A fully-automatic caudate nucleus segmentation of brain MRI: application in volumetric analysis of pediatric attention-deficit/hyperactivity disorder

A Volumetric Study of the Corpus Callosum in the Turkish Population

Objective The aim of this study is to measure the average corpus callosum (CC) volume of healthy Turkish humans and to analyze the effects of gender and age on volumes, including the genu, truncus, and splenium parts of the CC.

Patients and Methods Magnetic resonance imaging brain scans were obtained from 301 healthy male and female subjects, aged 11 to 84 years. The median age was 42 years (min–max: 11–82) in females and 49 years (min–max: 12–84) in males. Corpus callosum and its parts were calculated by using MRICloud. CC volumes of each subject were compared with those of the age and gender groups.

Results All volumes of the CC were significantly higher in males than females. All left volumes except BCC were significantly higher than the right volumes in both males and females. The oldest two age groups (50–69 and 70–84 years) were found to have higher bilateral CC volumes, and bilateral BCC volumes were also higher than in the other two age groups (11–29 and 30–49 years).

Conclusion The results suggest that compared with females/males, females have a faster decline in the volume of all volumes of the CC. We think that quantitative structural magnetic resonance data of the brain is vital in understanding human brain function and development.

Objective ADHD Diagnosis Using Convolutional Neural Networks Over Daily-Life Activity Records

Attention Deficit/Hyperactivity Disorder (ADHD) is the most common neurobehavioral disorder in children and adolescents. However, its etiology is still unknown, and this hinders the existence of reliable, fast and inexpensive standard diagnostic methods.

OBJECTIVE

This paper proposes an end-to-end methodology for automatic diagnosis of the combined type of ADHD.

METHODS

Diagnosis is based on the analysis of 24 hour-long activity records using Convolutional Neural Networks to classify spectrograms of activity windows.

RESULTS

We achieve up to [Formula: see text] average sensitivity, [Formula: see text] specificity and AUC values over [Formula: see text]. Overall, our figures overcome those obtained by actigraphy-based methods reported in the literature as well as others based on more expensive (and not so convenient) acquisition methods.

CONCLUSION

These results reinforce the idea that combining deep learning techniques together with actimetry can lead to a robust and efficient system for objective ADHD diagnosis.

SIGNIFICANCE

Reliance on simple activity measurements leads to an inexpensive and non-invasive objective diagn-ostic method, which can be easily implemented with daily devices.

Multivariate analyses applied to fetal, neonatal and pediatric MRI of neurodevelopmental disorders

Multivariate analysis (MVA) is a class of statistical and pattern recognition methods that involve the processing of data that contains multiple measurements per sample. MVA can be used to address a wide variety of medical neuroimaging-related challenges including identifying variables associated with a measure of clinical importance (i.e. patient outcome), creating diagnostic tests, assisting in characterizing developmental disorders, understanding disease etiology, development and progression, assisting in treatment monitoring and much more. Compared to adults, imaging of developing immature brains has attracted less attention from MVA researchers. However, remarkable MVA research growth has occurred in recent years. This paper presents the results of a systematic review of the literature focusing on MVA technologies applied to neurodevelopmental disorders in fetal, neonatal and pediatric magnetic resonance imaging (MRI) of the brain. The goal of this manuscript is to provide a concise review of the state of the scientific literature on studies employing brain MRI and MVA in a pre-adult population. Neurological developmental disorders addressed in the MVA research contained in this review include autism spectrum disorder, attention deficit hyperactivity disorder, epilepsy, schizophrenia and more. While the results of this review demonstrate considerable interest from the scientific community in applications of MVA technologies in pediatric/neonatal/fetal brain MRI, the field is still young and considerable research growth remains ahead of us.

Cerebrospinal fluid image segmentation using spatial fuzzy clustering method with improved evolutionary Expectation Maximization

Visualization of cerebrospinal fluid (CSF), that flow in the brain and spinal cord, plays an important role to detect neurodegenerative diseases such as Alzheimer's disease. This is performed by measuring the substantial changes in the CSF flow dynamics, volume and/or pressure gradient. Magnetic resonance imaging (MRI) technique has become a prominent tool to quantitatively measure these changes and image segmentation method has been widely used to distinguish the CSF flows from the brain tissues. However, this is often hampered by the presence of partial volume effect in the images. In this paper, a new hybrid evolutionary spatial fuzzy clustering method is introduced to overcome the partial volume effect in the MRI images. The proposed method incorporates Expectation Maximization (EM) method, which is improved by the evolutionary operations of the Genetic Algorithm (GA) to differentiate the CSF from the brain tissues. The proposed improvement is incorporated into a spatial-based fuzzy clustering (SFCM) method to improve segmentation of the boundary curve of the CSF and the brain tissues. The proposed method was validated using MRI images of Alzheimer's disease patient. The results presented that the proposed method is capable to filter the CSF regions from the brain tissues more effectively compared to the standard EM, FCM, and SFCM methods.

Assessing the performance of atlas-based prefrontal brain parcellation in an aging cohort

OBJECTIVE

It is unclear whether atlas-based parcellation is suitable in aging cohorts because age-related brain changes confound the performance of automatic methods. We assessed atlas-based parcellation of the prefrontal lobe in an aging population using visual assessment and volumetric and spatial concordance.

