Medical-image Analysis and Statistical Interpretation (MASI) Lab

Anatomical context improves deep learning on the brain age estimation task

Jul. 12, 2019—Bermudez, C., Plassard, A. J., Chaganti, S., Huo, Y., Aboud, K. E., Cutting, L. E., … & Landman, B. A. (2019). Anatomical context improves deep learning on the brain age estimation task. Magnetic Resonance Imaging. Full Text: https://www.ncbi.nlm.nih.gov/pubmed/31247249 Abstract Deep learning has shown remarkable improvements in the analysis of medical images without the need for...

An overview of the proposed method. Three geometric features (iH, SD, H) are used for training the spherical U-Net to predict 49 cortical parcellation labels. For each geometric property, intermediate deformation fields draw a total of 11+11 respective samples after boundary and geometric alignment for data augmentation. The cortical parcellation is then performed using the original geometric features of testing subjects.

Cortical Surface Parcellation using Spherical Convolutional Neural Networks

Jun. 6, 2019—*Prasanna Parvathaneni, *Shunxing Bao, Vishwesh Nath, David H. Zald, Neil D. Woodward, Daniel O. Claassen, Carissa Cascio, Yuankai Huo, Bennett A. Landman, Ilwoo Lyu, “Cortical Surface Parcellation using Spherical Convolutional Neural Networks”, MICCAI 2019 (Accepted). Abstract We present cortical surface parcellation using spherical deep convolutional neural networks. Traditional multi-atlas cortical surface parcellation requires inter-subject surface registration using geometric features with high processing time...

Improved gray matter surface based spatial statistics in neuroimaging studies

May. 21, 2019—Prasanna Parvathaneni; Ilwoo Lyu; Yuankai Huo; Baxter P. Rogers; Kurt G. Schilling; Vishwesh Nath; Justin A Blaber; Allison E Hainline; Adam W Anderson; Neil D. Woodward; Bennett A Landman. “Improved gray matter surface based spatial statistics in neuroimaging studies.” In MRI – Accepted. Abstract Neuroimaging often involves acquiring high-resolution anatomical images along with other low-resolution image modalities,...

Compensation of Gradient Field Nonlinearity and Signal Drift in Diffusion Weighted MRI

Apr. 1, 2019—Colin B. Hansen, Vishwesh Nath, Kurt G. Schilling, Justin A. Blaber, Baxter P. Rogers, Bennett A. Landman, “Compensation of Gradient Field Nonlinearity and Signal Drift in Diffusion Weighted MRI.” ISBI, Venice, Italy, 2019 Diffusion weighted magnetic resonance imaging (DW-MRI) represents an important method of studying local brain tissue microarchitecture and structural connectivity. Interpretation of DW-MRI is challenging...

Learning 3D White Matter Microstructure from 2D Histology

Apr. 1, 2019—Histological analysis is typically the gold standard for validating measures of tissue microstructure derived from magnetic resonance imaging (MRI) contrasts. However, most histological investigations are inherently 2-dimensional (2D), due to increased field-of-view, higher in-plane resolutions, ease of acquisition, decreased costs, and a large number of available contrasts compared to 3-dimensional (3D) analysis. Because of this,...

Consideration of Cerebrospinal Fluid Intensity Variation in Diffusion Weighted MRI

Feb. 7, 2019—Colin B. Hansen, Vishwesh Nath, Allison E. Hainline, Kurt G. Schilling, Prasanna Parvathaneni, Roza G. Bayrak, Justin A. Blaber, Owen Williams, Susan Resnick, Lori Beason-Held, Okan Irfanoglu, Carlo Pierpaoli, Adam W. Anderson, Baxter P. Rogers, Bennett A. Landman, “Consideration of Cerebrospinal Fluid Intensity Variation in Diffusion Weighted MRI.” SPIE Medical Imaging, San Diego, CA, 2019 Abstract Diffusion weighted MRI (DW-MRI) depends on...

