Medical-image Analysis and Statistical Interpretation (MASI) Lab

Figure 4. The response function varies across brain regions. Three locations in the same monkey brain (monkey #2) are shown, along with the histological fiber orientation distribution, signal, and derived response function for all 9 voxels. In addition, the average response function for each z-stack is shown in two views.

Histologically derived fiber response functions for diffusion MRI vary across white matter fibers – an ex vivo validation study in the squirrel monkey brain

Aug. 25, 2020—Kurt G Schilling, Yurui Gao, Iwona Stepniewska, Vaibhav Janve, Bennett A. Landman, Adam W. Anderson. “Histologically derived fiber response functions for diffusion MRI vary across white matter fibers – an ex vivo validation study in the squirrel monkey brain”. NMR in Biomedicine. 2019 Jun;32(6):e4090. doi: 10.1002/nbm.4090. Epub 2019 Mar 25. Full text: https://pubmed.ncbi.nlm.nih.gov/30908803/ Abstract Understanding the...

Fig 8. External dataset validation.
External validation of corrected b0’s after applying the synthesized b0 distortion correction pipeline with data from open-sourced studies. The distorted (“D”) and undistorted (“U”) b0 images are shown alongside T1 images. In all cases, effective distortion correction is visually apparent (distortions indicated by arrows).

Distortion correction of diffusion weighted MRI without reverse phase-encoding scans or field-maps

Aug. 25, 2020—Kurt G Schilling*, Justin Blaber*, Colin Hansen, Leon Cai, Baxter Rogers, Adam W Anderson, Seth A Smith, Praitayini Kanakaraj, Tonia Rex, Susan M. Resnick, Andrea T. Shafer, Laurie Cutting, Neil Woodward, David Zald, Bennett A Landman.“ Distortion correction of diffusion weighted MRI without reverse phase-encoding scans or field-maps ”. PLoS ONE 15(7): e0236418. https://doi.org/10.1371/journal.pone.0236418 Full text: https:...

Automatic Labeling of Cortical Sulci using Convolutional Neural Networks in a Developmental Cohort

Apr. 20, 2020—Lingyan Hao, Shunxing Bao, Yucheng Tang, Riqiang Gao, Prasanna Parvathaneni, Jacob Miller, Willa Voorhies, Jewelia Yao, Silvia Bunge, Kevin Weiner, Bennett Landman, Ilwoo Lyu. “Automatic Labeling of Cortical Sulci using Convolutional Neural Networks in a Developmental Cohort”. IEEE International Symposium on Biomedical Imaging (ISBI) 2020, IEEE, 412-415, Iowa City, Iowa, USA, 2020. [Full text][Code] Abstract...

Validation and Optimization of Multi-Organ Segmentation on Clinical Imaging Archives

Feb. 12, 2020—Olivia Tang, Yuchen Xu, Yucheng Tang, Ho Hin Lee, Yunqiang Chen, Dashan Gao, Shizhong Han, Riqiang Gao, Michael R. Savona, Richard G. Abramson, Yuankai Huo, Bennett A. Landman, “Validation and Optimization of Multi-Organ Segmentation on Clinical Imaging Archives”, SPIE IP:MI 2020. Houston, TX. https://arxiv.org/abs/2002.04102 Abstract Segmentation of abdominal computed tomography (CT) provides spatial context, morphological...

Examples of segmentations generated by the baseline algorithm. A. An inlier, where the algorithm correctly predicted larger organs, like the liver (on the left side of image in purple) and spleen (on the right side of image in red- pink) and suggested mostly accurate areas of smaller organs. B. An outlier (global failure), where the liver (purple) and spleen (red-pink) were largely correct but major inconsistencies are visible with other organs.

Outlier Guided Optimization of Abdominal Segmentation

Feb. 12, 2020—Yuchen Xu*, Olivia Tang*, Yucheng Tang, Ho Hin Lee, Yunqiang Chen, Dashan Gao, Shizhong Han, Riqiang Gao, Michael R. Savona, Richard G. Abramson, Yuankai Huo, Bennett A. Landman, “Outlier Guided Optimization of Abdomen Segmentation”, SPIE IP:MI 2020. Houston, TX https://arxiv.org/abs/2002.04098 Abstract Abdominal multi-organ segmentation of computed tomography (CT) images has been the subject of extensive...

Different classes of methods have been used to infer tissue microstructure from single shell and multi shell DW-MRI data. The gap addressed herein is in data-driven machine learning models for multi-shell DW-MRI data.

