Multi-atlas segmentation of biomedical images: A survey

Metric Learning for Multi-atlas based Segmentation of Hippocampus

Automatic and reliable segmentation of hippocampus from MR brain images is of great importance in studies of neurological diseases, such as epilepsy and Alzheimer's disease. In this paper, we proposed a novel metric learning method to fuse segmentation labels in multi-atlas based image segmentation. Different from current label fusion methods that typically adopt a predefined distance metric model to compute a similarity measure between image patches of atlas images and the image to be segmented, we learn a distance metric model from the atlases to keep image patches of the same structure close to each other while those of different structures are separated. The learned distance metric model is then used to compute the similarity measure between image patches in the label fusion. The proposed method has been validated for segmenting hippocampus based on the EADC-ADNI dataset with manually labelled hippocampus of 100 subjects. The experiment results demonstrated that our method achieved statistically significant improvement in segmentation accuracy, compared with state-of-the-art multi-atlas image segmentation methods.

Reproducibility of superficial white matter tracts using diffusion-weighted imaging tractography

Human brain connection map is far from being complete. In particular the study of the superficial white matter (SWM) is an unachieved task. Its description is essential for the understanding of human brain function and the study of pathogenesis triggered by abnormal connectivity. In this work we automatically created a multi-subject atlas of SWM diffusion-based bundles of the whole brain. For each subject, the complete cortico-cortical tractogram is first split into sub-tractograms connecting pairs of gyri. Then intra-subject shape-based fiber clustering performs compression of each sub-tractogram into a set of bundles. Proceeding further with shape-based clustering provides a match of the bundles across subjects. Bundles found in most of the subjects are instantiated in the atlas. To increase robustness, this procedure was performed with two independent groups of subjects, in order to discard bundles without match across the two independent atlases. Finally, the resulting intersection atlas was projected on a third independent group of subjects in order to filter out bundles without reproducible and reliable projection. The final multi-subject diffusion-based U-fiber atlas is composed of 100 bundles in total, 50 per hemisphere, from which 35 are common to both hemispheres.

Extended Modality Propagation: Image Synthesis of Pathological Cases

This paper describes a novel generative model for the synthesis of multi-modal medical images of pathological cases based on a single label map. Our model builds upon i) a generative model commonly used for label fusion and multi-atlas patch-based segmentation of healthy anatomical structures, ii) the Modality Propagation iterative strategy used for a spatially-coherent synthesis of subject-specific scans of desired image modalities. The expression Extended Modality Propagation is coined to refer to the extension of Modality Propagation to the synthesis of images of pathological cases. Moreover, image synthesis uncertainty is estimated. An application to Magnetic Resonance Imaging synthesis of glioma-bearing brains is i) validated on the training dataset of a Multimodal Brain Tumor Image Segmentation challenge, ii) compared to the state-of-the-art in glioma image synthesis, and iii) illustrated using the output of two different tumor growth models. Such a generative model allows the generation of a large dataset of synthetic cases, which could prove useful for the training, validation, or benchmarking of image processing algorithms.

Simultaneous total intracranial volume and posterior fossa volume estimation using multi-atlas label fusion

Total intracranial volume (TICV) is an essential covariate in brain volumetric analyses. The prevalent brain imaging software packages provide automatic TICV estimates. FreeSurfer and FSL estimate TICV using a scaling factor while SPM12 accumulates probabilities of brain tissues. None of the three provide explicit skull/CSF boundary (SCB) since it is challenging to distinguish these dark structures in a T1-weighted image. However, explicit SCB not only leads to a natural way of obtaining TICV (i.e., counting voxels inside the skull) but also allows sub-definition of TICV, for example, the posterior fossa volume (PFV). In this article, they proposed to use multi-atlas label fusion to obtain TICV and PFV simultaneously. The main contributions are: (1) TICV and PFV are simultaneously obtained with explicit SCB from a single T1-weighted image. (2) TICV and PFV labels are added to the widely used BrainCOLOR atlases. (3) Detailed mathematical derivation of non-local spatial STAPLE (NLSS) label fusion is presented. As the skull is clearly distinguished in CT images, we use a semi-manual procedure to obtain atlases with TICV and PFV labels using 20 subjects who both have a MR and CT scan. The proposed method provides simultaneous TICV and PFV estimation while achieving more accurate TICV estimation compared with FreeSurfer, FSL, SPM12, and the previously proposed STAPLE based approach. The newly developed TICV and PFV labels for the OASIS BrainCOLOR atlases provide acceptable performance, which enables simultaneous TICV and PFV estimation during whole brain segmentation. The NLSS method and the new atlases have been made freely available. Hum Brain Mapp 38:599-616, 2017. © 2016 Wiley Periodicals, Inc.

