Search

In many diagnostic imaging settings, including positron emission tomography (PET), images are typically used for multiple tasks such as detecting disease and quantifying disease. Unlike conventional image reconstruction that optimizes a single objective, this work proposes a multi-objective optimization algorithm for PET image reconstruction to identify a set of images that are optimal for more than one task. This work is reliant on a genetic algorithm to evolve a set of solutions that satisfies two distinct objectives. In this paper, we defined the objectives as the commonly used Poisson log-likelihood function, typically reflective of quantitative accuracy, and a variant of the generalized scan-statistic model, to reflect detection performance. The genetic algorithm uses new mutation and crossover operations at each iteration. After each iteration, the child population is selected with non-dominated sorting to identify the set of solutions along the dominant front or fronts. After multiple iterations, these fronts approach a single non-dominated optimal front, defined as the set of PET images for which none the objective function values can be improved without reducing the opposing objective function. This method was applied to simulated 2D PET data of the heart and liver with hot features. We compared this approach to conventional, single-objective approaches for trading off performance: maximum likelihood estimation with increasing explicit regularization and maximum a posteriori estimation with varying penalty strength. Results demonstrate that the proposed method generates solutions with comparable to improved objective function values compared to the conventional approaches for trading off performance amongst different tasks. In addition, this approach identifies a diverse set of solutions in the multi-objective function space which can be challenging to estimate with single-objective formulations. [ABSTRACT FROM AUTHOR]

Reconstruction of neuronal populations from ultra-scale optical microscopy (OM) images is essential to investigate neuronal circuits and brain mechanisms. The noises, low contrast, huge memory requirement, and high computational cost pose significant challenges in the neuronal population reconstruction. Recently, many studies have been conducted to extract neuron signals using deep neural networks (DNNs). However, training such DNNs usually relies on a huge amount of voxel-wise annotations in OM images, which are expensive in terms of both finance and labor. In this paper, we propose a novel framework for dense neuronal population reconstruction from ultra-scale images. To solve the problem of high cost in obtaining manual annotations for training DNNs, we propose a progressive learning scheme for neuronal population reconstruction (PLNPR) which does not require any manual annotations. Our PLNPR scheme consists of a traditional neuron tracing module and a deep segmentation network that mutually complement and progressively promote each other. To reconstruct dense neuronal populations from a terabyte-sized ultra-scale image, we introduce an automatic framework which adaptively traces neurons block by block and fuses fragmented neurites in overlapped regions continuously and smoothly. We build a dataset “VISoR-40” which consists of 40 large-scale OM image blocks from cortical regions of a mouse. Extensive experimental results on our VISoR-40 dataset and the public BigNeuron dataset demonstrate the effectiveness and superiority of our method on neuronal population reconstruction and single neuron reconstruction. Furthermore, we successfully apply our method to reconstruct dense neuronal populations from an ultra-scale mouse brain slice. The proposed adaptive block propagation and fusion strategies greatly improve the completeness of neurites in dense neuronal population reconstruction. [ABSTRACT FROM AUTHOR]

Multi-label probabilistic maps, a.k.a. probabilistic segmentations, parameterize a population of intimately co-existing anatomical shapes and are useful for various medical imaging applications, such as segmentation, anatomical atlases, shape analysis, and consensus generation. Existing methods to estimate probabilistic segmentations rely on ad hoc intermediate representations (e.g., average of Gaussian-smoothed label maps and smoothed signed distance maps) that do not necessarily conform to the underlying generative process. Generative modeling of such maps could help discover as well as aide in the statistical analysis of sub-groups in a population via clustering and mixture modeling techniques. In this paper, we propose an estimation of multi-label probabilistic maps and showcase their favorable performance for modeling anatomical shapes such as the left atrium of the human heart and brain structures. The proposed formulation relies on a constrained optimization in the natural parameter space of the exponential family form of categorical distributions. A smoothness prior provides generalizability in the model and helps achieve greater performance in modeling tasks for unseen samples. We demonstrate and compare the effectiveness of the proposed method for Bayesian image segmentation, multi-atlas segmentation, and shape-based clustering. [ABSTRACT FROM AUTHOR]