Enabling Multi-shell b-Value Generalizability of Data-Driven Diffusion Models with Deep SHORE

Jan. 17, 2020—Nath V, Lyu I, Schilling KG, Parvathaneni P, Hansen CB, Huo Y, Janve VA, Gao Y, Stepniewska I, Anderson AW, Landman BA. Enabling Multi-shell b-Value Generalizability of Data-Driven Diffusion Models with Deep SHORE. In International Conference on Medical Image Computing and Computer-Assisted Intervention 2019 Oct 13 (pp. 573-581). Springer, Cham. Full text: https://arxiv.org/ftp/arxiv/papers/1907/1907.06319.pdf Abstract Intra-voxel...

The base regression neural network is depicted in the center which describes the parameters of the fullyconnected dense layers with respective activation functions. The plot at left: Depicts three inputs where the center input
comes from corresponding DW-MRI with histology. The other two are pairwise inputs from corresponding voxels of
scanner 1.5T and 3T. The plot at right: Depicts the loss function which uses the hypothesis that the outcome/prediction
should be same irrespective of the scanner gradient strength.

Harmonizing 1.5 T/3T diffusion weighted MRI through development of deep learning stabilized microarchitecture estimators

Jan. 17, 2020—Nath V, Remedios S, Parvathaneni P, Hansen CB, Bayrak RG, Bermudez C, Blaber JA, Schilling KG, Janve VA, Gao Y, Huo Y. Harmonizing 1.5 T/3T diffusion weighted MRI through development of deep learning stabilized microarchitecture estimators. In Medical Imaging 2019: Image Processing 2019 Mar 15 (Vol. 10949, p. 109490O). International Society for Optics and Photonics....

Violin plots of intrasession submissions across both the scanners per tract. (A) Dice similarity coefficients, (B) intraclass correlation coefficients. The top row depicts the median of the top five intrasession submissions. The tracts are in the following order (L/R): a) Uncinate, b) Fornix, c) Fminor & Fmajor, d) Cingulum, e) Corticospinal tract, f) Inferior longitudinal fasciculus, g) Superior longitudinal fasciculus, h) Inferior fronto‐occipital tract.

Tractography reproducibility challenge with empirical data (TRAceD): The 2017 ISMRM diffusion study group challenge

Jan. 17, 2020—Nath V, Schilling KG, Parvathaneni P, Huo Y, Blaber JA, Hainline AE, Barakovic M, Romascano D, Rafael‐Patino J, Frigo M, Girard G. Tractography reproducibility challenge with empirical data (traced): The 2017 ISMRM diffusion study group challenge. Journal of Magnetic Resonance Imaging. 2020 Jan;51(1):234-49. Full text: https://www.ncbi.nlm.nih.gov/pubmed/31179595 Abstract BACKGROUND: Fiber tracking with diffusion-weighted MRI has become an...

A) Middle axial slice of a human brain acquired using DW-MRI. B, C) CSD FOD's of the same subject on two different scanners showing inconsistency which cannot be validated without ground truth. D) Coronal slice of a Squirrel Monkey. E, F, G, H) Right: CSD FOD's at b-value of 3000 s/mm2 Left: Ground truth reconstruction using aggregated histological structural tensors depicting a loss in precision.

Deep learning reveals untapped information for local white-matter fiber reconstruction in diffusion-weighted MRI

Jan. 17, 2020—Nath V, Schilling KG, Parvathaneni P, Hansen CB, Hainline AE, Huo Y, Blaber JA, Lyu I, Janve V, Gao Y, Stepniewska I, Anderson AW, Landman BA. Deep learning reveals untapped information for local white-matter fiber reconstruction in diffusion-weighted MRI. Magnetic resonance imaging. 2019 Oct 1;62:220-7. Abstract PURPOSE: Diffusion-weighted magnetic resonance imaging (DW-MRI) is of critical importance...

Figure 2

Illustration of multiple instance learning with gradient accumulation. The first CT volume is organized into a bag of its 2D slices. Then, the model performs inference on all slices in the bag, and class probabilities are calculated. The gradient is calculated only for the instance corresponding to the most probable positive class. This gradient is saved and the gradient calculation is repeated for the next bag until the batch is done, and the accumulated gradient is averaged for the batch size and applied to the model.

Extracting 2D weak labels from volume labels using multiple instance learning in CT hemorrhage detection

Jan. 2, 2020—Remedios, S. W., Wu, Z., Bermudez, C., Kerley, C. I., Roy, S., Patel, M. B., Butman, J. A., Landman, B. A., Pham, D. L. (2019). Extracting 2D weak labels from volume labels using multiple instance learning in CT hemorrhage detection. arXiv preprint arXiv:1911.05650. Full Text: Arxiv Link Abstract Multiple instance learning (MIL) is a supervised learning methodology...

« Previous Page