Computation of the mid-sagittal plane in 3-D brain images

Symmetry of computerised tomography of the brain in traumatic brain injury: a quality improvement audit

BACKGROUND

Non-contrast Computerised Tomography (NCCT) of brain is the gold standard investigation for diagnosis and management of Traumatic brain injury (TBI). Asymmetrical CT brain images as a result of improper head positioning in the CT gantry will compromise the diagnostic value. Therefore, this audit aimed to assess the degree of asymmetry in CT brain studies carried out in TBI patients.

METHODS

This audit was carried out at a level one trauma centre and included CT scans of TBI patients with a Glasgow come scale (GCS) score ≤ 13, admitted to the Neurological intensive care unit (NICU). The first cycle involved a period of three months. The data collected included demographic data and variables such as GCS at the time of the scan and whether the patient was intubated or not. The visualisation of bilateral internal auditory meatuses was used as landmark to determine scan symmetry. If the internal auditory meatus on both sides were visible on the same slice of CT scan, it was considered symmetric. The degree of asymmetry was gauged based on the axial slice difference between bilateral meatuses. The data collected was tabulated and presented to Neurosurgery residents and a checklist was formulated which had to be followed while positioning the patient on CT table prior to imaging.

RESULTS

The first cycle of the audit showed that 83.8% of scans were asymmetric and among them 44.1% revealed gross asymmetry affecting interpretation of the scan. Following, implementation of the checklist the percentage of gross asymmetry dropped to 21.86% in the second and to 22.22% in the third audit.

CONCLUSION

The use of checklist prior to CT brain studies showed sustainable improvement in reducing gross asymmetry and in acquisition of symmetrical CT brain images.

A new approach to symmetric registration of longitudinal structural MRI of the human brain

BACKGROUND

This paper presents the Automatic Temporal Registration Algorithm (ATRA) for symmetric rigid-body registration of longitudinal T1-weighted three-dimensional MRI scans of the human brain. This is a fundamental processing step in computational neuroimaging.

NEW METHOD

The notion of leave-one-out consistent (LOOC) landmarks with respect to a supervised landmark detection algorithm is introduced. An automatic algorithm is presented for identification of LOOC landmarks on MRI scans. Multiple sets of LOOC landmarks are identified on each volume and a Generalized Orthogonal Procrustes Analysis of the landmarks is used to find a rigid-body transformation of each volume into a common space where the volumes are aligned precisely.

RESULTS

Qualitative and quantitative evaluations of ATRA registration accuracy were performed using 2012 volumes from 503 subjects (4 longitudinal volumes/subject), and on a further 120 volumes acquired from 3 normal subjects (40 longitudinal volumes/subject). Since the ground truth registrations are unknown, we devised a novel method for showing that ATRA's registration accuracy is at least better than 0.5 mm translation or 0.5° rotation.

COMPARISON WITH EXISTING METHOD(S)

In comparison with existing methods, ATRA does not require any image preprocessing (e.g., skull-stripping or intensity normalization) and can handle conditions where rigid-body motion assumptions are not true (e.g., movement in eyes, jaw, neck) and brain tissue loss over time in neurodegenerative diseases. In a systematic comparison with the FSL FLIRT algorithm, ATRA provided faster and more accurate registrations.

CONCLUSIONS

The algorithm is symmetric, in the sense that any permutation of the input volumes does not change the transformation matrices, and unbiased, in that all volumes undergo exactly one interpolation operation, which precisely aligns them in a common space. There is no interpolation bias and no reference volume. All volumes are treated exactly the same. The algorithm is fast and highly accurate.

Content-Based Estimation of Brain MRI Tilt in Three Orthogonal Directions

In a general scenario, the brain images acquired from magnetic resonance imaging (MRI) may experience tilt, distorting brain MR images. The tilt experienced by the brain MR images may result in misalignment during image registration for medical applications. Manually correcting (or estimating) the tilt on a large scale is time-consuming, expensive, and needs brain anatomy expertise. Thus, there is a need for an automatic way of performing tilt correction in three orthogonal directions (X, Y, Z). The proposed work aims to correct the tilt automatically by measuring the pitch angle, yaw angle, and roll angle in X-axis, Z-axis, and Y-axis, respectively. For correction of the tilt around the Z-axis (pointing to the superior direction), image processing techniques, principal component analysis, and similarity measures are used. Also, for correction of the tilt around the X-axis (pointing to the right direction), morphological operations, and tilt correction around the Y-axis (pointing to the anterior direction), orthogonal regression is used. The proposed approach was applied to adjust the tilt observed in the T1- and T2-weighted MR images. The simulation study with the proposed algorithm yielded an error of 0.40 ± 0.09°, and it outperformed the other existing studies. The tilt angle (in degrees) obtained is ranged from 6.2 ± 3.94, 2.35 ± 2.61, and 5 ± 4.36 in X-, Z-, and Y-directions, respectively, by using the proposed algorithm. The proposed work corrects the tilt more accurately and robustly when compared with existing studies.

Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets

Brain tissue segmentation from multimodal MRI is a key building block of many neuroimaging analysis pipelines. Established tissue segmentation approaches have, however, not been developed to cope with large anatomical changes resulting from pathology, such as white matter lesions or tumours, and often fail in these cases. In the meantime, with the advent of deep neural networks (DNNs), segmentation of brain lesions has matured significantly. However, few existing approaches allow for the joint segmentation of normal tissue and brain lesions. Developing a DNN for such a joint task is currently hampered by the fact that annotated datasets typically address only one specific task and rely on task-specific imaging protocols including a task-specific set of imaging modalities. In this work, we propose a novel approach to build a joint tissue and lesion segmentation model from aggregated task-specific hetero-modal domain-shifted and partially-annotated datasets. Starting from a variational formulation of the joint problem, we show how the expected risk can be decomposed and optimised empirically. We exploit an upper bound of the risk to deal with heterogeneous imaging modalities across datasets. To deal with potential domain shift, we integrated and tested three conventional techniques based on data augmentation, adversarial learning and pseudo-healthy generation. For each individual task, our joint approach reaches comparable performance to task-specific and fully-supervised models. The proposed framework is assessed on two different types of brain lesions: White matter lesions and gliomas. In the latter case, lacking a joint ground-truth for quantitative assessment purposes, we propose and use a novel clinically-relevant qualitative assessment methodology.