The goal of this paper is to increase the statistical power of crossing-fiber statistics in voxelwise analyses of diffusion-weighted magnetic resonance imaging (DW-MRI) data. In the proposed framework, a fiber orientation atlas and a model complexity atlas were used to fit the ball-and-sticks model to diffusion-weighted images of subjects in a prospective population-based cohort study. Reproducibility and sensitivity of the partial volume fractions in the ball-and-sticks model were analyzed using TBSS (tract-based spatial statistics) and compared to a reference framework. The reproducibility was investigated on two scans of 30 subjects acquired with an interval of approximately three weeks by studying the intraclass correlation coefficient (ICC). The sensitivity to true biological effects was evaluated by studying the regression with age on 500 subjects from 65 to 90 years old. Compared to the reference framework, the ICC improved significantly when using the proposed framework. Higher t-statistics indicated that regression coefficients with age could be determined more precisely with the proposed framework and more voxels correlated significantly with age. The application of a fiber orientation atlas and a model complexity atlas can significantly improve the reproducibility and sensitivity of crossing-fiber statistics in TBSS. [ABSTRACT FROM AUTHOR]

Diffusion MRI is a powerful tool for non-invasive probing of brain tissue microstructure. Recent multi-center efforts in the acquisition and analysis of diffusion MRI data significantly increase sample sizes and hence improve sensitivity and reliability in detecting subtle changes associated with development, aging, and diseases. However, discrepancies resulting from different scanner vendors, acquisition protocols, and image reconstruction algorithms can cause data incompatibility across imaging centers. In this paper, we introduce a model-free method that is based on the method of moments for the direct harmonization of diffusion MRI data to reduce site-specific variations. Our method directly harmonizes diffusion-attenuated signal without the need to fit any diffusion model. Moreover, our method allows the explicit definition of well-behaved mapping functions with properties such as invertibility, smoothness, and injectivity. We show that our method is effective in lowering the variations of diffusion scalars of traveling human phantoms scanned at different sites from 1%–3% to less than 0.9% for fractional anisotropy (FA) and mean diffusivity and from 1%–2.5% to 0.3%–1.2% for generalized FA. We also demonstrate its ability in preserving individual differences and in increasing across-site consistency in tractography and white matter connectivity. [ABSTRACT FROM AUTHOR]

In recent years, we have witnessed the explosion of large-scale data in various fields. Classical statistical methodologies, such as linear regression or generalized linear regression, often show inadequate performance on heterogeneous data because the key homogeneity assumption fails. In this paper, we present a flexible framework to handle heterogeneous populations that can be naturally grouped into several ordered subtypes. A local model technique utilizing ordinal class labels during the training stage is proposed. We define a new “progression score” that captures the progression of ordinal classes, and use a truncated Gaussian kernel to construct the weight function in a local regression framework. Furthermore, given the weights, we apply sparse shrinkage on the local fitting to handle high dimensionality. In this way, our local model is able to conduct variable selection on each query point. Numerical studies show the superiority of our proposed method over several existing ones. Our method is also applied to the Alzheimer’s Disease Neuroimaging Initiative data to make predictions on the longitudinal clinical scores based on different modalities of baseline brain image features. [ABSTRACT FROM AUTHOR]

Tumor growth is associated with cell invasion and mass-effect, which are traditionally formulated by mathematical models, namely reaction-diffusion equations and biomechanics. Such models can be personalized based on clinical measurements to build the predictive models for tumor growth. In this paper, we investigate the possibility of using deep convolutional neural networks to directly represent and learn the cell invasion and mass-effect, and to predict the subsequent involvement regions of a tumor. The invasion network learns the cell invasion from information related to metabolic rate, cell density, and tumor boundary derived from multimodal imaging data. The expansion network models the mass-effect from the growing motion of tumor mass. We also study different architectures that fuse the invasion and expansion networks, in order to exploit the inherent correlations among them. Our network can easily be trained on population data and personalized to a target patient, unlike most previous mathematical modeling methods that fail to incorporate population data. Quantitative experiments on a pancreatic tumor data set show that the proposed method substantially outperforms a state-of-the-art mathematical model-based approach in both accuracy and efficiency, and that the information captured by each of the two subnetworks is complementary. [ABSTRACT FROM PUBLISHER]

