Medical-image Analysis and Statistical Interpretation (MASI) Lab

Representative segmentations for two subjects. Labels: red: volumetric hernia, yellow: outer abdominal wall (axial), blue: inner abdominal wall (axial), green: outer abdominal wall (sagittal), pink: inner abdominal wall (sagittal), cyan: skin

Quantitative Anatomical Labeling of the Anterior Abdominal Wall

Feb. 1, 2013—Wade M. Allen, Zhoubing Xu, Andrew J. Asman, Benjamin K. Poulose, Bennett A. Landman. “Quantitative Anatomical Labeling of the Anterior Abdominal Wall.” In Proceedings of the SPIE Medical Imaging Conference. Orlando, Florida, February 2013. Oral Presentation. † Full text: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3903294/?report=classic Abstract Ventral hernias (VHs) are abnormal openings in the anterior abdominal wall that are common...

Flowchart demonstrating the PACS-based Diffusion Tensor Imaging quality analysis framework. The framework begins by utilizing a PACS-based framework for acquiring a recently scanned target. Once the DTI image is acquired, standard pre-processing steps are performed for accounting for patient movement via an intra-subject rigid registration. Next, a whole image FA map and the multi-atlas segmentation process (using the pre-computed B0 atlases) are performed simultaneously in order to achieve the pertinent information about the current subject. Finally, structure-wise FA noise estimates are constructed using a wild-bootstrap estimation procedure.

Robust Inter-Modality Multi-Atlas Segmentation for PACS-based DTI Quality Control

Feb. 1, 2013—Andrew J. Asman, Carolyn B. Lauzon, Bennett A. Landman. “Robust Inter-Modality Multi-Atlas Segmentation for PACS-based DTI Quality Control.” In Proceedings of the SPIE Medical Imaging Conference. Orlando, Florida, February 2013. Oral Presentation. † Full text: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3874255/ Abstract Anatomical contexts (spatial labels) are critical for interpretation of medical imaging content. Numerous approaches have been devised for...

Segmentation results for four subjects. The first column represents the results of bone skeleton and skin. The second column demonstrates the segmentation of outer abdominal wall (green) overlaid with grids of labeled ground truth (red). The third to the sixth columns show the intra- and inter- variability of abdominal wall over slices and the segmentation results of our approach (red).

Automatic Segmentation of Abdominal Wall in Ventral Hernia CT: A Pilot Study

Feb. 1, 2013—Zhoubing Xu, Wade M. Allen, Benjamin K. Poulose, Bennett A. Landman. “Automatic Segmentation of Abdominal Wall in Ventral Hernia CT: A Pilot Study.” In Proceedings of the SPIE Medical Imaging Conference. Orlando, Florida, February 2013† Full text: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3877250/?report=classic Abstract The treatment of ventral hernias (VH) has been a challenging problem for medical care. Repair of...

Flowchart demonstrating the proposed registration procedure. As the volumes used in this dataset are wildly varying in terms of field-of-view and voxel resolution, a robust registration procedure is needed. Our model begins by rigidly registering the bone structure of the target and the atlas images (achieved through thresholding). Using these rigid registrations the optic nerve centroids are estimated on the target image in order to estimate an appropriate region-of-interest. Using this consistent region-of-interest, consistent non-rigid registration can then be performed in order to achieve the highest possible correspondence between the targets and the atlases.

Robust Non-Local Multi-Atlas Segmentation of the Optic Nerve

Feb. 1, 2013—A. Asman, Michael P. DeLisi, Louise A. Mawn, Robert L. Galloway, and B. Landman. “Robust Non-Local Multi-Atlas Segmentation of the Optic Nerve.” In Proceedings of the SPIE Medical Imaging Conference. Orlando, Florida, February 2013. Oral Presentation. † PMCID 24478826 Full text: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3903299/?report=classic Abstract Labeling or segmentation of structures of interest on medical images plays an...

System for Integrated Neuroimaging Analysis and Processing of Structure.

