February, 2012

Empirical experiment using axial cross-section of cerebellar data to assess the performance of STAPLE (on a slice-by-slice basis) and STAPLER (volumetric fusion). The representative slices shown in (A) – (C) present an example truth model, and observations by minimally trained undergraduate students, respectively. The slices seen in (D) and (E) are the estimated labels by STAPLE and STAPLER, respectively. The plot on the top of (F) shows the accuracy on a per slice basis of the observations (box plots) STAPLER (green), STAPLE (blue), and majority vote (red). The histogram on the bottom of (F) shows the number of observations per slice. Lastly, the plot seen in (G) shows the difference in DSC between STAPLER, STAPLE, and majority vote on a per label basis. The legend for these label numbers can be seen at the bottom of (G).

Robust Statistical Fusion of Image Labels

Feb. 1, 2012—Bennett A. Landman, Andrew J. Asman, Drew Scoggins, John A. Bogovic, Fangxu Xing, and Jerry L. Prince. “Robust Statistical Fusion of Image Labels”, IEEE Transactions on Medical Imaging. 2012 Feb;31(2):512-22. PMC3262958 Full text: https://www.ncbi.nlm.nih.gov/pubmed/22010145 Abstract Image labeling and parcellation (i.e., assigning structure to a collection of voxels) are critical tasks for the assessment of volumetric...

Comparison of DTI and HARDI direction estimates. Mean unweighted scans (A, E) and DTI colormap images (B, F) are shown for two representative slices. Enlargements show estimated diffusion tensors (C, G) alongside CFARI directions (D, H) based on two repetitions of 30 directions at a b-value of 700 s/mm2

Resolution of Crossing Fibers with Constrained Compressed Sensing using Diffusion Tensor MRI

Feb. 1, 2012—Bennett A. Landman, John A Bogovic; Hanlin Wan; Fatma El Zahraa ElShahaby; Pierre-Louis Bazin, and Jerry L Prince. “Resolution of Crossing Fibers with Constrained Compressed Sensing using Diffusion Tensor MRI”, NeuroImage. 2012 Feb 1;59(3):2175-86. PMC22019877 Full text: https://www.ncbi.nlm.nih.gov/pubmed/22019877 Abstract Diffusion tensor imaging (DTI) is widely used to characterize tissue micro-architecture and brain connectivity. In regions...

Finding Seeds for Segmentation Using Statistical Fusion

Feb. 1, 2012—Fangxu Xing, Andrew J. Asman, Jerry L. Prince, Bennett A. Landman. “Finding Seeds for Segmentation Using Statistical Fusion.” In Proceedings of the SPIE Medical Imaging Conference. San Diego, California, February 2012 Full text: https://www.ncbi.nlm.nih.gov/pubmed/23019385 Abstract Image labeling is an essential step for quantitative analysis of medical images. Many image labeling algorithms require seed identification in order...

Towards Automatic Quantitative Quality Control for MRI

Feb. 1, 2012—C. Lauzon, B. Caffo, and B. Landman. “Towards Automatic Quantitative Quality Control for MRI.” In Proceedings of the SPIE Medical Imaging Conference. San Diego, California, February 2012 (Oral Presentation) Full text: https://www.ncbi.nlm.nih.gov/pubmed/23087586 Abstract Quality and consistency of clinical and research data collected from Magnetic Resonance Imaging (MRI) scanners may become suspect due to a wide variety...

Automating PACS Quality Control with the Vanderbilt Image Processing Enterprise Resource

Feb. 1, 2012—M. L. Esparza, E. B. Welch and B. A. Landman. “Automating PACS Quality Control with the Vanderbilt Image Processing Enterprise Resource.” In Proceedings of the SPIE Medical Imaging Conference. San Diego, California, February 2012 (Oral Presentation) Full text: https://www.ncbi.nlm.nih.gov/pubmed/24357910 Abstract Precise image acquisition is an integral part of modern patient care and medical imaging research. Periodic...

Figure 2
Illustration of minimally rater performance relative to an experienced rater for T1 data (A) and T2 data (B). The top row shows 200 slices which have been expertly labeled sorted by the median overlap with minimally trained raters. The center row shows the number of times each slice has been labeled. The final row illustrates an arbitrary example from the lowest, median, and highest accuracy slices.

