‘label’

Qualitative fusion results. A representative slice shows the effect of the additional confidence parameter on the output of both the voting and statistical fusion techniques. The three rater observations (one submitted empty) are shown. In this example, CWV and “Best Pick” would result in an identical segmentation.

Self-Assessed Performance Improves Statistical Fusion of Image Labels.

Feb. 15, 2014—Frederick W. Bryan, Zhoubing Xu, Andrew J. Asman, Wade M. Allen, Daniel S. Reich, and Bennett A. Landman. “Self-Assessed Performance Improves Statistical Fusion of Image Labels.” Medical Physics. 2014 Mar;41(3):031903. PMC24593721† Full Text: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3978333/ Abstract Purpose: Expert manual labeling is the gold standard for image segmentation, but this process is difficult, time-consuming, and prone...

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...

Comparison of existing and proposed labeling approaches. In a traditional context, either an expert rater with extensive anatomical knowledge evaluates each dataset (A) or a small set of well-training domain experts who have been instructed by an anatomical expert (B) label each image. Intra- and inter-rater reproducibility analyses are typically performed a per-protocol basis rather than on all datasets. In the proposed WebMILL approach (C), a computer system divides the set of images to be labeled into simple puzzles consisting of a piece of a larger volume and distributes these challenges to a distributed collection of minimally training individuals. Each piece is labeled multiple times by multiple raters. A statistical fusion process simultaneously estimates the true label for each pixel and performance characteristics of each rater.

Foibles, Follies, and Fusion: Web-Based Collaboration for Medical Image Labeling

Jan. 31, 2012—Bennett A Landman, Andrew J Asman, Andrew G Scoggins, John A Bogovic, Joshua A Stein; Jerry L Prince, “Foibles, Follies, and Fusion: Web-Based Collaboration for Medical Image Labeling”, NeuroImage. 2012 Jan 2;59(1):530-9. PMC3195954 † Full text: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3195954/ Abstract Labels that identify specific anatomical and functional structures within medical images are essential to the characterization of...