for the experts considered as a group. Over all the structures in a rank of true positive rates at a 2 mm threshold from the simulated ground truth, the automatic system ranked second of the nine raters. This work underscores the need for large scale studies utilizing statistically robust numbers of patients and experts in evaluating quality of automatic algorithms.

Laser range scanning for image-guided neurosurgery: investigation of image-to-physical space registrations.

In this article a comprehensive set of registration methods is utilized to provide image-to-physical space registration for image-guided neurosurgery in a clinical study. Central to all methods is the use of textured point clouds as provided by laser range scanning technology. The objective is to perform a systematic comparison of registration methods that include both extracranial (skin marker point-based registration (PBR), and face-based surface registration) and intracranial methods (feature PBR, cortical vessel-contour registration, a combined geometry/intensity surface registration method, and a constrained form of that method to improve robustness). The platform facilitates the selection of discrete soft-tissue landmarks that appear on the patient's intraoperative cortical surface and the preoperative gadolinium-enhanced magnetic resonance (MR) image volume, i.e., true corresponding novel targets. In an 11 patient study, data were taken to allow statistical comparison among registration methods within the context of registration error. The results indicate that intraoperative face-based surface registration is statistically equivalent to traditional skin marker registration. The four intracranial registration methods were investigated and the results demonstrated a target registration error of 1.6 +/- 0.5 mm, 1.7 +/- 0.5 mm, 3.9 +/- 3.4 mm, and 2.0 +/- 0.9 mm, for feature PBR, cortical vessel-contour registration, unconstrained geometric/intensity registration, and constrained geometric/intensity registration, respectively. When analyzing the results on a per case basis, the constrained geometric/intensity registration performed best, followed by feature PBR, and finally cortical vessel-contour registration. Interestingly, the best target registration errors are similar to targeting errors reported using bone-implanted markers within the context of rigid targets. The experience in this study as with others is that brain shift can compromise extracranial registration methods from the earliest stages. Based on the results reported here, organ-based approaches to registration would improve this, especially for shallow lesions.

Brain atlas deformation in the presence of small and large space-occupying tumors.

Brain atlases contain a wealth of information that could be used in radiation therapy or neurosurgical planning. Until now, however, when large space-occupying tumors and lesions drastically alter the shape of brain structures and substructures, atlas-based methods have been of limited use. In this work, we present a new technique that permits a brain atlas to be warped onto image volumes in which large lesions are present. First we show that a method previously used for atlas-based segmentation of normal brains can also be used for brains with small lesions. We then present an extension of this technique for brains with large lesions. This involves several steps: a global registration to bring the two volumes into approximate correspondence; a local registration to warp the atlas onto the patient volume; the seeding of the warped atlas with a tumor model derived from patient data; and the deformation of the seeded atlas. Global registration is performed using a mutual information criterion. The method we have used for atlas warping is derived from optical flow principles. Preliminary results obtained on real patient images are presented. These results indicate that the proposed method can be used to automatically segment structures of interest in brains with gross deformation. Potential areas of application for this method include automatic labeling of critical structures for radiation therapy and presurgical planning.

Automatic lumbar vertebral identification using surface-based registration.

This work proposes the use of surface-based registration to automatically select a particular vertebra of interest during surgery. Manual selection of the correct vertebra can be a challenging task, especially for closed-back, minimally invasive procedures. Our method uses shape variations that exist among lumbar vertebrae to automatically determine the portion of the spinal column surface that correctly matches a set of physical vertebral points. In our experiments, we register vertebral points representing posterior elements of a single vertebra in physical space to spinal column surfaces extracted from computed tomography images of multiple vertebrae. After registering the set of physical points to each vertebral surface that is a potential match, we then compute the standard deviation of the surface error for each registration trial. The registration that corresponds to the lowest standard deviation designates the correct match. We have performed our current experiments on two plastic spine phantoms and two patients.

Closing the loop in ICU decision support: physiologic event detection, alerts, and documentation.

Automated physiologic event detection and alerting is a challenging task in the ICU. Ideally care providers should be alerted only when events are clinically significant and there is opportunity for corrective action. However, the concepts of clinical significance and opportunity are difficult to define in automated systems, and effectiveness of alerting algorithms is difficult to measure. This paper describes recent efforts on the Simon project to capture information from ICU care providers about patient state and therapy in response to alerts, in order to assess the value of event definitions and progressively refine alerting algorithms. Event definitions for intracranial pressure and cerebral perfusion pressure were studied by implementing a reliable system to automatically deliver alerts to clinical users alphanumeric pagers, and to capture associated documentation about patient state and therapy when the alerts occurred. During a 6-month test period in the trauma ICU at Vanderbilt University Medical Center, 530 alerts were detected in 2280 hours of data spanning 14 patients. Clinical users electronically documented 81% of these alerts as they occurred. Retrospectively classifying documentation based on therapeutic actions taken, or reasons why actions were not taken, provided useful information about ways to potentially improve event definitions and enhance system utility.

