Multi-atlas segmentation provides a general purpose, fully-automated approach for transferring spatial information from an existing dataset (“atlases”) to a previously unseen context (“target”) through image registration. The method to resolve voxelwise label conflicts between the registered atlases (“label fusion”) has a substantial impact on segmentation quality. Ideally, statistical fusion algorithms (e.g., STAPLE) would result in accurate segmentations as they provide a framework to elegantly integrate models of rater performance. The accuracy of statistical fusion hinges upon accurately modeling the underlying process of how raters err. Despite success on human raters, current approaches inaccurately model multi-atlas behavior as they fail to seamlessly incorporate exogenous intensity information into the estimation process. As a result, locally weighted voting algorithms represent the de facto standard fusion approach in clinical applications. Moreover, regardless of the approach, fusion algorithms are generally dependent upon large atlas sets and highly accurate registration as they implicitly assume that the registered atlases form a collectively unbiased representation of the target. Herein, we propose a novel statistical fusion algorithm, Non-Local STAPLE (NLS). NLS reformulates the STAPLE framework from a non-local means perspective in order to learn what label an atlas would have observed, given perfect correspondence. Through this reformulation, NLS (1) seamlessly integrates intensity into the estimation process, (2) provides a theoretically consistent model of multi-atlas observation error, and (3) largely diminishes the need for large atlas sets and very high-quality registrations. We assess the sensitivity and optimality of the approach and demonstrate significant improvement in two empirical multi-atlas experiments.

To date, label fusion methods have primarily relied either on global (e.g. STAPLE, globally weighted vote) or voxelwise (e.g. locally weighted vote) performance models. Optimality of the statistical fusion framework hinges upon the validity of the stochastic model of how a rater errs (i.e., the labeling process model). Hitherto, approaches have tended to focus on the extremes of potential models. Herein, we propose an extension to the STAPLE approach to seamlessly account for spatially varying performance by extending the performance level parameters to account for a smooth, voxelwise performance level field that is unique to each rater. This approach, Spatial STAPLE, provides significant improvements over state-of-the-art label fusion algorithms in both simulated and empirical data sets.

Segmentation and delineation of structures of interest in medical images is paramount to quantifying and characterizing structural, morphological, and functional correlations with clinically relevant conditions. The established gold standard for performing segmentation has been manual voxel-by-voxel labeling by a neuroanatomist expert. This process can be extremely time consuming, resource intensive and fraught with high inter-observer variability. Hence, studies involving characterizations of novel structures or appearances have been limited in scope (numbers of subjects), scale (extent of regions assessed), and statistical power. Statistical methods to fuse data sets from several different sources (e.g., multiple human observers) have been proposed to simultaneously estimate both rater performance and the ground truth labels. However, with empirical datasets, statistical fusion has been observed to result in visually inconsistent findings. So, despite the ease and elegance of a statistical approach, single observers and/or direct voting are often used in practice. Hence, rater performance is not systematically quantified and exploited during label estimation. To date, statistical fusion methods have relied on characterizations of rater performance that do not intrinsically include spatially varying models of rater performance. Herein, we present a novel, robust statistical label fusion algorithm to estimate and account for spatially varying performance. This algorithm, COnsensus Level, Labeler Accuracy and Truth Estimation (COLLATE), is based on the simple idea that some regions of an image are difficult to label (e.g., confusion regions: boundaries or low contrast areas) while other regions are intrinsically obvious (e.g., consensus regions: centers of large regions or high contrast edges). Unlike its predecessors, COLLATE estimates the consensus level of each voxel and estimates differing models of observer behavior in each region. We show that COLLATE provides significant improvement in label accuracy and rater assessment over previous fusion methods in both simulated and empirical datasets.

Diffusion tensor imaging (DTI) enables non-invasive, cyto-architectural mapping of in vivo tissue microarchitecture through voxel-wise mathematical modeling of multiple magnetic resonance imaging (MRI) acquisitions, each differently sensitized to water diffusion. DTI computations are fundamentally estimation processes and are sensitive to noise and artifacts. Despite widespread adoption in the neuroimaging community, maintaining consistent DTI data quality remains challenging given the propensity for patient motion, artifacts associated with fast imaging techniques, and the possibility of hardware changes/failures. Furthermore, the quantity of data acquired per voxel, the non-linear estimation process, and numerous potential use cases complicate traditional visual data inspection approaches. Currently, quality inspection of DTI data has relied on visual inspection and individual processing in DTI analysis software programs (e.g. DTIPrep, DTI-studio). However, recent advances in applied statistical methods have yielded several different metrics to assess noise level, artifact propensity, quality of tensor fit, variance of estimated measures, and bias in estimated measures. To date, these metrics have been largely studied in isolation. Herein, we select complementary metrics for integration into an automatic DTI analysis and quality assurance pipeline. The pipeline completes in 24 hours, stores statistical outputs, and produces a graphical summary quality analysis (QA) report. We assess the utility of this streamlined approach for empirical quality assessment on 608 DTI datasets from pediatric neuroimaging studies. The efficiency and accuracy of quality analysis using the proposed pipeline is compared with quality analysis based on visual inspection. The unified pipeline is found to save a statistically significant amount of time (over 70%) while improving the consistency of QA between a DTI expert and a pool of research associates. Projection of QA metrics to a low dimensional manifold reveal qualitative, but clear, QA-study associations and suggest that automated outlier/anomaly detection would be feasible.

Image labeling and parcellation (i.e. assigning structure to a collection of voxels) are critical tasks for the assessment of volumetric and morphometric features in medical imaging data. The process of image labeling is inherently error prone as images are corrupted by noise and artifacts. Even expert interpretations are subject to subjectivity and the precision of the individual raters. Hence, all labels must be considered imperfect with some degree of inherent variability. One may seek multiple independent assessments to both reduce this variability and quantify the degree of uncertainty. Existing techniques have exploited maximum a posteriori statistics to combine data from multiple raters and simultaneously estimate rater reliabilities. Although quite successful, wide-scale application has been hampered by unstable estimation with practical datasets, for example, with label sets with small or thin objects to be labeled or with partial or limited datasets. As well, these approaches have required each rater to generate a complete dataset, which is often impossible given both human foibles and the typical turnover rate of raters in a research or clinical environment. Herein, we propose a robust approach to improve estimation performance with small anatomical structures, allow for missing data, account for repeated label sets, and utilize training/catch trial data. With this approach, numerous raters can label small, overlapping portions of a large dataset, and rater heterogeneity can be robustly controlled while simultaneously estimating a single, reliable label set and characterizing uncertainty. The proposed approach enables many individuals to collaborate in the construction of large datasets for labeling tasks (e.g., human parallel processing) and reduces the otherwise detrimental impact of rater unavailability.