Regional brain development analysis through registration using anisotropic similarity, a constrained affine transformation

We propose a novel method to quantify brain growth in 3 arbitrary orthogonal directions of the brain or its sub-regions through linear registration. This is achieved by introducing a 9 degrees of freedom (dof) transformation called anisotropic similarity which is an affine transformation with constrained scaling directions along arbitrarily chosen orthogonal vectors. This gives the opportunity to extract scaling factors describing brain growth along those directions by registering a database of subjects onto a common reference. This information about directional growth brings insights that are not usually available in longitudinal volumetric analysis. The interest of this method is illustrated by studying the anisotropic regional and global brain development of 308 healthy subjects betwen 0 and 19 years old. A gender comparison of those scaling factors is also performed for four age-intervals. We demonstrate through these applications the stability of the method to the chosen reference and its ability to highlight growth differences accros regions and gender.

An Efficient Automatic Midsagittal Plane Extraction in Brain MRI

In this paper, a fully automatic and computationally efficient midsagittal plane (MSP) extraction technique in brain magnetic resonance images (MRIs) has been proposed. Automatic detection of MSP in neuroimages can significantly aid in registration of medical images, asymmetric analysis, and alignment or tilt correction (recenter and reorientation) in brain MRIs. The parameters of MSP are estimated in two steps. In the first step, symmetric features and principal component analysis (PCA)-based technique is used to vertically align the bilateral symmetric axis of the brain. In the second step, PCA is used to achieve a set of parallel lines (principal axes) from the selected two-dimensional (2-D) elliptical slices of brain MRIs, followed by a plane fitting using orthogonal regression. The developed algorithm has been tested on 157 real T1-weighted brain MRI datasets including 14 cases from the patients with brain tumors. The presented algorithm is compared with a state-of-the-art approach based on bilateral symmetry maximization. Experimental results revealed that the proposed algorithm is fast (<1.04 s per MRI volume) and exhibits superior performance in terms of accuracy and precision (a mean z-distance of 0.336 voxels and a mean angle difference of 0.06).

Brain Midline Shift Measurement and Its Automation: A Review of Techniques and Algorithms

Midline shift (MLS) of the brain is an important feature that can be measured using various imaging modalities including X-ray, ultrasound, computed tomography, and magnetic resonance imaging. Shift of midline intracranial structures helps diagnosing intracranial lesions, especially traumatic brain injury, stroke, brain tumor, and abscess. Being a sign of increased intracranial pressure, MLS is also an indicator of reduced brain perfusion caused by an intracranial mass or mass effect. We review studies that used the MLS to predict outcomes of patients with intracranial mass. In some studies, the MLS was also correlated to clinical features. Automated MLS measurement algorithms have significant potentials for assisting human experts in evaluating brain images. In symmetry-based algorithms, the deformed midline is detected and its distance from the ideal midline taken as the MLS. In landmark-based ones, MLS was measured following identification of specific anatomical landmarks. To validate these algorithms, measurements using these algorithms were compared to MLS measurements made by human experts. In addition to measuring the MLS on a given imaging study, there were newer applications of MLS that included comparing multiple MLS measurement before and after treatment and developing additional features to indicate mass effect. Suggestions for future research are provided.

Computational and mathematical methods in brain atlasing

Brain atlases have a wide range of use from education to research to clinical applications. Mathematical methods as well as computational methods and tools play a major role in the process of brain atlas building and developing atlas-based applications. Computational methods and tools cover three areas: dedicated editors for brain model creation, brain navigators supporting multiple platforms, and atlas-assisted specific applications. Mathematical methods in atlas building and developing atlas-aided applications deal with problems in image segmentation, geometric body modelling, physical modelling, atlas-to-scan registration, visualisation, interaction and virtual reality. Here I overview computational and mathematical methods in atlas building and developing atlas-assisted applications, and share my contribution to and experience in this field.

On-site Rapid Diagnosis of Intracranial Hematoma using Portable Multi-slice Microwave Imaging System

Rapid, on-the-spot diagnostic and monitoring systems are vital for the survival of patients with intracranial hematoma, as their conditions drastically deteriorate with time. To address the limited accessibility, high costs and static structure of currently used MRI and CT scanners, a portable non-invasive multi-slice microwave imaging system is presented for accurate 3D localization of hematoma inside human head. This diagnostic system provides fast data acquisition and imaging compared to the existing systems by means of a compact array of low-profile, unidirectional antennas with wideband operation. The 3D printed low-cost and portable system can be installed in an ambulance for rapid on-site diagnosis by paramedics. In this paper, the multi-slice head imaging system’s operating principle is numerically analysed and experimentally validated on realistic head phantoms. Quantitative analyses demonstrate that the multi-slice head imaging system is able to generate better quality reconstructed images providing 70% higher average signal to clutter ratio, 25% enhanced maximum signal to clutter ratio and with around 60% hematoma target localization compared to the previous head imaging systems. Nevertheless, numerical and experimental results demonstrate that previous reported 2D imaging systems are vulnerable to localization error, which is overcome in the presented multi-slice 3D imaging system. The non-ionizing system, which uses safe levels of very low microwave power, is also tested on human subjects. Results of realistic phantom and subjects demonstrate the feasibility of the system in future preclinical trials.

volBrain: An Online MRI Brain Volumetry System

The amount of medical image data produced in clinical and research settings is rapidly growing resulting in vast amount of data to analyze. Automatic and reliable quantitative analysis tools, including segmentation, allow to analyze brain development and to understand specific patterns of many neurological diseases. This field has recently experienced many advances with successful techniques based on non-linear warping and label fusion. In this work we present a novel and fully automatic pipeline for volumetric brain analysis based on multi-atlas label fusion technology that is able to provide accurate volumetric information at different levels of detail in a short time. This method is available through the volBrain online web interface (http://volbrain.upv.es), which is publically and freely accessible to the scientific community. Our new framework has been compared with current state-of-the-art methods showing very competitive results.