Registration of physical space to laparoscopic image space for use in minimally invasive hepatic surgery.

While laparoscopes are used for numerous minimally invasive (MI) procedures, MI liver resection and ablative surgery is infrequently performed. The paucity of cases is due to the restriction of the field of view by the laparoscope and the difficulty in determining tumor location and margins under video guidance. By merging MI surgery with interactive, image-guided surgery (IIGS), we hope to overcome localization difficulties present in laparoscopic liver procedures. One key component of any IIGS system is the development of accurate registration techniques to map image space to physical or patient space. This manuscript focuses on the accuracy and analysis of the direct linear transformation (DLT) method to register physical space with laparoscopic image space on both distorted and distortion-corrected video images. Experiments were conducted on a liver-sized plastic phantom affixed with 20 markers at various depths. After localizing the points in both physical and laparoscopic image space, registration accuracy was assessed for different combinations and numbers of control points (n) to determine the quantity necessary to develop a robust registration matrix. For n = 11, average target registration error (TRE) was 0.70 +/- 0.20 mm. We also studied the effects of distortion correction on registration accuracy. For the particular distortion correction method and laparoscope used in our experiments, there was no statistical significance between physical to image registration error for distorted and corrected images. In cases where a minimum number of control points (n = 6) are acquired, the DLT is often not stable and the mathematical process can lead to high TRE values. Mathematical filters developed through the analysis of the DLT were used to prospectively eliminate outlier cases where the TRE was high. For n = 6, prefilter average TRE was 17.4 +/- 153 mm for all trials; when the filters were applied, average TRE decreased to 1.64 +/- 1.10 mm for the remaining trials.

Surface registration for use in interactive, image-guided liver surgery.

OBJECTIVE: Liver surgery is difficult because of limited external landmarks, significant vascularity, and inexact definition of intra-hepatic anatomy. Intra-operative ultrasound (IOUS) has been widely used in an attempt to overcome these difficulties, but is limited by its two-dimensional nature, inter-user variability, and image obliteration with ablative or resectional techniques. Because the anatomy of the liver and intra-operative removal of hepatic ligaments make intrinsic or extrinsic point-based registration impractical, we have implemented a surface registration technique to map physical space into CT image space, and have tested the accuracy of this method on an anatomical liver phantom with embedded tumor targets. MATERIALS AND METHODS: Liver phantoms were created from anatomically correct molds with "tumors" embedded within the substance of the liver. Helical CT scans were performed with 3-mm slices. Using an optically active position sensor, the surface of the liver was digitized according to anatomical segments. A surface registration was performed and RMS errors of the locations of internal tumors are presented as verification. An initial point-based marker registration was performed and considered the "gold standard" for error measurement. RESULTS: Errors for surface registration were 2.9 mm for the entire surface and 2.8 mm for embedded targets. CONCLUSION: This is an initial study considering the use of surface registration for the purpose of physical-to-image registration in the area of liver surgery.

Model creation and deformation for the automatic segmentation of the brain in MR images.

In this paper a method for the automatic segmentation of the brain in magnetic resonance images is presented and validated. The proposed method involves two steps 1) the creation of an initial model and 2) the deformation of this model to fit the exact contours of the brain in the images. A new method to create the initial model has been developed and compared to a more traditional approach in which initial models are created by means of brain atlases. A comprehensive validation of the complete segmentation method has been conducted on a series of three-dimensional T1-weighted magnetization-prepared rapid gradient echo image volumes acquired both from control volunteers and patients suffering from Cushing's disease. This validation study compares results obtained with the method we propose and contours drawn manually. Averages differences between manual and automatic segmentation with the model creation method we propose are 1.7% and 2.7% for the control volunteers and the Cushing's patients, respectively. These numbers are 1.8% and 5.6% when the atlas-based method is used.

Retrospective intermodality registration techniques for images of the head: surface-based versus volume-based.