Principal component analysis (PCA) is an exploratory tool widely used in data analysis to uncover the dominant patterns of variability within a population. Despite its ability to represent a data set in a low-dimensional space, PCA’s interpretability remains limited. Indeed, the components produced by PCA are often noisy or exhibit no visually meaningful patterns. Furthermore, the fact that the components are usually non-sparse may also impede interpretation, unless arbitrary thresholding is applied. However, in neuroimaging, it is essential to uncover clinically interpretable phenotypic markers that would account for the main variability in the brain images of a population. Recently, some alternatives to the standard PCA approach, such as sparse PCA (SPCA), have been proposed, their aim being to limit the density of the components. Nonetheless, sparsity alone does not entirely solve the interpretability problem in neuroimaging, since it may yield scattered and unstable components. We hypothesized that the incorporation of prior information regarding the structure of the data may lead to improved relevance and interpretability of brain patterns. We therefore present a simple extension of the popular PCA framework that adds structured sparsity penalties on the loading vectors in order to identify the few stable regions in the brain images that capture most of the variability. Such structured sparsity can be obtained by combining, e.g., \ell 1 and total variation (TV) penalties, where the TV regularization encodes information on the underlying structure of the data. This paper presents the structured SPCA (denoted SPCA-TV) optimization framework and its resolution. We demonstrate SPCA-TV’s effectiveness and versatility on three different data sets. It can be applied to any kind of structured data, such as, e.g., N -dimensional array images or meshes of cortical surfaces. The gains of SPCA-TV over unstructured approaches (such as SPCA and ElasticNet PCA) or structured approach (such as GraphNet PCA) are significant, since SPCA-TV reveals the variability within a data set in the form of intelligible brain patterns that are easier to interpret and more stable across different samples. [ABSTRACT FROM PUBLISHER]

Segmenting a broad class of histological structures in transmitted light and/or fluorescence-based images is a prerequisite for determining the pathological basis of cancer, elucidating spatial interactions between histological structures in tumor microenvironments (e.g., tumor infiltrating lymphocytes), facilitating precision medicine studies with deep molecular profiling, and providing an exploratory tool for pathologists. This paper focuses on segmenting histological structures in hematoxylin- and eosin-stained images of breast tissues, e.g., invasive carcinoma, carcinoma in situ, atypical and normal ducts, adipose tissue, and lymphocytes. We propose two graph-theoretic segmentation methods based on local spatial color and nuclei neighborhood statistics. For benchmarking, we curated a data set of 232 high-power field breast tissue images together with expertly annotated ground truth. To accurately model the preference for histological structures (ducts, vessels, tumor nets, adipose, etc.) over the remaining connective tissue and non-tissue areas in ground truth annotations, we propose a new region-based score for evaluating segmentation algorithms. We demonstrate the improvement of our proposed methods over the state-of-the-art algorithms in both region- and boundary-based performance measures. [ABSTRACT FROM PUBLISHER]

The proper analysis of biological microscopy images is an important and complex task. Therefore, it requires verification of all steps involved in the process, including image segmentation and tracking algorithms. It is generally better to verify algorithms with computer-generated ground truth datasets, which, compared to manually annotated data, nowadays have reached high quality and can be produced in large quantities even for 3D time-lapse image sequences. Here, we propose a novel framework, called MitoGen, which is capable of generating ground truth datasets with fully 3D time-lapse sequences of synthetic fluorescence-stained cell populations. MitoGen shows biologically justified cell motility, shape and texture changes as well as cell divisions. Standard fluorescence microscopy phenomena such as photobleaching, blur with real point spread function (PSF), and several types of noise, are simulated to obtain realistic images. The MitoGen framework is scalable in both space and time. MitoGen generates visually plausible data that shows good agreement with real data in terms of image descriptors and mean square displacement (MSD) trajectory analysis. Additionally, it is also shown in this paper that four publicly available segmentation and tracking algorithms exhibit similar performance on both real and MitoGen-generated data. The implementation of MitoGen is freely available. [ABSTRACT FROM PUBLISHER]

Brain atlases are an essential component in understanding the dynamic cerebral development, especially for the early postnatal period. However, longitudinal atlases are rare for infants, and the existing ones are generally limited by their fuzzy appearance. Moreover, since longitudinal atlas construction is typically performed independently over time, the constructed atlases often fail to preserve temporal consistency. This problem is further aggravated for infant images since they typically have low spatial resolution and insufficient tissue contrast. In this paper, we propose a novel framework for consistent spatial-temporal construction of longitudinal atlases for developing infant brain MR images. Specifically, for preserving structural details, the atlas construction is performed in spatial-temporal wavelet domain simultaneously. This is achieved by a patch-based combination of results from each frequency subband. Compared with the existing infant longitudinal atlases, our experimental results indicate that our approach is able to produce longitudinal atlases with richer structural details and also better longitudinal consistency, thus leading to higher performance when used for spatial normalization of a group of infant brain images. [ABSTRACT FROM PUBLISHER]