Design and Experimental Evaluation of a Non-Invasive Microwave Head Imaging System for Intracranial Haemorrhage Detection

An intracranial haemorrhage is a life threatening medical emergency, yet only a fraction of the patients receive treatment in time, primarily due to the transport delay in accessing diagnostic equipment in hospitals such as Magnetic Resonance Imaging or Computed Tomography. A mono-static microwave head imaging system that can be carried in an ambulance for the detection and localization of intracranial haemorrhage is presented. The system employs a single ultra-wideband antenna as sensing element to transmit signals in low microwave frequencies towards the head and capture backscattered signals. The compact and low-profile antenna provides stable directional radiation patterns over the operating bandwidth in both near and far-fields. Numerical analysis of the head imaging system with a realistic head model in various situations is performed to realize the scattering mechanism of haemorrhage. A modified delay-and-summation back-projection algorithm, which includes effects of surface waves and a distance-dependent effective permittivity model, is proposed for signal and image post-processing. The efficacy of the automated head imaging system is evaluated using a 3D-printed human head phantom with frequency dispersive dielectric properties including emulated haemorrhages with different sizes located at different depths. Scattered signals are acquired with a compact transceiver in a mono-static circular scanning profile. The reconstructed images demonstrate that the system is capable of detecting haemorrhages as small as 1 cm³. While quantitative analyses reveal that the quality of images gradually degrades with the increase of the haemorrhage’s depth due to the reduction of signal penetration inside the head; rigorous statistical analysis suggests that substantial improvement in image quality can be obtained by increasing the data samples collected around the head. The proposed head imaging prototype along with the processing algorithm demonstrates its feasibility for potential use in ambulances as an effective and low cost diagnostic tool to assure timely triaging of intracranial hemorrhage patients.

Optimal Symmetric Multimodal Templates and Concatenated Random Forests for Supervised Brain Tumor Segmentation (Simplified) with ANTsR

Segmenting and quantifying gliomas from MRI is an important task for diagnosis, planning intervention, and for tracking tumor changes over time. However, this task is complicated by the lack of prior knowledge concerning tumor location, spatial extent, shape, possible displacement of normal tissue, and intensity signature. To accommodate such complications, we introduce a framework for supervised segmentation based on multiple modality intensity, geometry, and asymmetry feature sets. These features drive a supervised whole-brain and tumor segmentation approach based on random forest-derived probabilities. The asymmetry-related features (based on optimal symmetric multimodal templates) demonstrate excellent discriminative properties within this framework. We also gain performance by generating probability maps from random forest models and using these maps for a refining Markov random field regularized probabilistic segmentation. This strategy allows us to interface the supervised learning capabilities of the random forest model with regularized probabilistic segmentation using the recently developed ANTsR package--a comprehensive statistical and visualization interface between the popular Advanced Normalization Tools (ANTs) and the R statistical project. The reported algorithmic framework was the top-performing entry in the MICCAI 2013 Multimodal Brain Tumor Segmentation challenge. The challenge data were widely varying consisting of both high-grade and low-grade glioma tumor four-modality MRI from five different institutions. Average Dice overlap measures for the final algorithmic assessment were 0.87, 0.78, and 0.74 for "complete", "core", and "enhanced" tumor components, respectively.

Estimation of vocal fold plane in 3D CT images for diagnosis of vocal fold abnormalities

Vocal folds are the key body structures that are responsible for phonation and regulating air movement into and out of lungs. Various vocal fold disorders may seriously impact the quality of life. When diagnosing vocal fold disorders, CT of the neck is the commonly used imaging method. However, vocal folds do not align with the normal axial plane of a neck and the plane containing vocal cords and arytenoids does vary during phonation. It is therefore important to generate an algorithm for detecting the actual plane containing vocal folds. In this paper, we propose a method to automatically estimate the vocal fold plane using vertebral column and anterior commissure localization. Gray-level thresholding, connected component analysis, rule based segmentation and unsupervised k-means clustering were used in the proposed algorithm. The anterior commissure segmentation method achieved an accuracy of 85%, a good estimate of the expert assessment.

Shape analysis of the human brain: a brief survey

The survey outlines and compares popular computational techniques for quantitative description of shapes of major structural parts of the human brain, including medial axis and skeletal analysis, geodesic distances, Procrustes analysis, deformable models, spherical harmonics, and deformation morphometry, as well as other less widely used techniques. Their advantages, drawbacks, and emerging trends, as well as results of applications, in particular, for computer-aided diagnostics, are discussed.

