In conjunction with the ISBI 2015 conference, we organized a longitudinal lesion segmentation challenge providing training and test data to registered participants. The training data consisted of five subjects with a mean of 4.4 time-points, and test data of fourteen subjects with a mean of 4.4 time-points. All 82 data sets had the white matter lesions associated with multiple sclerosis delineated by two human expert raters. Eleven teams submitted results using state-of-the-art lesion segmentation algorithms to the challenge, with ten teams presenting their results at the conference. We present a quantitative evaluation comparing the consistency of the two raters as well as exploring the performance of the eleven submitted results in addition to three other lesion segmentation algorithms. The challenge presented three unique opportunities: 1) the sharing of a rich data set; 2) collaboration and comparison of the various avenues of research being pursued in the community; and 3) a review and refinement of the evaluation metrics currently in use. We report on the performance of the challenge participants, as well as the construction and evaluation of a consensus delineation. The image data and manual delineations will continue to be available for download, through an evaluation website 1 as a resource for future researchers in the area. This data resource provides a platform to compare existing methods in a fair and consistent manner to each other and multiple manual raters.

No abstract

The Sørensen-Dice index (SDI) is a widely used measure for evaluating medical image segmentation algorithms. It offers a standardized measure of segmentation accuracy which has proven useful. However, it offers diminishing insight when the number of objects is unknown, such as in white matter lesion segmentation of multiple sclerosis (MS) patients. We present a refinement for finer grained parsing of SDI results in situations where the number of objects is unknown. We explore these ideas with two case studies showing what can be learned from our two presented studies. Our first study explores an inter-rater comparison, showing that smaller lesions cannot be reliably identified. In our second case study, we demonstrate fusing multiple MS lesion segmentation algorithms based on the insights into the algorithms provided by our analysis to generate a segmentation that exhibits improved performance. This work demonstrates the wealth of information that can be learned from refined analysis of medical image segmentations. Segmentation is one of the cornerstones of image processing; it is the process of automatic or semi-automatic detection of boundaries within an image. In a medical imaging context, segmentation is concerned with differentiating tissue classes (i.e., white matter vs. gray matter in the brain), identifying anatomy, or pathology. Motivating examples for the use of segmentation in medical imaging include content based image retrieval 1 , tumor delineation 2 , cell detection 3 and motion tracking 4 , object measurement for size 5 , shape analysis 6 evaluation, and myriad other uses 7-47. The review articles by Pham et al. 48 and Sharma et al. 49 are a useful resource, providing an overview of the different applications of segmentation in medical imaging. A common feature of all this literature is the evaluation of the proposed segmentation algorithm either in comparison to previous work, or more importantly, to some manual/digital gold-standard. In fact, it is impossible to report new segmentation methods without such evaluation; it therefore follows that evaluating medical image segmentation algorithms is important. There have been many methods employed in the evaluation of medical image segmentation algorithms. Voxel-based methods such as intra-class correlation coefficient (ICC) 50,51 , Sørensen-Dice Index 52,53 , and Jaccard coefficient 54 can provide insight about the agreement between a ground truth segmentation and an algorithm

The modern synthetic view of human evolution proposes that the fixation of novel mutations is driven by the balance among selective advantage, selective disadvantage, and genetic drift. When considering the global architecture of the human genome, the same model can be applied to understanding the rapid acquisition and proliferation of exogenous DNA. To explore the evolutionary forces that might have morphed human genome architecture, we investigated the origin, composition, and functional potential of numts (nuclear mitochondrial pseudogenes), partial copies of the mitochondrial genome found abundantly in chromosomal DNA. Our data indicate that these elements are unlikely to be advantageous, since they possess no gross positional, transcriptional, or translational features that might indicate beneficial functionality subsequent to integration. Using sequence analysis and fossil dating, we also show a probable burst of integration of numts in the primate lineage that centers on the prosimian–anthropoid split, mimics closely the temporal distribution of Alu and processed pseudogene acquisition, and coincides with the major climatic change at the Paleocene–Eocene boundary. We therefore propose a model according to which the gross architecture and repeat distribution of the human genome can be largely accounted for by a population bottleneck early in the anthropoid lineage and subsequent effectively neutral fixation of repetitive DNA, rather than positive selection or unusual insertion pressures.