Globally Optimal Label Fusion with Shape Priors

Multi-atlas label fusion methods have gained popularity in a variety of segmentation tasks given their attractive performance. Graph-based segmentation methods are widely used given their global optimality guarantee. We propose a novel approach, GOLF, that combines the strengths of these two approaches. GOLF incorporates shape priors to the label-fusion problem and provides a globally optimal solution even for the multi-label scenario, while also leveraging the highly accurate posterior maps from a multi-atlas label fusion approach. We demonstrate GOLF for the joint segmentation of the left and right pairs of caudate, putamen, globus pallidus and nucleus accumbens. Compared to the FreeSurfer and FIRST approaches, GOLF is significantly more accurate on all reported indices for all 8 structures. We also present comparisons to a multi-atlas approach, which reveals further insights on the contributions of the different components of the proposed framework.

Fast and sequence-adaptive whole-brain segmentation using parametric Bayesian modeling

Quantitative analysis of magnetic resonance imaging (MRI) scans of the brain requires accurate automated segmentation of anatomical structures. A desirable feature for such segmentation methods is to be robust against changes in acquisition platform and imaging protocol. In this paper we validate the performance of a segmentation algorithm designed to meet these requirements, building upon generative parametric models previously used in tissue classification. The method is tested on four different datasets acquired with different scanners, field strengths and pulse sequences, demonstrating comparable accuracy to state-of-the-art methods on T1-weighted scans while being one to two orders of magnitude faster. The proposed algorithm is also shown to be robust against small training datasets, and readily handles images with different MRI contrast as well as multi-contrast data.

Abdomen and spinal cord segmentation with augmented active shape models

Active shape models (ASMs) have been widely used for extracting human anatomies in medical images given their capability for shape regularization of topology preservation. However, sensitivity to model initialization and local correspondence search often undermines their performances, especially around highly variable contexts in computed-tomography (CT) and magnetic resonance (MR) images. In this study, we propose an augmented ASM (AASM) by integrating the multiatlas label fusion (MALF) and level set (LS) techniques into the traditional ASM framework. Using AASM, landmark updates are optimized globally via a region-based LS evolution applied on the probability map generated from MALF. This augmentation effectively extends the searching range of correspondent landmarks while reducing sensitivity to the image contexts and improves the segmentation robustness. We propose the AASM framework as a two-dimensional segmentation technique targeting structures with one axis of regularity. We apply AASM approach to abdomen CT and spinal cord (SC) MR segmentation challenges. On 20 CT scans, the AASM segmentation of the whole abdominal wall enables the subcutaneous/visceral fat measurement, with high correlation to the measurement derived from manual segmentation. On 28 3T MR scans, AASM yields better performances than other state-of-the-art approaches in segmenting white/gray matter in SC.

aMAP is a validated pipeline for registration and segmentation of high-resolution mouse brain data

The validation of automated image registration and segmentation is crucial for accurate and reliable mapping of brain connectivity and function in three-dimensional (3D) data sets. While validation standards are necessarily high and routinely met in the clinical arena, they have to date been lacking for high-resolution microscopy data sets obtained from the rodent brain. Here we present a tool for optimized automated mouse atlas propagation (aMAP) based on clinical registration software (NiftyReg) for anatomical segmentation of high-resolution 3D fluorescence images of the adult mouse brain. We empirically evaluate aMAP as a method for registration and subsequent segmentation by validating it against the performance of expert human raters. This study therefore establishes a benchmark standard for mapping the molecular function and cellular connectivity of the rodent brain.

