Medical-image Analysis and Statistical Interpretation (MASI) Lab

Mosaic of dissections of the first timepoint of the first HCP subject from 20 raters (left), all dissections look extremely similar. On the right, the average dissection (gold standard) in both the streamlines and the voxel representations. The coloring is based on the orientation of each streamline, where the X/Y/Z differences are mapped to R/G/B. To be considered part of the gold standard, elements had to be labeled in at least 50% of dissection associated with each subject. The PYT had a more consistent spatial coverage compared to the first Tractostorm project (only bundle in common)

Tractostorm 2: Optimizing tractography dissection reproducibility with segmentation protocol dissemination

Feb. 11, 2022—Rheault, Francois, Kurt G. Schilling, Alex Valcourt-Caron, Antoine Théberge, Charles Poirier, Gabrielle Grenier, Guido I. Guberman, John Begnoche, Jon Haitz Legarreta, Leon Y. Cai, Maggie Roy, Manon Edde, Marco Perez Caceres, Mario Ocampo-Pineda, Noor Al-Sharif, Philippe Karan, Pietro Bontempi, Sami Obaid, Sara Bosticardo, Simona Schiavi, Viljami Sairanen, Alessandro Daducci, Laurie E. Cutting, Laurent Petit, Maxime...

Longitudinal changes of connectomes and graph theory measures in aging

Jan. 17, 2022—Yuzhe Wang, Francois Rheault, Kurt G. Schilling, Lori L. Beason-Held, Andrea T. Shafer, Susan M. Resnick, Bennett A. Landman Abstract Changes in brain structure and connectivity in aging can be probed through diffusion weighted MRI and summarized with structural connectome matrices. Complex network analysis based on graph theory has been applied to provide measures that...

pyPheWAS: A Phenome-Disease Association Tool for Electronic Medical Record Analysis

Jan. 12, 2022—Kerley, C.I., Chaganti, S., Nguyen, T.Q. et al. pyPheWAS: A Phenome-Disease Association Tool for Electronic Medical Record Analysis. Neuroinform (2022). https://doi.org/10.1007/s12021-021-09553-4 Full text: NIHMSID, Springer Abstract Along with the increasing availability of electronic medical record (EMR) data, phenome-wide association studies (PheWAS) and phenome-disease association studies (PheDAS) have become a prominent, first-line method of analysis for uncovering...

Representative images are predicted to associate with comorbidities and ICD-10 codes
(phenotype components) identified in each risk category. The red outlines show the pancreas
tissue can be different under phenotyping contexts. (1) is from a nominally healthy pancreas
group with potential lung infections; (2) is from type I diabetes and other chronic kidney disease
patients with atrophic pancreas; (3) is from other metabolic syndromes including type II diabetes;
(4) is from patients with weight loss and pancreatitis.

Pancreas CT Segmentation by Predictive Phenotyping

Dec. 14, 2021—Y. Tang, R.Gao, H.H.Lee, Q.Yang, X.Yu,Y.Zhou, S.Bao, Y.Huo, J.Spraggins, J.Virostko, Z.Xu, B.A. Landman. “Pancreas CTSegmentation by Predictive Phenotyping”. International Conference on MedicalImage Computing and Computer Assisted Intervention(MICCAI), 2021 Full Text: https://link.springer.com/chapter/10.1007/978-3-030-87193-2_3 Abstract Pancreas CT segmentation offers promise at understanding the structural manifestation of metabolic conditions. To date, the medical primary record of conditions that impact...

Method framework. Given a CT scan with at high resolution of ~0.8 x ~0.8 x ~2 mm, a low-res section (left panel) is trained with multi-channel segmentation. The low-res part contains down-sampling and normalization in order to preserve the complete spatial information. After the coarse segmentations are acquired from low- res UNet, we interpolate the mask to match the image’s original resolution. Next, random patch sampling (mid panel) is employed to collect patches, and patches are concatenated with corresponding coarse segmentation masks. Finally, we trained a patch-based high-res (right panel) segmentation model, the high-dimensional probability maps are acquired from integration of all patches on field of views. Majority vote is used to merge estimates into a final segmentation.

High-resolution 3D abdominal segmentation with random patch network fusion

Dec. 14, 2021—Y. Tang,R.Gao,S.Han, Y.Chen, D.Gao, V.Nath, C.Bermudez, M.R. Savona, R.G. Abramson, S.Bao,I.Lyu, Y.Huo and B.A. Landman,“High-resolution 3D Abdominal Segmentation with Random PatchNetworkFusion”,Medical Image Analysis, 2021. Full Text: https://www.sciencedirect.com/science/article/pii/S1361841520302589 Abstract Deep learning for three dimensional (3D) abdominal organ segmentation on high-resolution computed to- mography (CT) is a challenging topic, in part due to the limited memory provide...

Effects of gradient non-linearity in clinically relevant field of view

Mapping the impact of non-linear gradient fields on diffusion MRI tensor estimation

Dec. 11, 2021—Praitayini Kanakaraj, Colin B. Hansen, Francois Rheault, Leon Y. Cai, Baxter P. Rogers, Kurt G. Schilling and Bennett A. Landman. “Mapping the impact of non-linear gradient fields on diffusion MRI tensor estimation”. SPIE Medical Imaging 2022. Accepted. Full Text Abstract Non-linear gradients impact diffusion weighted (DW) MRI by corrupting the experimental setup and lead to problems during...

Inpainting Missing Tissue in Multiplexed Immunofluorescence Imaging

Dec. 10, 2021—Shunxing Bao, Yucheng Tang, Ho Hin Lee, Riqiang Gao, Qi Yang, Xin Yu, Sophie Chiron, Lori A. Coburn, Keith T. Wilson, Joseph T. Roland, Bennett A. Landman, Yuankai Huo. “Inpainting Missing Tissue in Multiplexed Immunofluorescence Imaging” Medical Imaging 2022: Digital and Computational Pathology. International Society for Optics and Photonics, accepted Full text: [TBD] Abstract Multiplex immunofluorescence (MxIF) is...

Accelerating 2D Abdominal Organ Segmentation with Active Learning

Dec. 10, 2021—Xin Yu, Yucheng Tang, Qi Yang, Ho Hin Lee, Shunxing Bao, Ann Zenobia Moore, Luigi Ferrucci, Bennett A. Landman Abdominal computed tomography CT imaging enables assessment of body habitus and organ health. Quantification of these health factors necessitates semantic segmentation of key structures. Deep learning efforts have shown remarkable success in automating segmentation of...

Quantification of muscle, bones and fat on single slice thigh CT

Dec. 10, 2021—Qi Yang, Xin Yu, Ho Hin Lee, Yucheng Tang, Shunxing Bao, Kristofer S Gravenstein, Ann Zenobia Moore, Sokratis Makrogiannis ,Luigi Ferrucci , Bennett A Landman Abstract Muscle, bone, and fat segmentation of CT thigh slice is essential for body composition research. Voxel-wise image segmentation enables quantification of tissue properties including area, intensity and texture. Deep learning...

Joint independent component analysis for hypothesizing spatiotemporal relationships between longitudinal gray and white matter changes in preclinical Alzheimer’s disease

Dec. 10, 2021—Leon Y. Cai, Francois Rheault, Cailey I. Kerley, Katherine S. Aboud, Lori L. Beason-Held, Andrea T. Shafer, Susan M. Resnick, Lori C. Jordan, Adam W. Anderson, Kurt G. Schilling, and Bennett A. Landman Abstract Characterizing relationships between gray matter (GM) and white matter (WM) in early Alzheimer’s disease (AD) would improve understanding of how and...

« Previous Page