Automatic extraction of the midsagittal surface from brain MR Images using the Kullback-Leibler measure

The midsagittal surface separates the two hemispheres of the cerebrum. This surface is often typified as a geometrical plane: the midsagittal plane. However, in subjects with a considerable amount of naturally occurring brain torque, the midsagittal surface deviates to a large extent from a plane. In the present study, an automated method to extract the midsagittal surface is proposed, evaluated on a large dataset, and compared to a conventional midsagittal plane representation. The midsagittal plane was extracted from MR images with a technique based on the Kullback-Leibler measure. This plane was used to initialize a surface, that was deformed to represent the midsagittal surface. One hundred subjects were selected from the SMART-MR study: fifty subjects with brain torque and fifty random subjects. Manual delineations of the midsagittal surface were used for evaluation. The extracted midsagittal planes and surfaces were compared to the manual delineations by assessing the absolute volume of misclassified cerebrum tissue. The midsagittal surface resulted in significantly better separations of the hemispheres. In the randomly selected subjects, the error reduced from 2.71 ± 1.05 ml to 2.20 ± 0.66 ml and in subjects with brain torque from 4.85±2.79 ml to 2.23±0.77 ml, with improvements up to 16.6 ml in individual subjects with marked brain torque.

Evaluation of coils for imaging histological slides: signal-to-noise ratio and filling factor

PURPOSE

To investigate the relative gain in sensitivity of five histology coils designed in-house to accommodate tissue sections of various sizes and compare with commercial mouse head coils.

METHODS

The coil set was tailored to house tissue sections ranging from 5 to1000 µm encased in either glass slides or coverslips.

RESULTS

Our simulations and experimental measurements demonstrated that although the sensitivity of this flat structure consistently underperforms relative to a birdcage head coil based on the gain expected from their respective filling factor ratios, our results demonstrate that it can still provide a remarkable gain in sensitivity. Our study also describes preparation protocols for freshly excised sections, as well as premounted tissue slides of both mouse and human specimens. Examples of the exceptional level of tissue detail and the near-perfect magnetic resonance imaging to light microscopic image coregistration are provided.

CONCLUSION

The increase in filling factor achieved by the histology radiofrequency (RF) probe overcomes the losses associated with electric leaks inherent to this structure, leading to a 6.7-fold improvement in performance for the smallest coil implemented. Alternatively, the largest histology coil design exhibited equal sensitivity to the mouse head coil while nearly doubling the RF planar area coverage.

Midsagittal plane extraction from brain images based on 3D SIFT

Midsagittal plane (MSP) extraction from 3D brain images is considered as a promising technique for human brain symmetry analysis. In this paper, we present a fast and robust MSP extraction method based on 3D scale-invariant feature transform (SIFT). Unlike the existing brain MSP extraction methods, which mainly rely on the gray similarity, 3D edge registration or parameterized surface matching to determine the fissure plane, our proposed method is based on distinctive 3D SIFT features, in which the fissure plane is determined by parallel 3D SIFT matching and iterative least-median of squares plane regression. By considering the relative scales, orientations and flipped descriptors between two 3D SIFT features, we propose a novel metric to measure the symmetry magnitude for 3D SIFT features. By clustering and indexing the extracted SIFT features using a k-dimensional tree (KD-tree) implemented on graphics processing units, we can match multiple pairs of 3D SIFT features in parallel and solve the optimal MSP on-the-fly. The proposed method is evaluated by synthetic and in vivo datasets, of normal and pathological cases, and validated by comparisons with the state-of-the-art methods. Experimental results demonstrated that our method has achieved a real-time performance with better accuracy yielding an average yaw angle error below 0.91° and an average roll angle error no more than 0.89°.

Automatic segmentation of intra-cochlear anatomy in post-implantation CT of unilateral cochlear implant recipients

A cochlear implant (CI) is a neural prosthetic device that restores hearing by directly stimulating the auditory nerve using an electrode array that is implanted in the cochlea. In CI surgery, the surgeon accesses the cochlea and makes an opening where he/she inserts the electrode array blind to internal structures of the cochlea. Because of this, the final position of the electrode array relative to intra-cochlear anatomy is generally unknown. We have recently developed an approach for determining electrode array position relative to intra-cochlear anatomy using a pre- and a post-implantation CT. The approach is to segment the intra-cochlear anatomy in the pre-implantation CT, localize the electrodes in the post-implantation CT, and register the two CTs to determine relative electrode array position information. Currently, we are using this approach to develop a CI programming technique that uses patient-specific spatial information to create patient-customized sound processing strategies. However, this technique cannot be used for many CI users because it requires a pre-implantation CT that is not always acquired prior to implantation. In this study, we propose a method for automatic segmentation of intra-cochlear anatomy in post-implantation CT of unilateral recipients, thus eliminating the need for pre-implantation CTs in this population. The method is to segment the intra-cochlear anatomy in the implanted ear using information extracted from the normal contralateral ear and to exploit the intra-subject symmetry in cochlear anatomy across ears. To validate our method, we performed experiments on 30 ears for which both a pre- and a post-implantation CT are available. The mean and the maximum segmentation errors are 0.224 and 0.734mm, respectively. These results indicate that our automatic segmentation method is accurate enough for developing patient-customized CI sound processing strategies for unilateral CI recipients using a post-implantation CT alone.

Automated interhemispheric surface extraction in T1-weighted MRI using intensity and symmetry information

BACKGROUND

Localizing the human interhemispheric region is of interest in image analysis mainly because it can be used for hemisphere separation and as a preprocessing step for interhemispheric structure localization. Many existing methods focus on only one of these applications.

NEW METHOD

Here a new Intensity and Symmetry based Interhemispheric Surface extraction method (ISIS) that enables both applications is presented. A combination of voxel intensity and local symmetry is used to optimize a surface from T1-weighted MRI.

RESULTS

ISIS was evaluated in regard to cerebral hemisphere separation using manual segmentations. It was also evaluated in regard to being a preprocessing step for interhemispheric structure localization using manually placed landmarks.