Reproducibility of hippocampal atrophy rates measured with manual, FreeSurfer, AdaBoost, FSL/FIRST and the MAPS-HBSI methods in Alzheimer's disease

The purpose of this study is to assess the reproducibility of hippocampal atrophy rate measurements of commonly used fully-automated algorithms in Alzheimer disease (AD). The reproducibility of hippocampal atrophy rate for FSL/FIRST, AdaBoost, FreeSurfer, MAPS independently and MAPS combined with the boundary shift integral (MAPS-HBSI) were calculated. Back-to-back (BTB) 3D T1-weighted MPRAGE MRI from the Alzheimer's Disease Neuroimaging Initiative (ADNI1) study at baseline and year one were used. Analysis on 3 groups of subjects was performed - 562 subjects at 1.5T, a 75 subject group that also had manual segmentation and 111 subjects at 3T. A simple and novel statistical test based on the binomial distribution was used that handled outlying data points robustly. Median hippocampal atrophy rates were -1.1%/year for healthy controls, -3.0%/year for mildly cognitively impaired and -5.1%/year for AD subjects. The best reproducibility was observed for MAPS-HBSI (1.3%), while the other methods tested had reproducibilities at least 50% higher at 1.5T and 3T which was statistically significant. For a clinical trial, MAPS-HBSI should require less than half the subjects of the other methods tested. All methods had good accuracy versus manual segmentation. The MAPS-HBSI method has substantially better reproducibility than the other methods considered.

Four challenges in medical image analysis from an industrial perspective

Today's medical imaging systems produce a huge amount of images containing a wealth of information. However, the information is hidden in the data and image analysis algorithms are needed to extract it, to make it readily available for medical decisions and to enable an efficient work flow. Advances in medical image analysis over the past 20 years mean there are now many algorithms and ideas available that allow to address medical image analysis tasks in commercial solutions with sufficient performance in terms of accuracy, reliability and speed. At the same time new challenges have arisen. Firstly, there is a need for more generic image analysis technologies that can be efficiently adapted for a specific clinical task. Secondly, efficient approaches for ground truth generation are needed to match the increasing demands regarding validation and machine learning. Thirdly, algorithms for analyzing heterogeneous image data are needed. Finally, anatomical and organ models play a crucial role in many applications, and algorithms to construct patient-specific models from medical images with a minimum of user interaction are needed. These challenges are complementary to the on-going need for more accurate, more reliable and faster algorithms, and dedicated algorithmic solutions for specific applications.

Evaluation of Six Registration Methods for the Human Abdomen on Clinically Acquired CT

OBJECTIVE

This work evaluates current 3-D image registration tools on clinically acquired abdominal computed tomography (CT) scans.

METHODS

Thirteen abdominal organs were manually labeled on a set of 100 CT images, and the 100 labeled images (i.e., atlases) were pairwise registered based on intensity information with six registration tools (FSL, ANTS-CC, ANTS-QUICK-MI, IRTK, NIFTYREG, and DEEDS). The Dice similarity coefficient (DSC), mean surface distance, and Hausdorff distance were calculated on the registered organs individually. Permutation tests and indifference-zone ranking were performed to examine the statistical and practical significance, respectively.

RESULTS

The results suggest that DEEDS yielded the best registration performance. However, due to the overall low DSC values, and substantial portion of low-performing outliers, great care must be taken when image registration is used for local interpretation of abdominal CT.

CONCLUSION

There is substantial room for improvement in image registration for abdominal CT.

SIGNIFICANCE

All data and source code are available so that innovations in registration can be directly compared with the current generation of tools without excessive duplication of effort.

Consistent cortical reconstruction and multi-atlas brain segmentation

Whole brain segmentation and cortical surface reconstruction are two essential techniques for investigating the human brain. Spatial inconsistences, which can hinder further integrated analyses of brain structure, can result due to these two tasks typically being conducted independently of each other. FreeSurfer obtains self-consistent whole brain segmentations and cortical surfaces. It starts with subcortical segmentation, then carries out cortical surface reconstruction, and ends with cortical segmentation and labeling. However, this "segmentation to surface to parcellation" strategy has shown limitations in various cohorts such as older populations with large ventricles. In this work, we propose a novel "multi-atlas segmentation to surface" method called Multi-atlas CRUISE (MaCRUISE), which achieves self-consistent whole brain segmentations and cortical surfaces by combining multi-atlas segmentation with the cortical reconstruction method CRUISE. A modification called MaCRUISE(+) is designed to perform well when white matter lesions are present. Comparing to the benchmarks CRUISE and FreeSurfer, the surface accuracy of MaCRUISE and MaCRUISE(+) is validated using two independent datasets with expertly placed cortical landmarks. A third independent dataset with expertly delineated volumetric labels is employed to compare segmentation performance. Finally, 200MR volumetric images from an older adult sample are used to assess the robustness of MaCRUISE and FreeSurfer. The advantages of MaCRUISE are: (1) MaCRUISE constructs self-consistent voxelwise segmentations and cortical surfaces, while MaCRUISE(+) is robust to white matter pathology. (2) MaCRUISE achieves more accurate whole brain segmentations than independently conducting the multi-atlas segmentation. (3) MaCRUISE is comparable in accuracy to FreeSurfer (when FreeSurfer does not exhibit global failures) while achieving greater robustness across an older adult population. MaCRUISE has been made freely available in open source.