Jan. 11, 2013—Bennett A. Landman, John A. Bogovic, Aaron Carass, Min Chen, Snehashis Roy, Navid Shiee, Zhen Yang, Bhaskar Kishore, Dzung Pham, Pierre-Louis Bazin, Susan M. Resnick, and Jerry L. Prince. “System for Integrated Neuroimaging Analysis and Processing of Structure.” Neuroinformatics. 2013 Jan;11(1):91-10 PMC22932976 † Full Text: https://www.ncbi.nlm.nih.gov/pubmed/22932976 Abstract: Mapping brain structure in relation to neurological development,...

Example qualitative results. Three representative slices from three different brains are presented for comparison. For each example, the target, truth labels, an example atlas, the label fusion estimate and the cancer likelihood estimate are presented. Note the high quality likelihood estimate in the first two examples. On the third example, the cancer is detected, but it is not as well localized as in the first two examples.

Out-of-Atlas Labeling: A Multi-Atlas Approach to Cancer Segmentation

Dec. 31, 2012—Andrew J. Asman and Bennett A. Landman, “Out-of-Atlas Labeling: A Multi-Atlas Approach to Cancer Segmentation”, In Proceedings of the 2012 International Symposium on Biomedical Imaging (ISBI). Barcelona, Spain† Full Text: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3892947/ Abstract Conventional automated segmentation techniques for magnetic resonance imaging (MRI) fail to perform in a robust and consistent manner when brain anatomy differs...

Segmentation of Malignant Gliomas through Remote Collaboration and Statistical Fusion.

Oct. 31, 2012—Zhoubing Xu, Andrew J. Asman, Eesha Singh, Lola Chambless, Reid Thompson, Bennett A. Landman. “Segmentation of Malignant Gliomas through Remote Collaboration and Statistical Fusion.” Medical Physics. 2012 Oct;39(10):5981-9 PMC3461053 † Full Text: https://www.ncbi.nlm.nih.gov/pubmed/?term=Segmentation+of+Malignant+Gliomas+through+Remote+Collaboration+and+Statistical+Fusion. Abstract: PURPOSE: Malignant gliomas represent an aggressive class of central nervous system neoplasms. Correlation of interventional outcomes with tumor morphometry data necessitates 3D...

Resilience features capture the stability of an inference method to data decimation. An rs-fMRI dataset (1) is temporally decimated into subsets; each inference method (2) is applied independently to each subset; voxel-wise statistics (3) are estimated; and the parameter maps (4) capture spatial dependencies.

Quantitative Evaluation of Statistical Inference in Resting State Functional MRI

Sep. 30, 2012—Xue Yang and Bennett A. Landman. “Quantitative Evaluation of Statistical Inference in Resting State Functional MRI”, In International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Nice, France, September 2012 (32% acceptance rate) Full text: https://www.ncbi.nlm.nih.gov/pubmed/23286055 Abstract Modern statistical inference techniques may be able to improve the sensitivity and specificity of resting state functional...

Biological Parametric Mapping Accounting for Random Regressors with Regression Calibration and Model II Regression

Sep. 1, 2012—Xue Yang, Carolyn B. Lauzon, Ciprian Crainiceanu, Brian Caffo, Susan M. Resnick, Bennett A. Landman. “Biological Parametric Mapping Accounting for Random Regressors with Regression Calibration and Model II Regression.” NeuroImage. 2012 Sep;62(3):1761-8. PMC22609453 Full text: https://www.ncbi.nlm.nih.gov/pubmed/22609453 Abstract Massively univariate regression and inference in the form of statistical parametric mapping have transformed the way in which multi-dimensional...

Next Generation of the JAVA Image Science Toolkit (JIST) Visualization and Validation

Aug. 1, 2012—Bo Li, Frederick Bryan, Bennett A. Landman, “Next Generation of the JAVA Image Science Toolkit (JIST) Visualization and Validation.” Insight Journal. August 2012. P 874 PMC4181667 Full text: https://www.ncbi.nlm.nih.gov/pubmed/25285310 Abstract Modern medical imaging analyses often involve the concatenation of multiple steps, and neuroimaging analysis is no exception. The Java Image Science Toolkit (JIST) has provided a...

« Previous Page