COMPARISON WITH EXISTING METHODS

Results were compared to cerebral hemisphere separations by BrainVisa and Freesurfer as well as to a midsagittal plane (MSP) extraction method. ISIS had less misclassified voxels than BrainVisa (ISIS: 0.119±0.114%, BrainVisa: 0.138±0.084%, p=0.020). Freesurfer had less misclassified voxels than ISIS for one dataset (ISIS: 0.063±0.056%, Freesurfer: 0.049±0.044%, p=0.019), but failed to produce usable results for another. Total voxel distance from all manual landmarks did not differ significantly between ISIS and the MSP method (ISIS: 4.00±1.88, MSP: 4.47±4.97).

CONCLUSIONS

ISIS was found successful in both cerebral hemisphere separation and as a preprocessing step for interhemispheric structure localization. It needs no time consuming preprocessing and extracts the interhemispheric surface in less than 30 s.

Fully automated segmentation of the pons and midbrain using human T1 MR brain images

Purpose

This paper describes a novel method to automatically segment the human brainstem into midbrain and pons, called LABS: Landmark-based Automated Brainstem Segmentation. LABS processes high-resolution structural magnetic resonance images (MRIs) according to a revised landmark-based approach integrated with a thresholding method, without manual interaction.

Methods

This method was first tested on morphological T1-weighted MRIs of 30 healthy subjects. Its reliability was further confirmed by including neurological patients (with Alzheimer's Disease) from the ADNI repository, in whom the presence of volumetric loss within the brainstem had been previously described. Segmentation accuracies were evaluated against expert-drawn manual delineation. To evaluate the quality of LABS segmentation we used volumetric, spatial overlap and distance-based metrics.

Results

The comparison between the quantitative measurements provided by LABS against manual segmentations revealed excellent results in healthy controls when considering either the midbrain (DICE measures higher that 0.9; Volume ratio around 1 and Hausdorff distance around 3) or the pons (DICE measures around 0.93; Volume ratio ranging 1.024–1.05 and Hausdorff distance around 2). Similar performances were detected for AD patients considering segmentation of the pons (DICE measures higher that 0.93; Volume ratio ranging from 0.97–0.98 and Hausdorff distance ranging 1.07–1.33), while LABS performed lower for the midbrain (DICE measures ranging 0.86–0.88; Volume ratio around 0.95 and Hausdorff distance ranging 1.71–2.15).

Conclusions

Our study represents the first attempt to validate a new fully automated method for in vivo segmentation of two anatomically complex brainstem subregions. We retain that our method might represent a useful tool for future applications in clinical practice.

Multi-Sectional Views Textural Based SVM for MS Lesion Segmentation in Multi-Channels MRIs

In this paper, a new technique is proposed for automatic segmentation of multiple sclerosis (MS) lesions from brain magnetic resonance imaging (MRI) data. The technique uses a trained support vector machine (SVM) to discriminate between the blocks in regions of MS lesions and the blocks in non-MS lesion regions mainly based on the textural features with aid of the other features. The classification is done on each of the axial, sagittal and coronal sectional brain view independently and the resultant segmentations are aggregated to provide more accurate output segmentation. The main contribution of the proposed technique described in this paper is the use of textural features to detect MS lesions in a fully automated approach that does not rely on manually delineating the MS lesions. In addition, the technique introduces the concept of the multi-sectional view segmentation to produce verified segmentation. The proposed textural-based SVM technique was evaluated using three simulated datasets and more than fifty real MRI datasets. The results were compared with state of the art methods. The obtained results indicate that the proposed method would be viable for use in clinical practice for the detection of MS lesions in MRI.

Multi-Sectional Views Textural Based SVM for MS Lesion Segmentation in Multi-Channels MRIs

In this paper, a new technique is proposed for automatic segmentation of multiple sclerosis (MS) lesions from brain magnetic resonance imaging (MRI) data. The technique uses a trained support vector machine (SVM) to discriminate between the blocks in regions of MS lesions and the blocks in non-MS lesion regions mainly based on the textural features with aid of the other features. The classification is done on each of the axial, sagittal and coronal sectional brain view independently and the resultant segmentations are aggregated to provide more accurate output segmentation. The main contribution of the proposed technique described in this paper is the use of textural features to detect MS lesions in a fully automated approach that does not rely on manually delineating the MS lesions. In addition, the technique introduces the concept of the multi-sectional view segmentation to produce verified segmentation. The proposed textural-based SVM technique was evaluated using three simulated datasets and more than fifty real MRI datasets. The results were compared with state of the art methods. The obtained results indicate that the proposed method would be viable for use in clinical practice for the detection of MS lesions in MRI.

TRACING THE DEFORMED MIDLINE ON BRAIN CT

Midline shift (MLS) is the most important quantitative feature clinicians use to evaluate the severity of brain compression by various pathologies. We proposed a model of the deformed midline according to the biomechanical properties of different types of intracranial tissue. The model comprised three segments. The upper and lower straight segments represented parts of the tough meninges separating two hemispheres, and the central curved segment, formed by a quadratic Bezier curve, represented the intervening soft brain tissue. For each point of the model, the intensity difference was calculated over 48 adjacent point pairs at each side. The deformed midline was considered ideal as summed square of the difference across all midline points approaches global minimum, simulating maximal bilateral symmetry. Genetic algorithm was applied to optimize the values of the three control points of the Bezier curve. Our system was tested on images containing various pathologies from 81 consecutive patients treated in a single institute over one-year period. The deformed midlines itself as well as the amount of midline shift were evaluated by human experts, with satisfactory results.

