Tools for multiple granularity analysis of brain MRI data for individualized image analysis

Djamanakova, Aigerim; Tang, Xiaoying; Li, Xin; Faria, Andréia V.; Ceritoglu, Can; Oishi, Kenichi; Hillis, Argye E.; Albert, Marilyn; Lyketsos, Constantine G.; Miller, Michael I.; Mori, Susumu

doi:10.1016/j.neuroimage.2014.06.046

Cited by 48 publications

(58 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The hierarchical analysis, therefore, is important for examining the regional specificity of the findings. Our recent multi-ontology-level analysis confirmed expected results about the relationship between the precision (test-retest reproducibility) and ontology levels when they were used for automated multi-atlas brain segmentation (Djamanakova et al, 2014). As the level went up (thus, fewer defined structures and more voxel grouping), the precision went up, saturating at about 1.5% test-retest reproducibility using T1-weigthed images with 1mm resolution.…”

Section: Methodssupporting

confidence: 82%

Resource atlases for multi-atlas brain segmentations with multiple ontology levels based on T1-weighted MRI

Ceritoglu

et al. 2016

NeuroImage

Self Cite

View full text Add to dashboard Cite

Technologies for multi-atlas brain segmentation of T1-weighted MRI images have rapidly progressed in recent years, with highly promising results. This approach, however, relies on a large number of atlases with accurate and consistent structural identifications. Here, we introduce our atlas inventories (n = 90), which cover ages 4 – 82 years with unique hierarchical structural definitions (286 structures at the finest level). This multi-atlas library resource provides the flexibility to choose appropriate atlases for various studies with different age ranges and structure-definition criteria. In this paper, we describe the details of the atlas resources and demonstrate the improved accuracy achievable with a dynamic age-matching approach, in which atlases that most closely match the subject’s age are dynamically selected. The advanced atlas creation strategy, together with atlas pre-selection principles, are expected to support the further development of multi-atlas image segmentation.

show abstract

Section: Methodssupporting

confidence: 82%

Resource atlases for multi-atlas brain segmentations with multiple ontology levels based on T1-weighted MRI

Ceritoglu

et al. 2016

NeuroImage

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, it is of great interest to automatically select the most reliable samples, boosting up robustness of the method and its application under a clinical setting. On the other hand, many studies analyze MR images by parcellating them into several pre-defined regions of interest (ROIs) and then extracting features from each ROI (Djamanakova et al, 2014; Thung et al, 2014; Tzourio-Mazoyer et al, 2002). It is noted that PD, like many other neurodegenerative diseases, highly affects a number of brain regions (Braak et al, 2003).…”

Section: Introductionmentioning

confidence: 99%

Joint feature-sample selection and robust diagnosis of Parkinson's disease from MRI data

Adeli

Shi

et al. 2016

NeuroImage

View full text Add to dashboard Cite

Parkinson’s disease (PD) is an overwhelming neurodegenerative disorder caused by deterioration of a neurotransmitter, known as dopamine. Lack of this chemical messenger impairs several brain regions and yields various motor and non-motor symptoms. Incidence of PD is predicted to double in the next two decades, which urges more research to focus on its early diagnosis and treatment. In this paper, we propose an approach to diagnose PD using magnetic resonance imaging (MRI) data. Specifically, we first introduce a joint feature-sample selection (JFSS) method for selecting an optimal subset of samples and features, to learn a reliable diagnosis model. The proposed JFSS model effectively discards poor samples and irrelevant features. As a result, the selected features play an important role in PD characterization, which will help identify the most relevant and critical imaging biomarkers for PD. Then, a robust classification framework is proposed to simultaneously de-noise the selected subset of features and samples, and learn a classification model. Our model can also de-noise testing samples based on the cleaned training data. Unlike many previous works that perform de-noising in an unsupervised manner, we perform supervised de-noising for both training and testing data, thus boosting the diagnostic accuracy. Experimental results on both synthetic and publicly available PD datasets show promising results. To evaluate the proposed method, we use the popular Parkinson’s progression markers initiative (PPMI) database. Our results indicate that the proposed method can differentiate between PD and normal control (NC), and outperforms the competing methods by a relatively large margin. It is noteworthy to mention that our proposed framework can also be used for diagnosis of other brain disorders. To show this, we have also conducted experiments on the widely-used ADNI database. The obtained results indicate that our proposed method can identify the imaging biomarkers and diagnose the disease with favorable accuracies compared to the baseline methods.

show abstract

“…), a fully-automated multi-atlas label-fusion method for anatomical segmentation (Tang et al 2013; Djamanakova et al 2014). The volumes of striatal structures were corrected for the total brain volume.…”

Section: Methodsmentioning

confidence: 99%

Brain Microstructure and Impulsivity Differ between Current and Past Methamphetamine Users

Andres

Ernst

Oishi

et al. 2016

J Neuroimmune Pharmacol

Self Cite

View full text Add to dashboard Cite

Methamphetamine (Meth) use disorder continues to be highly prevalent worldwide. Meth users have higher impulsivity and brain abnormalities that may be different between current and past Meth users. The current study assessed impulsivity and depressive symptoms in 94 participants (27 current Meth users, 32 past Meth users and 35 non-drug user controls). Additionally, brain microstructure was assessed using diffusion tensor imaging (DTI); fractional anisotropy (FA) and mean diffusivity (MD) were assessed in the striatum, and FA, MD, radial and axial diffusivity were quantified in five white matter structures using DtiStudio.Across the three subject groups, current users had the highest self-reported impulsivity scores, while both Meth user groups had larger striatal structures than the controls. Past Meth users had the highest FA and lowest MD in the striatum, which is likely due to greater magnetic susceptibility from higher iron content and greater dendritic spine density. In white matter tracts, current Meth users had higher AD than past users, indicating greater water diffusion along the axons, and suggesting inflammation with axonal swelling. In contrast, past users had the lowest AD, indicating more restricted diffusion, which might have resulted from reactive gliosis. Although current Meth users had greater impulsivity than past users, the brain microstructural abnormalities showed differences that may reflect different stages of neuroinflammation or iron-induced neurodegeneration. Combining current and past Meth users may lead to greater variability in studies of Meth users. Longitudinal studies are needed to further evaluate the relationship between recency of Meth use and brain microstructure.

show abstract

Tools for multiple granularity analysis of brain MRI data for individualized image analysis

Cited by 48 publications

References 25 publications

Resource atlases for multi-atlas brain segmentations with multiple ontology levels based on T1-weighted MRI

Resource atlases for multi-atlas brain segmentations with multiple ontology levels based on T1-weighted MRI

Joint feature-sample selection and robust diagnosis of Parkinson's disease from MRI data

Brain Microstructure and Impulsivity Differ between Current and Past Methamphetamine Users

Contact Info

Product

Resources

About