Caryne Craige

Multi-Atlas Segmentation with Joint Label Fusion

Multi-atlas segmentation is an effective approach for automatically labeling objects of interest in biomedical images. In this approach, multiple expert-segmented example images, called atlases, are registered to a target image, and deformed atlas segmentations are combined using label fusion. Among the proposed label fusion strategies, weighted voting with spatially varying weight distributions derived from atlas-target intensity similarity have been particularly successful. However, one limitation of these strategies is that the weights are computed independently for each atlas, without taking into account the fact that different atlases may produce similar label errors. To address this limitation, we propose a new solution for the label fusion problem in which weighted voting is formulated in terms of minimizing the total expectation of labeling error and in which pairwise dependency between atlases is explicitly modeled as the joint probability of two atlases making a segmentation error at a voxel. This probability is approximated using intensity similarity between a pair of atlases and the target image in the neighborhood of each voxel. We validate our method in two medical image segmentation problems: hippocampus segmentation and hippocampus subfield segmentation in magnetic resonance (MR) images. For both problems, we show consistent and significant improvement over label fusion strategies that assign atlas weights independently.

A learning-based wrapper method to correct systematic errors in automatic image segmentation: Consistently improved performance in hippocampus, cortex and brain segmentation☆

We propose a simple but generally applicable approach to improving the accuracy of automatic image segmentation algorithms relative to manual segmentations. The approach is based on the hypothesis that a large fraction of the errors produced by automatic segmentation are systematic, i.e., occur consistently from subject to subject, and serves as a wrapper method around a given host segmentation method. The wrapper method attempts to learn the intensity, spatial and contextual patterns associated with systematic segmentation errors produced by the host method on training data for which manual segmentations are available. The method then attempts to correct such errors in segmentations produced by the host method on new images. One practical use of the proposed wrapper method is to adapt existing segmentation tools, without explicit modification, to imaging data and segmentation protocols that are different from those on which the tools were trained and tuned. An open-source implementation of the proposed wrapper method is provided, and can be applied to a wide range of image segmentation problems. The wrapper method is evaluated with four host brain MRI segmentation methods: hippocampus segmentation using FreeSurfer (Fischl et al., 2002); hippocampus segmentation using multi-atlas label fusion (Artaechevarria et al., 2009); brain extraction using BET (Smith, 2002); and brain tissue segmentation using FAST (Zhang et al., 2001). The wrapper method generates 72%, 14%, 29% and 21% fewer erroneously segmented voxels than the respective host segmentation methods. In the hippocampus segmentation experiment with multi-atlas label fusion as the host method, the average Dice overlap between reference segmentations and segmentations produced by the wrapper method is 0.908 for normal controls and 0.893 for patients with mild cognitive impairment. Average Dice overlaps of 0.964, 0.905 and 0.951 are obtained for brain extraction, white matter segmentation and gray matter segmentation, respectively.

Bias in estimation of hippocampal atrophy using deformation-based morphometry arises from asymmetric global normalization: an illustration in ADNI 3 T MRI data.

Measurement of brain change due to neurodegenerative disease and treatment is one of the fundamental tasks of neuroimaging. Deformation-based morphometry (DBM) has been long recognized as an effective and sensitive tool for estimating the change in the volume of brain regions over time. This paper demonstrates that a straightforward application of DBM to estimate the change in the volume of the hippocampus can result in substantial bias, i.e., an overestimation of the rate of change in hippocampal volume. In ADNI data, this bias is manifested as a non-zero intercept of the regression line fitted to the 6 and 12 month rates of hippocampal atrophy. The bias is further confirmed by applying DBM to repeat scans of subjects acquired on the same day. This bias appears to be the result of asymmetry in the interpolation of baseline and followup images during longitudinal image registration. Correcting this asymmetry leads to bias-free atrophy estimation.

Histology-derived volumetric annotation of the human hippocampal subfields in postmortem MRI.

Recently, there has been a growing effort to analyze the morphometry of hippocampal subfields using both in vivo and postmortem magnetic resonance imaging (MRI). However, given that boundaries between subregions of the hippocampal formation (HF) are conventionally defined on the basis of microscopic features that often lack discernible signature in MRI, subfield delineation in MRI literature has largely relied on heuristic geometric rules, the validity of which with respect to the underlying anatomy is largely unknown. The development and evaluation of such rules are challenged by the limited availability of data linking MRI appearance to microscopic hippocampal anatomy, particularly in three dimensions (3D). The present paper, for the first time, demonstrates the feasibility of labeling hippocampal subfields in a high resolution volumetric MRI dataset based directly on microscopic features extracted from histology. It uses a combination of computational techniques and manual post-processing to map subfield boundaries from a stack of histology images (obtained with 200μm spacing and 5μm slice thickness; stained using the Kluver-Barrera method) onto a postmortem 9.4Tesla MRI scan of the intact, whole hippocampal formation acquired with 160μm isotropic resolution. The histology reconstruction procedure consists of sequential application of a graph-theoretic slice stacking algorithm that mitigates the effects of distorted slices, followed by iterative affine and diffeomorphic co-registration to postmortem MRI scans of approximately 1cm-thick tissue sub-blocks acquired with 200μm isotropic resolution. These 1cm blocks are subsequently co-registered to the MRI of the whole HF. Reconstruction accuracy is evaluated as the average displacement error between boundaries manually delineated in both the histology and MRI following the sequential stages of reconstruction. The methods presented and evaluated in this single-subject study can potentially be applied to multiple hippocampal tissue samples in order to construct a histologically informed MRI atlas of the hippocampal formation.