Curved glide-reflection symmetry detection

We generalize the concept of bilateral reflection symmetry to curved glide-reflection symmetry in 2D euclidean space, such that classic reflection symmetry becomes one of its six special cases. We propose a local feature-based approach for curved glidereflection symmetry detection from real, unsegmented 2D images. Furthermore, we apply curved glide-reflection axis detection for curved reflection surface detection in 3D images. Our method discovers, groups, and connects statistically dominant local glidereflection axes in an Axis-Parameter-Space (APS) without preassumptions on the types of reflection symmetries. Quantitative evaluations and comparisons against state-of-the-art algorithms on a diverse 64-test-image set and 1,125 Swedish leaf-data images show a promising average detection rate of the proposed algorithm at 80 and 40 percent, respectively, and superior performance over existing reflection symmetry detection algorithms. Potential applications in computer vision, particularly biomedical imaging, include saliency detection from unsegmented images and quantification of deviations from normality. We make our 64-test-image set publicly available.

Spatially-dense 3D facial asymmetry assessment in both typical and disordered growth

Mild facial asymmetries are common in typical growth patterns. Therefore, detection of disordered facial growth patterns in individuals characterized by asymmetries is preferably accomplished by reference to the typical variation found in the general population rather than to some ideal of perfect symmetry, which rarely exists. This presents a challenge in developing an asymmetry assessment tool that is applicable, without modification, to detect both mild and severe facial asymmetries. In this paper we use concepts from geometric morphometrics to obtain robust and spatially-dense asymmetry assessments using a superimposition protocol for comparison of a face with its mirror image. Spatially-dense localization of asymmetries was achieved using an anthropometric mask consisting of uniformly sampled quasi-landmarks that were automatically indicated on 3D facial images. Robustness, in the sense of an unbiased analysis under increasing asymmetry, was ensured by an adaptive, robust, least-squares superimposition. The degree of overall asymmetry in an individual was scored using a root-mean-squared-error, and the proportion was scored using a novel relative significant asymmetry percentage. This protocol was applied to a database of 3D facial images from 359 young healthy individuals and three individuals with disordered facial growth. Typical asymmetry statistics were derived and were mainly located on, but not limited to, the lower two-thirds of the face in males and females. The asymmetry in males was more extensive and of a greater magnitude than in females. This protocol and proposed scoring of asymmetry with accompanying reference statistics will be useful for the detection and quantification of facial asymmetry in future studies.

A combination of atlas-based and voxel-wise approaches to analyze metabolic changes in autoradiographic data from Alzheimer's mice

Murine models are commonly used in neuroscience research to improve our knowledge of disease processes and to test drug effects. To accurately study brain glucose metabolism in these animals, ex vivo autoradiography remains the gold standard. The analysis of 3D-reconstructed autoradiographic volumes using a voxel-wise approach allows clusters of voxels representing metabolic differences between groups to be revealed. However, the spatial localization of these clusters requires careful visual identification by a neuroanatomist, a time-consuming task that is often subject to misinterpretation. Moreover, the large number of voxels to be computed in autoradiographic rodent images leads to many false positives. Here, we proposed an original automated indexation of the results of a voxel-wise approach using an MRI-based 3D digital atlas, followed by the restriction of the statistical analysis using atlas-based segmentation, thus taking advantage of the specific and complementary strengths of these two approaches. In a preliminary study of transgenic Alzheimer's mice (APP/PS1), and control littermates (PS1), we were able to achieve prompt and direct anatomical indexation of metabolic changes detected between the two groups, revealing both hypo- and hypermetabolism in the brain of APP/PS1 mice. Furthermore, statistical results were refined using atlas-based segmentation: most interesting results were obtained for the hippocampus. We thus confirmed and extended our previous results by identifying the brain structures affected in this pathological model and demonstrating modified glucose uptake in structures like the olfactory bulb. Our combined approach thus paves the way for a complete and accurate examination of functional data from cerebral structures involved in models of neurodegenerative diseases.

Employing symmetry features for automatic misalignment correction in neuroimages

A novel method to automatically compute the symmetry plane and to correct the 3D orientation of neuro-images is presented. In acquisition of neuroimaging scans, the lack of perfect alignment of a patient's head makes it challenging to evaluate brain images. By deploying a shape-based criterion, the symmetry plane is defined as a plane that best matches external surface points on one side of the head, with their counterparts on the other side. In our method, the head volume is represented as a re-parameterized surface point cloud, where each location is parameterized by its elevation (latitude), azimuth (longitude), and radius. The search for the best matching surfaces is implemented in a multi-resolution paradigm, and the computation time is significantly decreased. The algorithm was quantitatively evaluated using in both simulated data and in real T1, T2, Flair magnetic resonance patient images. This algorithm is found to be fast (<10s per MR volume), robust and accurate (<.6 degree of Mean Angular Error), invariant to the acquisition noise, slice thickness, bias field, and pathological asymmetries.

Segmentation of small animal PET/CT mouse brain scans using an MRI-based 3D digital atlas

The work reported in this paper aimed at developing and testing an automated method to calculate the biodistribution of a specific PET tracer in mouse brain PET/CT images using an MRI-based 3D digital atlas. Surface-based registration strategy and affine transformation estimation were considered. Such an approach allowed overcoming the lack of anatomical information in the inner regions of PET/CT brain scans. Promising results were obtained in one mouse (on two scans) and will be extended to a neuroinflammation mouse model to characterize the pathology and its evolution. Major improvements are expected regarding automation, time computation, robustness and reproducibility of mouse brain segmentation. Due to its generic implementation, this method could be successfully applied to PET/CT brain scans of other species (rat, primate) for which 3D digital atlases are available.

Atlas-based semiautomatic target volume definition (CTV) for head-and-neck tumors

PURPOSE

To develop a new semiautomatic method to improve target delineation in head-and-neck cancer.

METHODS AND MATERIALS

We implemented an atlas-based software program using fourteen anatomic landmarks as well as the most superior and inferior computerd tomography slices for automatic target delineation, using an advanced laryngeal carcinoma as an example. Registration was made by an affine transformation. Evaluation was performed with manually drawn contours for comparison. Three physicians sampled and further applied a target volume atlas to ten other computer tomography data sets. In addition, a rapid three-dimensional (3D) correction program was developed.