As shown in the literature, methods based on multiple templates usually achieve better performance, compared with those using only a single template for processing medical images. However, most existing multi-template based methods simply average or concatenate multiple sets of features extracted from different templates, which potentially ignores important structural information contained in the multi-template data. Accordingly, in this paper, we propose a novel relationship induced multi-template learning method for automatic diagnosis of Alzheimer's disease (AD) and its prodromal stage, i.e., mild cognitive impairment (MCI), by explicitly modeling structural information in the multi-template data. Specifically, we first nonlinearly register each brain's magnetic resonance (MR) image separately onto multiple pre-selected templates, and then extract multiple sets of features for this MR image. Next, we develop a novel feature selection algorithm by introducing two regularization terms to model the relationships among templates and among individual subjects. Using these selected features corresponding to multiple templates, we then construct multiple support vector machine (SVM) classifiers. Finally, an ensemble classification is used to combine outputs of all SVM classifiers, for achieving the final result. We evaluate our proposed method on 459 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, including 97 AD patients, 128 normal controls (NC), 117 progressive MCI (pMCI) patients, and 117 stable MCI (sMCI) patients. The experimental results demonstrate promising classification performance, compared with several state-of-the-art methods for multi-template based AD/MCI classification. [ABSTRACT FROM AUTHOR]

Detailed segmentation of the vertebrae is an important pre-requisite in various applications of image-based spine assessment, surgery and biomechanical modeling. In particular, accurate segmentation of the processes is required for image-guided interventions, for example for optimal placement of bone grafts between the transverse processes. Furthermore, the geometry of the processes is now required in musculoskeletal models due to their interaction with the muscles and ligaments. In this paper, we present a new method for detailed segmentation of both the vertebral bodies and processes based on statistical shape decomposition and conditional models. The proposed technique is specifically developed with the aim to handle the complex geometry of the processes and the large variability between individuals. The key technical novelty in this work is the introduction of a part-based statistical decomposition of the vertebrae, such that the complexity of the subparts is effectively reduced, and model specificity is increased. Subsequently, in order to maintain the statistical and anatomic coherence of the ensemble, conditional models are used to model the statistical inter-relationships between the different subparts. For shape reconstruction and segmentation, a robust model fitting procedure is used to exclude improbable inter-part relationships in the estimation of the shape parameters. Segmentation results based on a dataset of 30 healthy CT scans and a dataset of 10 pathological scans show a point-to-surface error improvement of 20% and 17% respectively, and the potential of the proposed technique for detailed vertebral modeling. [ABSTRACT FROM AUTHOR]

Given that heart disease can cause abnormal motion dynamics over the cardiac cycle, understanding and quantifying cardiac motion can provide insight for clinicians to aid with diagnosis, therapy planning, and determining prognosis. The goal of this paper is to extract population-specific motion patterns from 3D displacements in order to identify the mean motion in a population, and to describe pathology-specific motion patterns in terms of the spatial and temporal components. Since there are common motion patterns observed in patients with the same condition, extracting these can lead towards a better understanding of the disease. Quantifying cardiac motion at a population level is not a simple task since images can vary widely in terms of image quality, size, resolution, and pose. To overcome this, we analyze the parameters obtained from a cardiac-specific Polyaffine motion-tracking algorithm, which are aligned both spatially and temporally to a common reference space. Once all parameters are aligned, different subjects can be compared and analyzed in the space of Polyaffine transformations by projecting the transformations to a reduced order subspace in which dominant motion patterns in each population can be extracted. Using tensor decomposition, the spatial and temporal aspects can be decoupled in order to study the components individually. The proposed method was validated on healthy volunteers and Tetralogy of Fallot patients according to known spatial and temporal behavior for each population. A key advantage of this method is the ability to regenerate motion sequences from the models, which can be visualized in terms of the full motion. [ABSTRACT FROM AUTHOR]