Serotonin (2C) receptor regulation of cocaine-induced conditioned place preference and locomotor sensitization

Previous studies have identified an inhibitory regulatory role of the 5-HT(2C) receptor in serotonin and dopamine neurotransmission. As cocaine is known to enhance serotonin and dopamine transmission, the ability of 5-HT(2C) receptors to modulate cocaine-induced behaviors was investigated. Alterations in cocaine reward behavior were assessed in the conditioned place preference (CPP) paradigm. Mice were injected with a selective 5-HT(2C) receptor agonist, Ro 60-0175 (0, 1, 3, 10 mg/kg, i.p.) prior to cocaine administration (10 mg/kg, i.p.) on cocaine-conditioning days. Administration of Ro 60-0175(10 mg/kg) prior to cocaine attenuated the development of cocaine place preference. To assess the potential of the 5-HT(2C) receptor to influence cocaine-induced behavioral sensitization, mice were pretreated with either saline or Ro 60-0175 (10 mg/kg, i.p.) and 30 min later, administered cocaine (20 mg/kg, i.p.) or saline once daily for 5 days. Locomotor activity was measured daily following cocaine administration. After a 10-day drug-free period, locomotor activity was measured on day 16 following a challenge injection of cocaine (20 mg/kg, i.p.). Pharmacological activation of 5-HT(2C) receptors with Ro 60-0175 attenuated acute cocaine-induced activity on days 1-5, as well as the development of long-term cocaine-induced locomotor sensitization. Thus, activation of 5-HT(2C) receptors attenuated the rewarding and locomotor-stimulating effects of cocaine, as well as inhibited the development of sensitization. The current study shows that 5-HT(2C) receptor activity exerts an inhibitory influence on the short-term and long-term behavioral responses to cocaine.

Pharmacological Modulation of GSAP Reduces Amyloid-β Levels and Tau Phosphorylation in a Mouse Model of Alzheimer's Disease with Plaques and Tangles

Accumulation of neurotoxic amyloid-β (Aβ) is a major hallmark of Alzheimers disease (AD) pathology and an important player in its clinical manifestations. Formation of Aβ is controlled by the availability of an enzyme called γ-secretase. Despite its blockers being attractive therapeutic tools for lowering Aβ, this approach has failed because of their serious toxic side-effects. The discovery of the γ-secretase activating protein (GSAP), a co-factor for this protease which facilitates Aβ production without affecting other pathways responsible for the toxicity, is giving us the opportunity to develop a safer anti-Aβ therapy. In this study we have characterized the effect of Imatinib, an inhibitor of GSAP, in the 3×Tg mice, a mouse model of AD with plaques and tangles. Compared with controls, mice receiving the drug had a significant reduction in brain Aβ levels and deposition, but no changes in the steady state levels of AβPP, BACE-1, ADAM-10, or the four components of the γ-secretase complex. By contrast, Imatinib-treated animals had a significant increase in CTF-β and a significant reduction in GSAP expression levels. Additionally, we observed that tau phosphorylation was reduced at specific epitopes together with its insoluble fraction. In vitro studies confirmed that Imatinib prevents Aβ formation by modulating γ-secretase activity and GSAP levels. Our findings represent the first in vivo demonstration of the biological role that GSAP plays in the development of the AD-like neuropathologies. They establish this protein as a viable target for a safer anti-Aβ therapeutic approach in AD.

Standing on the shoulders of giants: improving medical image segmentation via bias correction

We propose a simple strategy to improve automatic medical image segmentation. The key idea is that without deep understanding of a segmentation method, we can still improve its performance by directly calibrating its results with respect to manual segmentation. We formulate the calibration process as a bias correction problem, which is addressed by machine learning using training data. We apply this methodology on three segmentation problems/methods and show significant improvements for all of them.

Shape-based semi-automatic hippocampal subfield segmentation with learning-based bias removal

We develop a semi-automatic technique for segmentation of hippocampal subfields in T2-weighted in vivo brain MRI. The technique takes the binary segmentation of the whole hippocampus as input, and automatically labels the subfields inside the hippocampus segmentation. Shape priors for the hippocampal subfields are generated from shape-based normalization of whole hippocampi via the continuous medial representation method. To combine the shape priors with appearance features, we use a machine learning based method. The key novelty is that we treat the mistakes made by the shape priors as bias, which can be detected and corrected via learning. The main advantage of this formulation is that it significantly simplifies the learning problem by taking full advantage of current segmentations and focusing on only improving their drawbacks. Experiments show that the bias removal approach achieves significant improvement in all subfields. Our bias removal idea is general, and can be applied to improve other segmentation methods as well.

Stress, Anxiety, and Cocaine Abuse

Abstract Heightened anxiety and sensitivity to stress following chronic cocaine use are likely to increase an individuals susceptibility for relapse to drug-seeking behavior. Thus, it is important to investigate the neural mechanisms responsible for the regulation of anxiety during cocaine withdrawal and stress-induced relapse in order to identify potential targets for pharmacological intervention. This chapter will address the involvement of several neurotransmitter systems in regulating anxiety during cocaine withdrawal and stress-induced relapse mechanisms. The distinct roles of the dopamine, serotonin, corticotropin releasing factor, norepinephrine, and opioid systems in regulating the negative consequences of cocaine withdrawal and the effects of stress in eliciting relapse to drug use will be discussed. In addition, a section detailing the potential role of other neuropeptides like cholecystokinin and neuropeptide Y in cocaine withdrawal-induced anxiety and stress-induced relapse is included. It is important to consider the roles of these brain-signaling systems separately, as well as integrated in a network that functions in regulating anxiety during cocaine withdrawal and the effects of stress on drug abuse and relapse to drug use. By targeting these regulatory mechanisms, potential pharmacological targets may be identified in support of the prevention of relapse to drug use.