RESULTS

The mean time to the first semiautomatic target delineation proposal was 2.7 minutes. Manual contouring required 20.2 minutes per target, whereas semiautomatic target volume definition with the rapid 3D correction was completed in only 9.7 minutes. The net calculation time for image registration of the target volume atlas was negligible (approximately 0.6 seconds). Our method depicted a sufficient adaptation of the target volume atlas on the new data sets, with a mean similarity index of 77.2%. The similarity index increased up to 85% after 3D correction performed by the physicians.

CONCLUSIONS

We have developed a new, feasible method for semiautomatic contouring that saves a significant amount (51.8%) of target delineation time for head-and-neck cancer patients. This approach uses a target volume atlas and a landmark model. The software was evaluated by means of laryngeal cancer but has important implications for various tumor types whereby target volumes remain constant in form and do not move with respiration.

Validation of MRI-based 3D digital atlas registration with histological and autoradiographic volumes: an anatomofunctional transgenic mouse brain imaging study

Murine models are commonly used in neuroscience to improve our knowledge of disease processes and to test drug effects. To accurately study neuroanatomy and brain function in small animals, histological staining and ex vivo autoradiography remain the gold standards to date. These analyses are classically performed by manually tracing regions of interest, which is time-consuming. For this reason, only a few 2D tissue sections are usually processed, resulting in a loss of information. We therefore proposed to match a 3D digital atlas with previously 3D-reconstructed post mortem data to automatically evaluate morphology and function in mouse brain structures. We used a freely available MRI-based 3D digital atlas derived from C57Bl/6J mouse brain scans (9.4T). The histological and autoradiographic volumes used were obtained from a preliminary study in APP(SL)/PS1(M146L) transgenic mice, models of Alzheimer's disease, and their control littermates (PS1(M146L)). We first deformed the original 3D MR images to match our experimental volumes. We then applied deformation parameters to warp the 3D digital atlas to match the data to be studied. The reliability of our method was qualitatively and quantitatively assessed by comparing atlas-based and manual segmentations in 3D. Our approach yields faster and more robust results than standard methods in the investigation of post mortem mouse data sets at the level of brain structures. It also constitutes an original method for the validation of an MRI-based atlas using histology and autoradiography as anatomical and functional references, respectively.

Automatic cerebral and cerebellar hemisphere segmentation in 3D MRI: adaptive disconnection algorithm

This paper describes the automatic Adaptive Disconnection method to segment cerebral and cerebellar hemispheres of human brain in three-dimensional magnetic resonance imaging (MRI). Using the partial differential equations based shape bottlenecks algorithm cooperating with an information potential value clustering process, it detects and cuts, first, the compartmental connections between the cerebrum, the cerebellum and the brainstem in the white matter domain, and then, the interhemispheric connections of the extracted cerebrum and cerebellum volumes. As long as the subject orientation in the scanner is given, the variations in subject location and normal brain morphology in different images are accommodated automatically, thus no stereotaxic image registration is required. The modeling of partial volume effect is used to locate cerebrum, cerebellum and brainstem boundaries, and make the interhemispheric connections detectable. The Adaptive Disconnection method was tested with 10 simulated images from the BrainWeb database and 39 clinical images from the LONI Probabilistic Brain Atlas database. It obtained lower error rates than a traditional shape bottlenecks algorithm based segmentation technique (BrainVisa) and linear and nonlinear registration based brain hemisphere segmentation methods. Segmentation accuracies were evaluated against manual segmentations. The Adaptive Disconnection method was also confirmed not to be sensitive to the noise and intensity non-uniformity in the images. We also applied the Adaptive Disconnection method to clinical images of 22 healthy controls and 18 patients with schizophrenia. A preliminary cerebral volumetric asymmetry analysis based on these images demonstrated that the Adaptive Disconnection method is applicable to study abnormal brain asymmetry in schizophrenia.

Spatial decision forests for MS lesion segmentation in multi-channel MR images

A new algorithm is presented for the automatic segmentation of Multiple Sclerosis (MS) lesions in 3D MR images. It builds on the discriminative random decision forest framework to provide a voxel-wise probabilistic classification of the volume. Our method uses multi-channel MIR intensities (T1, T2, Flair), spatial prior and long-range comparisons with 3D regions to discriminate lesions. A symmetry feature is introduced accounting for the fact that some MS lesions tend to develop in an asymmetric way. Quantitative evaluation of the data is carried out on publicly available labeled cases from the MS Lesion Segmentation Challenge 2008 dataset and demonstrates improved results over the state of the art.

Automated ventricular systems segmentation in brain CT images by combining low-level segmentation and high-level template matching

Background

Accurate analysis of CT brain scans is vital for diagnosis and treatment of Traumatic Brain Injuries (TBI). Automatic processing of these CT brain scans could speed up the decision making process, lower the cost of healthcare, and reduce the chance of human error. In this paper, we focus on automatic processing of CT brain images to segment and identify the ventricular systems. The segmentation of ventricles provides quantitative measures on the changes of ventricles in the brain that form vital diagnosis information.

Methods

First all CT slices are aligned by detecting the ideal midlines in all images. The initial estimation of the ideal midline of the brain is found based on skull symmetry and then the initial estimate is further refined using detected anatomical features. Then a two-step method is used for ventricle segmentation. First a low-level segmentation on each pixel is applied on the CT images. For this step, both Iterated Conditional Mode (ICM) and Maximum A Posteriori Spatial Probability (MASP) are evaluated and compared. The second step applies template matching algorithm to identify objects in the initial low-level segmentation as ventricles. Experiments for ventricle segmentation are conducted using a relatively large CT dataset containing mild and severe TBI cases.

