Harmonization Category

Figure 3. We perform kernel conversion on paired hard and soft CT kernel images using a pix2pix GAN. The generator, a U-Net, takes as input the source CT kernel image and predicts a residue image. The output kernel is obtained by adding the residue image to the input source kernel image. The discriminator, a PatchGAN, takes as input the generated image and the input kernel, and outputs the probability of the generated image being a translated version of the input.

Lung CT harmonization of paired reconstruction kernel images using generative adversarial networks

Apr. 24, 2024—Aravind R. Krishnan, Kaiwen Xu, Thomas Li, Lucas W. Remedios, Kim L. Sandler, Fabien Maldonado, Bennett A. Landman. “Lung CT harmonization of paired reconstruction kernel images using generative adversarial networks.”Med Phys. 2024;1-14.https://doi.org/10.1002/mp.17028 Abstract Background The kernel used in CT image reconstruction is an important factor that determines the texture of the CT image. Consistency of reconstruction...

A cycle GAN consists of a forward and backward path. In the forward path, the source encoder and target decoder combine together to form a U-Net that generates a synthetic image with the style of the target domain. The synthetic image and the real target domain image are passed as inputs to a discriminator DB which distinguishes whether the generated image is real or fake. In the backward path, a synthetic image with the style of the source domain is generated which is fed to discriminator DA along with the source domain image.

Inter-vendor harmonization of CT reconstruction kernels using unpaired image translation

Dec. 1, 2023—Aravind R. Krishnan, Kaiwen Xu, Thomas Li, Chenyu Gao, Lucas W. Remedios, Praitayini Kanakaraj, Ho Hin Lee, Shunxing Bao, Kim L. Sandler, Fabien Maldonado, Ivana Išgum, and Bennett A. Landman “Inter-vendor harmonization of CT reconstruction kernels using unpaired image translation”, Proc. SPIE 12926, Medical Imaging 2024: Image Processing, 129261D (2 April 2024); https://doi.org/10.1117/12.3006608 Abstract The reconstruction kernel in computed tomography (CT) generation determines the texture of the image. Consistency...

Learning site-invariant features of connectomes to harmonize complex network measures

Dec. 1, 2023—Figure 1. Previous research elucidated that connectomes suffer from confounding site effects. In this work we propose a data-driven model to learn disjoint site (𝑐 = {1,2}) and biological features (siteless z) for BIOCARD (orange) and VMAP (blue) (left). We then inject a prescribed site, c’, to the learned representations to compute harmonized connectome modularity,...

Characterizing Streamline Count Invariant Graph Measures of Structural Connectomes

Sep. 6, 2023—Nancy R. Newlin, Francois Rheault, Kurt G. Schilling, Bennett A. Landman. “Characterizing Streamline Count Invariant Graph Measures of Structural Connectomes” Journal of Magnetic Resonance Imaging. January 2023. Full Text Background While graph measures are used increasingly to characterize human connectomes, uncertainty remains in how to use these metrics in a quantitative and reproducible manner. Specifically, there is...

Body Composition Assessment with Limited Field-of-view Computed Tomography: A Semantic Image Extension Perspective. Medical Image Analysis

Aug. 31, 2023—Kaiwen Xu, Thomas Li, Mirza S. Khan, Riqiang Gao, Sanja L. Antic, Yuankai Huo, Kim L. Sandler, Fabien Maldonado, Bennett A. Landman Paper: https://www.sciencedirect.com/science/article/pii/S1361841523001123 Code: https://github.com/MASILab/S-EFOV Abstract Field-of-view (FOV) tissue truncation beyond the lungs is common in routine lung screening computed tomography (CT). This poses limitations for opportunistic CT-based body composition (BC) assessment as key anatomical structures...

Contrastive semi-supervised harmonization of single-shell to multi-shell diffusion MRI

Jul. 25, 2022—Colin B. Hansen, Kurt G. Schilling, Francois Rheault, Susan Resnick, Andrea T. Shafer, Lori L. Beason-Held, Bennett A. Landmƒan. “Contrastive semi-supervised harmonization of single-shell to multi-shell diffusion MRI.” Magnetic Resonance Imaging (2022). Full Text Abstract Diffusion weighted MRI (DW-MRI) harmonization is necessary for multi-site or multi-acquisition studies. Current statistical methods address the need to harmonize...