The primary objective of this study is to perform a blinded evaluation of two groups of retrospective image registration techniques, using as a gold standard a prospective marker-based registration method, and to compare the performance of one group with the other. These techniques have already been evaluated individually [27]. In this paper, however, we find that by grouping the techniques as volume based or surface based, we can make some interesting conclusions which were not visible in the earlier study. In order to ensure blindness, all retrospective registrations were performed by participants who had no knowledge of the gold-standard results until after their results had been submitted. Image volumes of three modalities: X-ray computed tomography (CT), magnetic resonance (MR), and positron emission tomography (PET) were obtained from patients undergoing neurosurgery at Vanderbilt University Medical Center on whom bone-implanted fiducial markers were mounted. These volumes had all traces of the markers removed and were provided via the Internet to project collaborators outside Vanderbilt, who then performed retrospective registrations on the volumes, calculating transformations from CT to MR and/or from PET to MR. These investigators communicated their transformations, again via the Internet, to Vanderbilt, where the accuracy of each registration was evaluated. In this evaluation, the accuracy is measured at multiple volumes of interest (VOI's). Our results indicate that the volume-based techniques in this study tended to give substantially more accurate and reliable results than the surface-based ones for the CT-to-MR registration tasks, and slightly more accurate results for the PET-to-MR tasks. Analysis of these results revealed that the rotational component of error was more pronounced for the surface-based group. It was also apparent that all of the registration techniques we examined have the potential to produce satisfactory results much of the time, but that visual inspection is necessary to guard against large errors.

Automatic 3-D segmentation of internal structures of the head in MR images using a combination of similarity and free-form transformations: Part I, Methodology and validation on normal subjects.

The study presented in this paper tests the hypothesis that the combination of a global similarity transformation and local free-form deformations can be used for the accurate segmentation of internal structures in MR images of the brain. To quantitatively evaluate our approach, the entire brain, the cerebellum, and the head of the caudate have been segmented manually by two raters on one of the volumes (the reference volume) and mapped back onto all the other volumes, using the computed transformations. The contours so obtained have been compared to contours drawn manually around the structures of interest in each individual brain. Manual delineation was performed twice by the same two raters to test inter- and intrarater variability. For the brain and the cerebellum, results indicate that for each rater, contours obtained manually and contours obtained automatically by deforming his own atlas are virtually indistinguishable. Furthermore, contours obtained manually by one rater and contours obtained automatically by deforming this rater's own atlas are more similar than contours obtained manually by two raters. For the caudate, manual intra- and interrater similarity indexes remain slightly better than manual versus automatic indexes, mainly because of the spatial resolution of the images used in this study. Qualitative results also suggest that this method can be used for the segmentation of more complex structures, such as the hippocampus.

Automatic 3-D segmentation of internal structures of the head in MR images using a combination of similarity and free-form transformations: Part II, validation on severely atrophied brains.

Studies aimed at quantifying neuroanatomical differences between populations require the volume measurements of individual brain structures. If the study contains a large number of images, manual segmentation is not practical. This study tests the hypothesis that a fully automatic, atlas-based segmentation method can be used to quantify atrophy indexes derived from the brain and cerebellum volumes in normal subjects and chronic alcoholics. This is accomplished by registering an atlas volume with a subject volume, first using a global transformation, and then improving the registration using a local transformation. Segmented structures in the atlas volume are then mapped to the corresponding structures in the subject volume using the combined global and local transformations. This technique has been applied to seven normal and seven alcoholic subjects. Three magnetic resonance volumes were obtained for each subject and each volume was segmented automatically, using the atlas-based method. Accuracy was assessed by manually segmenting regions and measuring the similarity between corresponding regions obtained automatically. Repeatability was determined by comparing volume measurements of segmented structures from each acquisition of the same subject. Results demonstrate that the method is accurate, that the results are repeatable, and that it can provide a method for automatic quantification of brain atrophy, even when the degree of atrophy is large.

Surface-based registration of CT images to physical space for image-guided surgery of the spine: a sensitivity study.

This paper presents a method designed to register preoperative computed tomography (CT) images to vertebral surface points acquired intraoperatively from ultrasound (US) images or via a tracked probe. It also presents a comparison of the registration accuracy achievable with surface points acquired from the entire posterior surface of the vertebra to the accuracy achievable with points acquired only from the spinous process and central laminar regions. Using a marker-based method as a reference, this work shows that submillimetric registration accuracy can be obtained even when a small portion of the posterior vertebral surface is used for registration. It also shows that when selected surface patches are used, CT slice thickness is not a critical parameter in the registration process. Furthermore, the paper includes qualitative results of registering vertebral surface points in US images to multiple CT slices. The method has been tested with US points and physical points on a plastic spine phantom and with simulated data on a patient CT scan.

Image-guided MR spectroscopy volume of interest localization for longitudinal studies.