Results

Experiments show that the acceptable rate of the ideal midline detection is over 95%. Two measurements are defined to evaluate ventricle recognition results. The first measure is a sensitivity-like measure and the second is a false positive-like measure. For the first measurement, the rate is 100% indicating that all ventricles are identified in all slices. The false positives-like measurement is 8.59%. We also point out the similarities and differences between ICM and MASP algorithms through both mathematically relationships and segmentation results on CT images.

Conclusion

The experiments show the reliability of the proposed algorithms. The novelty of the proposed method lies in its incorporation of anatomical features for ideal midline detection and the two-step ventricle segmentation method. Our method offers the following improvements over existing approaches: accurate detection of the ideal midline and accurate recognition of ventricles using both anatomical features and spatial templates derived from Magnetic Resonance Images.

Robust calculation of the midsagittal plane in CT scans using the Kullback-Leibler's measure

OBJECTIVE

The identification of the interhemispheric fissure (IF) is important in clinical applications for brain landmark identification, registration, symmetry assessment, and pathology detection. The IF is usually approximated by the midsagittal plane (MSP) separating the brain into two hemispheres. We present a fast accurate, automatic, and robust algorithm for finding the MSP for CT scans acquired in emergency room (ER) with a large slice thickness, high partial volume effect, and substantial head tilt.

MATERIALS AND METHODS

An earlier algorithm for MSP identification from MRI using the Kullback-Leibler's measure was extended for CT by estimating patient's head orientation using model fitting, image processing, and atlas-based techniques. The new algorithm was validated on 208 clinical scans acquired mainly in the ER with slice thickness ranging from 1.5 to 6 mm and severe head tilt.

RESULTS

The algorithm worked robustly for all 208 cases. An angular discrepancy (degrees) and maximum distance (mm) between the calculated MSP and ground truth have the mean value (SD) 0.0258 degrees (0.9541 degrees) and 0.1472 (0.7373) mm, respectively. In average, the algorithm takes 10 s to process of a typical CT case.

CONCLUSION

The proposed algorithm is robust to head rotation, and correctly identifies the MSP for a standard clinical CT scan with a large slice thickness. It has been applied in our several CT stroke CAD systems.

A three-dimensional histological atlas of the human basal ganglia. II. Atlas deformation strategy and evaluation in deep brain stimulation for Parkinson disease

OBJECT

The localization of any given target in the brain has become a challenging issue because of the increased use of deep brain stimulation to treat Parkinson disease, dystonia, and nonmotor diseases (for example, Tourette syndrome, obsessive compulsive disorders, and depression). The aim of this study was to develop an automated method of adapting an atlas of the human basal ganglia to the brains of individual patients.

METHODS

Magnetic resonance images of the brain specimen were obtained before extraction from the skull and histological processing. Adaptation of the atlas to individual patient anatomy was performed by reshaping the atlas MR images to the images obtained in the individual patient using a hierarchical registration applied to a region of interest centered on the basal ganglia, and then applying the reshaping matrix to the atlas surfaces.

RESULTS

Results were evaluated by direct visual inspection of the structures visible on MR images and atlas anatomy, by comparison with electrophysiological intraoperative data, and with previous atlas studies in patients with Parkinson disease. The method was both robust and accurate, never failing to provide an anatomically reliable atlas to patient registration. The registration obtained did not exceed a 1-mm mismatch with the electrophysiological signatures in the region of the subthalamic nucleus.

CONCLUSIONS

This registration method applied to the basal ganglia atlas forms a powerful and reliable method for determining deep brain stimulation targets within the basal ganglia of individual patients.

Model-based automatic detection of the anterior and posterior commissures on MRI scans

The projections of the anterior and posterior commissures (AC/PC) on the mid-sagittal plane of the human brain are important landmarks in neuroimaging. They can be used, for example, during MRI scanning for acquiring the imaging sections in a standard orientation. In post-acquisition image processing, these landmarks serve to establish an anatomically-based frame of reference within the brain that can be extremely useful in designing automated image analysis algorithms such as image segmentation and registration methods. This paper presents a fully automatic model-based algorithm for AC/PC detection on MRI scans. The algorithm utilizes information from a number of model images on which the locations of the AC/PC and a reference point (the vertex of the superior pontine sulcus) are known. This information is then used to locate the landmarks on test scans by template matching. The algorithm is designed to be fast, robust, and accurate. The method is flexible in that it can be trained to work on different image contrasts, optimized for different populations, or scanning modes. To assess the effectiveness of this technique, we compared automatically and manually detected landmark locations on 84 T(1)-weighted and 42 T(2)-weighted test scans. Overall, the average Euclidean distance between automatically and manually detected landmarks was 1.1 mm. A software implementation of the algorithm is freely available online at www.nitrc.org/projects/art.

Symmetry identification using partial surface matching and tilt correction in 3D brain images

We propose a novel method to automatically compute the symmetry plane and correct the 3D orientation of patient brain images. Many images of the brain are clinically unreadable because of the misalignment of the patient's head in the scanner. We proposed an algorithm that represents the brain volume as a re-parameterized surface point cloud where each location has been parameterized by its elevation (latitude), azimuth (longitude) and radius. The removal of the interior contents of the brain makes this approach perform robustly in the presence of the brain pathologies, e.g. tumor, stroke and bleed. Thus, we decompose the symmetry plane computation problem into a surface matching routine. The search for the best matching surface is implemented in a multi-resolution paradigm so as to decrease computational time considerably. Spatial affine transform then is performed to rotate the 3D brain images and align them within the coordinate system of the scanner. The corrected brain volume is re-sliced such that each planar image represents the brain at the same axial level.