Biology subjects

Keshavan, A.

Publications and source records attributed to Keshavan, A..

4 recordsLinked to original sources

bioRxiv2018

Combining citizen science and deep learning to amplify expertise in neuroimaging

Research in many fields has become increasingly reliant on large and complex datasets. \"Big Data\" holds untold promise to rapidly advance science by tackling new questions that cannot be answered with smaller datasets. While powerful, research with Big Data poses unique challenges, as many standard lab protocols rely on experts examining each one of the samples. This is not feasible for large-scale datasets because manual approaches are time-consuming and hence difficult to scale. Meanwhile, automated approaches lack the accuracy of examination by highly trained scientists and this may introduce major errors, sources of noise, and unforeseen biases into these large and complex datasets. Our proposed solution is to 1) start with a small, expertly labelled dataset, 2) amplify labels through web-based tools that engage citizen scientists, and 3) train machine learning on amplified labels to emulate expert decision making. As a proof of concept, we developed a system to quality control a large dataset of three-dimensional magnetic resonance images (MRI) of human brains. An initial dataset of 200 brain images labeled by experts were amplified by citizen scientists to label 722 brains, with over 80,000 ratings done through a simple web interface. A deep learning algorithm was then trained to predict data quality, based on a combination of the citizen scientist labels that accounts for differences in the quality of classification by different citizen scientists. In an ROC analysis (on left out test data), the deep learning network performed as well as a state-of-the-art, specialized algorithm (MRIQC) for quality control of T1-weighted images, each with an area under the curve of 0.99. Finally, as a specific practical application of the method, we explore how brain image quality relates to the replicability of a well established relationship between brain volume and age over development. Combining citizen science and deep learning can generalize and scale expert decision making; this is particularly important in emerging disciplines where specialized, automated tools do not already exist.

neuroscience↗

bioRxiv2017

Investigating The Functional Consequence Of White Matter Damage: An Automatic Pipeline To Create Longitudinal Disconnection Tractograms

Neurosurgical resection is one of the few opportunities researchers have to image the human brain both prior to and following focal damage. One of the challenges associated with studying brains undergoing surgical resection is that they often do not fit the brain templates most image-processing methodologies are based on, so manual intervention is required to reconcile the pathology and the most extreme cases must be excluded. Manual intervention requires significant time investment and introduces reproducibility concerns. We propose an automatic longitudinal pipeline based on High Angular Resolution Diffusion Imaging acquisitions to facilitate a Pathway Lesion Symptom Mapping analysis relating focal white matter injury to functional deficits. This two-part approach includes (i) automatic segmentation of focal white matter injury from anisotropic power differences, and (ii) modeling disconnection using tractography on the single-subject level, which specifically identifies the disconnections associated with focal white matter damage. The advantages of this approach stem from (1) objective and automatic lesion segmentation and tractogram generation, (2) objective and precise segmentation of affected tissue likely to be associated with damage to long-range white matter pathways (defined by anisotropic power), (3) good performance even in the cases of anatomical distortions by use of nonlinear tensor-based registration in the patient space, which aligns images using white matter contrast. Mapping a system as variable and complex as the human brain requires sample sizes much larger than the current technology can support. This pipeline can be used to execute large-scale, sufficiently powered analyses by meeting the need for an automatic approach to objectively quantify white matter disconnection.\n\nAbbreviations\n\nFundingThis work was supported by the National Institutes of Health [5R01NS066654-05]; KJ was supported by the Department of Defense (DoD) [National Defense Science & Engineering Graduate Fellowship (NDSEG) Program].

bioengineering↗

bioRxiv2016

Mindboggling morphometry of human brains

Mindboggle (http://mindboggle.info) is an open source brain morphometry platform that takes in preprocessed T1-weighted MRI data and outputs volume, surface, and tabular data containing label, feature, and shape information for further analysis. In this article, we document the software and demonstrate its use in studies of shape variation in healthy and diseased humans. The number of different shape measures and the size of the populations make this the largest and most detailed shape analysis of human brains every conducted. Brain image morphometry shows great potential for providing much-needed biological markers for diagnosing, tracking, and predicting progression of mental health disorders. Very few software algorithms provide more than measures of volume and cortical thickness, and more subtle shape measures may provide more sensitive and specific biomarkers. Mindboggle computes a variety of (primarily surface-based) shapes: area, volume, thickness, curvature, depth, Laplace-Beltrami spectra, Zernike moments, etc. We evaluate Mindboggles algorithms using the largest set of manually labeled, publicly available brain images in the world and compare them against state-of-the-art algorithms where they exist. All data, code, and results of these evaluations are publicly available.\n\nAuthor SummaryBrains vary in many ways, including their shape. Analysing differences in shape between brains or changes in brain shape over time has been used to characterize morphology of diseased brains, but these analyses conventionally rely on simple volumetric shape measures. We believe that access to a greater variety of shape measures could provide greater sensitivity and specificity to morphological disturbances, and could aid in diagnosis, tracking, and prediction of the progression of mental health disorders. Mindboggle is open source software that provides neuroscientists (and indeed, anyone interested in computing shapes) tools for computing a variety of shape measures, including area, volume, thickness, curvature, geodesic depth, travel depth, Laplace-Beltrami spectra, and Zernike moments. In addition to algorithmic contributions, we conducted evaluations and applied Mindboggle to conduct the most detailed shape analysis of human brains.

neuroscience↗

bioRxiv2016

Mindcontrol: A Web Application for Brain Segmentation Quality Control

Tissue classification plays a crucial role in the investigation of normal neural development, brain-behavior relationships, and the disease mechanisms of many psychiatric and neurological illnesses. Ensuring the accuracy of tissue classification is important for quality research and, in particular, the translation of imaging biomarkers to clinical practice. Assessment with the human eye is vital to correct various errors inherent to all currently available segmentation algorithms. Manual quality assurance becomes methodologically difficult at a large scale - a problem of increasing importance as the number of data sets is on the rise. To make this process more efficient, we have developed Mindcontrol, an open-source web application for the collaborative quality control of neuroimaging processing outputs. The Mindcontrol platform consists of a dashboard to organize data, descriptive visualizations to explore the data, an imaging viewer, and an in-browser annotation and editing toolbox for data curation and quality control. Mindcontrol is flexible and can be configured for the outputs of any software package in any data organization structure. Example configurations for three large, open-source datasets are presented: the 1000 Functional Connectomes Project (FCP), the Consortium for Reliability and Reproducibility (CoRR), and the Autism Brain Imaging Data Exchange (ABIDE) Collection. These demo applications link descriptive quality control metrics, regional brain volumes, and thickness scalars to a 3D imaging viewer and editing module, resulting in an easy-to-implement quality control protocol that can be scaled for any size and complexity of study.

bioinformatics↗