Multimodal neuroimaging in pediatric type 1 diabetes: a pilot multisite feasibility study of acquisition quality, motion, and variability

Dec. 10, 2021—Leon Y. Cai, Costin Tanase, Adam W. Anderson, Karthik Ramadass, Francois Rheault, Chelsea A. Lee, Niral J. Patel, Sky Jones, Lauren M. LeStourgeon, Alix Mahon, Sumit Pruthi, Kriti Gwal, Arzu Ozturk, Hakmook Kang, Nicole Glaser, Simona Ghetti, Sarah S. Jaser, Lori C. Jordan, and Bennett A. Landman Abstract Type 1 diabetes (T1D) affects over 200,000...

MASiVar: Multisite, Multiscanner, and Multisubject Acquisitions for Studying Variability in Diffusion Weighted Magnetic Resonance Imaging

Aug. 30, 2021—Leon Y. Cai, Qi Yang, Praitayini Kanakaraj, Vishwesh Nath, Allen T. Newton, Heidi A. Edmonson, Jeffrey Luci, Benjamin N. Conrad, Gavin R. Price, Colin B. Hansen, Cailey I. Kerley, Karthik Ramadass, Fang-Cheng Yeh, Hakmook Kang, Eleftherios Garyfallidis, Maxime Descoteaux, Francois Rheault, Kurt G. Schilling, and Bennett A. Landman. MASiVar: Multisite, Multiscanner, and Multisubject Acquisitions for...

Experimental workflow and generation of Pandora atlases. Data from three repositories (HCP, BLSA, and VU) were curated. Subject-level
processing includes tractography and registration to MNI space. Volumetric atlases for each set of bundle definitions is created by population-averaging
in standard space. Point clouds are displayed which allow qualitative visualization of probability densities of a number of fiber pathways. Finally, surface
atlases are created by assigning indices to the vertices of the MNI template white matter/gray matter boundary.

Pandora: 4-D White Matter Bundle Population-Based Atlases Derived from Diffusion MRI Fiber Tractography

Nov. 29, 2020—Colin B. Hansen, Qi Yang, Ilwoo Lyu, Francois Rheault, Cailey Kerley, Bramsh Qamar Chandio, Shreyas Fadnavis, Owen Williams, Andrea T. Shafer, Susan M. Resnick, David H. Zald, Laurie E. Cutting, Warren D. Taylor, Brian Boyd, Eleftherios Garyfallidis, Adam W. Anderson, Maxime Descoteaux, Bennett A. Landman, Kurt G. Schilling. Pandora: 4-D White Matter Bundle Population-Based Atlases Derived from Diffusion MRI Fiber Tractography. Neuroinform (2020). Full Text Abstract Brain atlases have proven to be valuable neuroscience tools for...

Figure 6. The absolute percent error (APE) in MD is shown for the human subject with one session acquired at isocenter on scanner A and another acquired 6cm superior from isocenter on scanner B. The top plot shows the sagittal and coronal view of the b0 from each session to demonstrate the shift within the scanner. The bottom plots show the APE for nine saggital slices before correction, after correction using the estimated fields, and after correction using the manufacturer specifications. The error before correction is most prominent in the superior regions of the phantom as those were the furthest from isocenter during the second acquisition.

Empirical field mapping for gradient nonlinearity correction of multi-site diffusion weighted MRI

Nov. 25, 2020—Colin B. Hansen, Baxter P. Rogers, Kurt G. Schilling, Vishwesh Nath, Justin A. Blaber, Okan Irfanoglu, Alan Barnett, Carlo Pierpaoli, Adam W. Anderson, Bennett A. Landman. “Empirical field mapping for gradient nonlinearity correction of multi-site diffusion weighted MRI.” Magnetic Resonance Imaging 2020. Full Text Abstract Background: Achieving inter-site / inter-scanner reproducibility of diffusion weighted magnetic resonance...

« Previous Page