A robust statistics driven volume-scalable active contour for segmenting anatomical structures in volumetric medical images with complex conditions

BACKGROUND

Accurate segmentation of anatomical structures in medical images is a critical step in the development of computer assisted intervention systems. However, complex image conditions, such as intensity inhomogeneity, noise and weak object boundary, often cause considerable difficulties in medical image segmentation. To cope with these difficulties, we propose a novel robust statistics driven volume-scalable active contour framework, to extract desired object boundary from magnetic resonance (MR) and computed tomography (CT) imagery in 3D.

METHODS

We define an energy functional in terms of the initial seeded labels and two fitting functions that are derived from object local robust statistics features. This energy is then incorporated into a level set scheme which drives the active contour evolving and converging at the desired position of the object boundary. Due to the local robust statistics and the volume scaling function in the energy fitting term, the object features in local volumes are learned adaptively to guide the motion of the contours, which thereby guarantees the capability of our method to cope with intensity inhomogeneity, noise and weak boundary. In addition, the initialization of active contour is simplified by select several seeds in the object and/or background to eliminate the sensitivity to initialization.

RESULTS

The proposed method was applied to extensive public available volumetric medical images with challenging image conditions. The segmentation results of various anatomical structures, such as white matter (WM), atrium, caudate nucleus and brain tumor, were evaluated quantitatively by comparing with the corresponding ground truths. It was found that the proposed method achieves consistent and coherent segmentation accuracy of 0.9246 ± 0.0068 for WM, 0.9043 ± 0.0131 for liver tumors, 0.8725 ± 0.0374 for caudate nucleus, 0.8802 ± 0.0595 for brain tumors, etc., measured by Dice similarity coefficients value for the overlap between the algorithm one and the ground truth. Further comparative experimental results showed desirable performances of the proposed method over several well-known segmentation methods in terms of accuracy and robustness.

CONCLUSION

We proposed an approach to accurate segment volumetric medical images with complex conditions. The accuracy of segmentation, robustness to noise and contour initialization were validated on the basis of extensive MR and CT volumes.

A Patch-Based Approach for the Segmentation of Pathologies: Application to Glioma Labelling

In this paper, we describe a novel and generic approach to address fully-automatic segmentation of brain tumors by using multi-atlas patch-based voting techniques. In addition to avoiding the local search window assumption, the conventional patch-based framework is enhanced through several simple procedures: an improvement of the training dataset in terms of both label purity and intensity statistics, augmented features to implicitly guide the nearest-neighbor-search, multi-scale patches, invariance to cube isometries, stratification of the votes with respect to cases and labels. A probabilistic model automatically delineates regions of interest enclosing high-probability tumor volumes, which allows the algorithm to achieve highly competitive running time despite minimal processing power and resources. This method was evaluated on Multimodal Brain Tumor Image Segmentation challenge datasets. State-of-the-art results are achieved, with a limited learning stage thus restricting the risk of overfit. Moreover, segmentation smoothness does not involve any post-processing.

Accurate Learning with Few Atlases (ALFA): an algorithm for MRI neonatal brain extraction and comparison with 11 publicly available methods

Accurate whole-brain segmentation, or brain extraction, of magnetic resonance imaging (MRI) is a critical first step in most neuroimage analysis pipelines. The majority of brain extraction algorithms have been developed and evaluated for adult data and their validity for neonatal brain extraction, which presents age-specific challenges for this task, has not been established. We developed a novel method for brain extraction of multi-modal neonatal brain MR images, named ALFA (Accurate Learning with Few Atlases). The method uses a new sparsity-based atlas selection strategy that requires a very limited number of atlases 'uniformly' distributed in the low-dimensional data space, combined with a machine learning based label fusion technique. The performance of the method for brain extraction from multi-modal data of 50 newborns is evaluated and compared with results obtained using eleven publicly available brain extraction methods. ALFA outperformed the eleven compared methods providing robust and accurate brain extraction results across different modalities. As ALFA can learn from partially labelled datasets, it can be used to segment large-scale datasets efficiently. ALFA could also be applied to other imaging modalities and other stages across the life course.