Longitudinal magnetic resonance spectroscopy (MRS) studies require accurate repositioning of the volume of interest (VOI) over which measurements are made. In this work we present and evaluate a method for the image-guided repositioning of brain volumes of interest. The point-based registration technique we developed allows the repositioning to be performed on-line (i.e. while the patient is in the scanner). MR image volumes were acquired from six subjects, three scans each over the course of a month. During the first scan, two spectroscopy VOIs are visually selected: one in the frontal white matter, the other in the superior cerebellar vermis. The coordinates of 13 internal brain landmarks are also identified. During both subsequent scans, the same 13 landmarks are identified, and the transformation that registers the first set of landmarks to the subsequent set is computed. This result is used to automatically map the position of the spectroscopy VOIs from the first volume to the current volume. For the six subjects evaluated to date, we show an average repositioning error of the spectroscopy VOIs in the order of 1 mm. This accuracy allows us to conclude that any variations in the MR spectra are unlikely to be due to repositioning error.

Comparison and evaluation of retrospective intermodality brain image registration techniques.

PURPOSE: The primary objective of this study is to perform a blinded evaluation of a group of retrospective image registration techniques using as a gold standard a prospective, marker-based registration method. To ensure blindedness, all retrospective registrations were performed by participants who had no knowledge of the gold standard results until after their results had been submitted. A secondary goal of the project is to evaluate the importance of correcting geometrical distortion in MR images by comparing the retrospective registration error in the rectified images, i.e., those that have had the distortion correction applied, with that of the same images before rectification. METHOD: Image volumes of three modalities (CT, MR, and PET) were obtained from patients undergoing neurosurgery at Vanderbilt University Medical Center on whom bone-implanted fiducial markers were mounted. These volumes had all traces of the markers removed and were provided via the Internet to project collaborators outside Vanderbilt, who then performed retrospective registrations on the volumes, calculating transformations from CT to MR and/ or from PET to MR. These investigators communicated their transformations again via the Internet to Vanderbilt, where the accuracy of each registration was evaluated. In this evaluation, the accuracy is measured at multiple volumes of interest (VOIs), i.e., areas in the brain that would commonly be areas of neurological interest. A VOI is defined in the MR image and its centroid c is determined. Then, the prospective registration is used to obtain the corresponding point c' in CT or PET. To this point, the retrospective registration is then applied, producing c" in MR. Statistics are gathered on the target registration error (TRE), which is the distance between the original point c and its corresponding point c". RESULTS: This article presents statistics on the TRE calculated for each registration technique in this study and provides a brief description of each technique and an estimate of both preparation and execution time needed to perform the registration. CONCLUSION: Our results indicate that retrospective techniques have the potential to produce satisfactory results much of the time, but that visual inspection is necessary to guard against large errors.

Web-based data integration and annotation in the intensive care unit.

Integrating patient data to facilitate review and annotation is a challenging task in the intensive care unit (ICU), partially due to the wide variety of proprietary systems and types of data involved. This paper describes SIMON-Web, a Java-based user interface to integrate data from an existing bedside monitoring system and a clinical information system (CIS). SIMON-Web displays graphical data from physiologic monitors and other bedside devices as well as information from the clinical laboratory and physician order-entry systems, and allows users to annotate the data using a point-and-click or free-text interface. By continuing to add functionality to SIMON-Web's extensible user interface, we hope to continue to augment and eventually replace manual care provider data charting in the ICU. As of March, 1997, SIMON-Web has been implemented on two bedside personal computer workstations in the cardiac care unit (CCU) at Vanderbilt University Medical Center.

Effect of geometrical distortion correction in MR on image registration accuracy.

In this article we investigate the effect of geometrical distortion correction in MR images on the accuracy of the registration of X-ray CT and MR head images for both a fiducial marker (extrinsic point) method and a surface-matching technique. We use CT and T2-weighted MR image volumes acquired from seven patients who underwent craniotomies in a stereotactic neurosurgical clinical trial. Each patient had four external markers attached to transcutaneous posts screwed into the outer table of the skull. The MR images are corrected for static field inhomogeneity by using an image rectification technique and corrected for scale distortion (gradient magnitude uncertainty) by using an attached stereotactic frame as an object of known shape and size. We define target registration error (TRE) as the distance between corresponding marker positions after registration and transformation. The accuracy of the fiducial marker method is determined by using each combination of three markers to estimate the transformation and the remaining marker to calculate registration error. Surface-based registration is accomplished by fitting MR contours corresponding to the CSF-dura interface to CT contours derived from the inner surface of the skull. The mean point-based TRE using three noncollinear fiducials improved 34%-from 1.15 to 0.76 mm-after correcting for both static field inhomogeneity and scale distortion. The mean surface-based TRE improved 46%-from 2.20 to 1.19 mm. Correction of geometrical distortion in MR images can significantly improve the accuracy of point-based and surface-based registration of CT and MR head images. Distortion correction can be important in clinical situations such as stereotactic and functional neurosurgery where 1 to 2 mm accuracy is required.