METHODS

We used an atlas-based approach to parcellate brain MR images of 90 non-demented healthy adults, aged 72.7 ± 0.7 years, and assessed performance.

RESULTS

Volumetric assessment showed that both single-atlas- and multi-atlas-based methods performed acceptably (intraclass correlation coefficient [ICC], 0.74-0.76). Spatial overlap measurements showed that multi-atlas (dice coefficient [DC], 0.84) offered an improvement over the single-atlas (DC, 0.75-0.78) approach. Visual assessment also showed that multi-atlas outperformed single atlas and identified an additional postprocessing step of cerebrospinal fluid removal, enhancing concordance (intraclass correlation coefficient, 0.86; DC, 0.89).

CONCLUSIONS

Atlas-based parcellation performed reasonably well in the aging population. Rigorous performance assessment aided method refinement and emphasizes the importance of age matching and postprocessing. Further work is required in more varied subjects.

Neuroimaging of attention-deficit/hyperactivity disorder: current neuroscience-informed perspectives for clinicians

The neuroimaging literature on attention-deficit/hyperactivity disorder (ADHD) is growing rapidly. Here, we provide a critical overview of neuroimaging studies published recently, highlighting perspectives that may be of relevance for clinicians. After a comprehensive search of PubMed, Ovid, Web of Science, and EMBASE, we located 41 pertinent papers published between January 2011 and April 2012, comprising both structural and functional neuroimaging studies. This literature is increasingly contributing to the notion that the pathophysiology of ADHD reflects abnormal interplay among large-scale brain circuits. Moreover, recent studies have begun to reveal the mechanisms of action of pharmacological treatment. Finally, imaging studies with a developmental perspective are revealing the brain correlates of ADHD over the lifespan, complementing clinical observations on the phenotypic continuity and discontinuity of the disorder. However, despite the increasing potential to eventually inform clinical practice, current imaging studies do not have validated applications in day-to-day clinical practice. Although novel analytical techniques are likely to accelerate the pace of translational applications, at the present we advise caution regarding inappropriate commercial misuse of imaging techniques in ADHD.

Automatic brain caudate nuclei segmentation and classification in diagnostic of Attention-Deficit/Hyperactivity Disorder

We present a fully automatic diagnostic imaging test for Attention-Deficit/Hyperactivity Disorder diagnosis assistance based on previously found evidences of caudate nucleus volumetric abnormalities. The proposed method consists of different steps: a new automatic method for external and internal segmentation of caudate based on Machine Learning methodologies; the definition of a set of new volume relation features, 3D Dissociated Dipoles, used for caudate representation and classification. We separately validate the contributions using real data from a pediatric population and show precise internal caudate segmentation and discrimination power of the diagnostic test, showing significant performance improvements in comparison to other state-of-the-art methods.

A comparison of VLSM and VBM in a cohort of patients with post-stroke aphasia

Studies attempting to map post-stroke cognitive or motor symptoms to lesion location have been available in the literature for over 150 years. In the last two decades, two computational techniques have been developed to identify the lesion sites associated with behavioural impairments. Voxel Based Morphometry (VBM) has now been used extensively for this purpose in many different patient populations. More recently, Voxel-based Lesion Symptom Mapping (VLSM) was developed specifically for the purpose of identifying lesion–symptom relationships in stroke patients, and has been used extensively to study, among others functions, language, motor abilities and attention. However, no studies have compared the results of these two techniques so far. In this study we compared VLSM and VBM in a cohort of 20 patients with chronic post-stroke aphasia. Comparison of the two techniques showed overlap in regions previously found to be relevant for the tasks used, suggesting that using both techniques and looking for overlaps between them can increase the reliability of the results obtained. However, overall VBM and VLSM provided only partially concordant results and the differences between the two techniques are discussed.

Functional MRI-guided probabilistic tractography of cortico-cortical and cortico-subcortical language networks in children

In this study, we analyzed the structural connectivity of cortico-cortical and cortico-subcortical language networks in healthy children, using probabilistic tractography based on high angular resolution diffusion imaging. In addition to anatomically defining seed and target regions for tractography, we used fMRI to target inferior frontal and superior temporal cortical language areas on an individual basis. Further, connectivity between these cortical and subcortical (thalamus, caudate nucleus) language regions was assessed. Overall, data from 15 children (8f) aged 8-17 years (mean age 12.1 ±3 years) could be included. A slight but non-significant trend towards leftward lateralization was found in the arcuate fasciculus/superior longitudinal fasciculus (AF/SLF) using anatomically defined masks (p>.05, Wilcoxon rank test), while the functionally-guided tractography showed a significant lateralization to the left (p<.01). Connectivity of the thalamus with language regions was strong but not lateralized. Connectivity of the caudate nucleus with inferior-frontal language regions was also symmetrical, while connectivity with superior-temporal language regions was strongly lateralized to the left (p<.01). To conclude, we could show that tracking the arcuate fasciculus/superior longitudinal fasciculus is possible using both anatomically and functionally-defined seed and target regions. With the latter approach, we could confirm the presence of structurally-lateralized cortico-cortical language networks already in children, and finally, we could demonstrate a strongly asymmetrical connectivity of the caudate nucleus with superior temporal language regions. Further research is necessary in order to assess the usability of such an approach to assess language dominance in children unable to participate in an active fMRI study.