MUSE: MUlti-atlas region Segmentation utilizing Ensembles of registration algorithms and parameters, and locally optimal atlas selection

Atlas-based automated anatomical labeling is a fundamental tool in medical image segmentation, as it defines regions of interest for subsequent analysis of structural and functional image data. The extensive investigation of multi-atlas warping and fusion techniques over the past 5 or more years has clearly demonstrated the advantages of consensus-based segmentation. However, the common approach is to use multiple atlases with a single registration method and parameter set, which is not necessarily optimal for every individual scan, anatomical region, and problem/data-type. Different registration criteria and parameter sets yield different solutions, each providing complementary information. Herein, we present a consensus labeling framework that generates a broad ensemble of labeled atlases in target image space via the use of several warping algorithms, regularization parameters, and atlases. The label fusion integrates two complementary sources of information: a local similarity ranking to select locally optimal atlases and a boundary modulation term to refine the segmentation consistently with the target image's intensity profile. The ensemble approach consistently outperforms segmentations using individual warping methods alone, achieving high accuracy on several benchmark datasets. The MUSE methodology has been used for processing thousands of scans from various datasets, producing robust and consistent results. MUSE is publicly available both as a downloadable software package, and as an application that can be run on the CBICA Image Processing Portal (https://ipp.cbica.upenn.edu), a web based platform for remote processing of medical images.

The white matter query language: a novel approach for describing human white matter anatomy

We have developed a novel method to describe human white matter anatomy using an approach that is both intuitive and simple to use, and which automatically extracts white matter tracts from diffusion MRI volumes. Further, our method simplifies the quantification and statistical analysis of white matter tracts on large diffusion MRI databases. This work reflects the careful syntactical definition of major white matter fiber tracts in the human brain based on a neuroanatomist's expert knowledge. The framework is based on a novel query language with a near-to-English textual syntax. This query language makes it possible to construct a dictionary of anatomical definitions that describe white matter tracts. The definitions include adjacent gray and white matter regions, and rules for spatial relations. This novel method makes it possible to automatically label white matter anatomy across subjects. After describing this method, we provide an example of its implementation where we encode anatomical knowledge in human white matter for ten association and 15 projection tracts per hemisphere, along with seven commissural tracts. Importantly, this novel method is comparable in accuracy to manual labeling. Finally, we present results applying this method to create a white matter atlas from 77 healthy subjects, and we use this atlas in a small proof-of-concept study to detect changes in association tracts that characterize schizophrenia.

Performance of single and multi-atlas based automated landmarking methods compared to expert annotations in volumetric microCT datasets of mouse mandibles

BACKGROUND

Here we present an application of advanced registration and atlas building framework DRAMMS to the automated annotation of mouse mandibles through a series of tests using single and multi-atlas segmentation paradigms and compare the outcomes to the current gold standard, manual annotation.

RESULTS

Our results showed multi-atlas annotation procedure yields landmark precisions within the human observer error range. The mean shape estimates from gold standard and multi-atlas annotation procedure were statistically indistinguishable for both Euclidean Distance Matrix Analysis (mean form matrix) and Generalized Procrustes Analysis (Goodall F-test). Further research needs to be done to validate the consistency of variance-covariance matrix estimates from both methods with larger sample sizes.

CONCLUSION

Multi-atlas annotation procedure shows promise as a framework to facilitate truly high-throughput phenomic analyses by channeling investigators efforts to annotate only a small portion of their datasets.

Segmentation and quantification of adipose tissue by magnetic resonance imaging

In this brief review, introductory concepts in animal and human adipose tissue segmentation using proton magnetic resonance imaging (MRI) and computed tomography are summarized in the context of obesity research. Adipose tissue segmentation and quantification using spin relaxation-based (e.g., T1-weighted, T2-weighted), relaxometry-based (e.g., T1-, T2-, T2*-mapping), chemical-shift selective, and chemical-shift encoded water-fat MRI pulse sequences are briefly discussed. The continuing interest to classify subcutaneous and visceral adipose tissue depots into smaller sub-depot compartments is mentioned. The use of a single slice, a stack of slices across a limited anatomical region, or a whole body protocol is considered. Common image post-processing steps and emerging atlas-based automated segmentation techniques are noted. Finally, the article identifies some directions of future research, including a discussion on the growing topic of brown adipose tissue and related segmentation considerations.