Collaborative Labeling of Malignant Glioma with WebMILL: A First Look

Feb. 1, 2012—E. Singh, Z. Xu, A. Asman, L. Chambless, R. Thompson and B. Landman. “Collaborative Labeling of Malignant Glioma with WebMILL: A First Look.” In Proceedings of the SPIE Medical Imaging Conference. San Diego, California, February 2012 † Full Text: https://www.ncbi.nlm.nih.gov/pubmed/?term=Collaborative+Labeling+of+Malignant+Glioma+with+WebMILL%3A+A+First+Look Abstract Malignant gliomas are the most common form of primary neoplasm in the central nervous...

Figure 3
Kurtosis of weighted residuals. The Kurtosis maps of the residuals from the weighted data are shown in the first column. The middle and the right column display one voxel residuals across the first 100 scans inside the cerebrospinal fluid region and the white matter region respectively.

A Comparison of Distributional Considerations with Statistical Analysis of Resting State fMRI at 3T and 7T

Feb. 1, 2012—Xue Yang, Martha J. Holmes, Allen T. Newton, Victoria L. Morgan, Bennett A. Landman. “A Comparison of Distributional Considerations with Statistical Analysis of Resting State fMRI at 3T and 7T.” In Proceedings of the SPIE Medical Imaging Conference. San Diego, California, February 2012 (Oral Presentation) NIHMS341654† Full Text: https://www.ncbi.nlm.nih.gov/pubmed/?term=A+Comparison+of+Distributional+Considerations+with+Statistical+Analysis+of+Resting+State+fMRI+at+3T+and+7T Abstract Ultra-high field 7T magnetic resonance...

A Surgeon Specific Automatic Path Planning Algorithm for Deep Brain Stimulation

Feb. 1, 2012—Yuan Liu, Benoit M. Dawant, Srivatsan Pallavaram, Joseph S. Neimat, Pierre-François D’Haese, Ryan D. Datteri, Bennett A. Landman and Jack H. Noble. “A Surgeon Specific Automatic Path Planning Algorithm for Deep Brain Stimulation.” In Proceedings of the SPIE Medical Imaging Conference. San Diego, California, February 2012 (Oral Presentation) † Full Text: http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1285627 Abstract In deep brain...

Figure 2
Results from the controlled rater observation simulation. The target intensity image and the corresponding true labels can be seen (A) and (B), respectively. The set of input observations used in this experiment can be seen in (C). The results of the four algorithms, Majority Vote, STAPLE, Binary-COLLATE and Multi-COLLATE can be seen in (D)–(G). Note that the 3 consensus-level implementation of Multi-COLLATE is the only algorithm that gets the correct answer. The 3 energy in each of the consensus levels can be seen in (H)–(J). Note that by distributing the non-consensus voxels into two separate levels, (H) and (I), the estimation process converges to the correct answer.

Generalized Statistical Label Fusion using Multiple Consensus Levels

Feb. 1, 2012—Z. Xu, A. Asman and B. Landman. “Generalized Statistical Label Fusion using Multiple Consensus Levels.” In Proceedings of the SPIE Medical Imaging Conference. San Diego, California, February 2012 (Oral Presentation) PMC3438516† Full Text: https://www.ncbi.nlm.nih.gov/pubmed/?term=%E2%80%9CGeneralized+Statistical+Label+Fusion+using+Multiple+Consensus+Levels. Abstract Segmentation plays a critical role in exposing connections between biological structure and function. The process of label fusion collects and...

Simultaneous Segmentation and Statistical Label Fusion.

Feb. 1, 2012—A. Asman and B. Landman. “Simultaneous Segmentation and Statistical Label Fusion.” In Proceedings of the SPIE Medical Imaging Conference. San Diego, California, February 2012 (Oral Presentation) † Full Text: https://www.ncbi.nlm.nih.gov/pubmed/24357909 Abstract Labeling or segmentation of structures of interest in medical imaging plays an essential role in both clinical and scientific understanding. Two of the common...