Imaging Biomarkers in Thyroid Eye Disease and their Clinical Associations

Dec. 18, 2018—Shikha Chaganti, Katrina Nelson, Kevin Mundy, Robert Harrigan, Robert Galloway, Louise A. Mawn, Bennett Landman, “Imaging biomarkers in thyroid eye disease and their clinical associations,” Journal of Medical Imaging. (2018), doi: 10.1117/1.JMI.5.4.044001. Abstract Purpose: The purpose of this study is to understand the phenotypes of thyroid eye disease (TED) through data derived from a multi-atlas...

Electronic Medical Record Context Signatures Improve Diagnostic Classification using Medical Image Computing

Dec. 17, 2018—Shikha Chaganti, Louise A. Mawn, Hakmook Kang, Josephine Egan, Susan M. Resnick, Lori L. Beason-Held, Bennett A. Landman, Thomas A. Lasko. “Electronic Medical Record Context Signatures Improve Diagnostic Classification using Medical Image Computing”. IEEE Journal of Biomedical and Health Informatics. (In Press) Abstract Composite models that combine medical imaging with electronic medical records (EMR) improve...

Subset of DTI streamlines for each tracking strategy. Labels for crown, wall, and fundi are shown with a zoomed in view of the SFG. DTI streamlines are shown for M1 (whole brain seeding), M2 (WM seeding), and M3 (WMGM boundary seeding), and are colored based on streamline orientation. The dashed arrow highlights a fundus, where no streamlines are able to propagate. The solid arrow points toward the increased curvature of streamlines entering the GM. And the oval highlights a large, homogenous, area of WM, where seeding will contribute to over‐representation of fibers terminating at the crown

Confirmation of a Gyral Bias in Diffusion MRI Fiber Tractography

Dec. 15, 2018—Kurt G Schilling, Yurui Gao, Iwona Stepniewska, Bennett A. Landman, and Adam W Anderson. “Confirmation of a Gyral Bias in Diffusion MRI Fiber Tractography”. Human Brain Mapping. 2018 Mar;39(3):1449-1466. doi: 10.1002/hbm.23936. Full text: https://www.ncbi.nlm.nih.gov/pubmed/?term=Confirmation+of+a+Gyral+Bias+in+Diffusion+MRI+Fiber+Tractography Abstract Diffusion MRI fiber tractography has been increasingly used to map the structural connectivity of the human brain. However, this technique...

Fiber orientation estimation in a crossing fiber region. The results of structure tensor analysis on a myelin-stained histological slice shown as a color-coded orientation map (A), is shown zoomed in on two regions containing crossing (yellow box), and disperse (blue box) fibers. The resulting FODs are displayed at varying resolution levels (B). From the resulting FODs, voxels are characterized as crossing fiber (C; green) vs. not-crossing fibers (C; red), as well as single fiber (D; red) vs. complex fibers (D; green), at all resolutions. Note that “not-crossing” voxels are those that with single fiber populations in addition to complex fibers that do not contain two discrete local maxima. Voxels from diffusion MRI in the same region are also displayed as single fiber (E; red) vs. crossing fibers (E; green). Histograms for this specific region of interest show percentages of crossing fibers (F; left) and percentages of complex fibers (F; middle) for histology, as well as percentage of crossing fibers (F; right) for dMRI.

Can increased spatial resolution solve the crossing fiber problem for diffusion MRI?

Dec. 15, 2018—Kurt G Schilling, Yurui Gao, Vaibhav Janve, Iwona Stepniewska, Bennett A Landman, Adam W Anderson. “Can increased spatial resolution solve the crossing fiber problem for diffusion MRI?”. NMR in Biomedicine. (2017) 30(12),e3787. https://doi.org/10.1002/nbm.3787. Full text: https://www.ncbi.nlm.nih.gov/pubmed/?term=Can+increased+spatial+resolution+solve+the+crossing+fiber+problem+for+diffusion+MRI%3F Abstract It is now widely recognized that voxels with crossing fibers or complex geometrical configurations present a challenge for...

« Previous Page