Image data is growing at a rapid rate, whether from the continuous uploads on video portals, photo-sharing platforms, new satellites, or even medical data. The volumes have grown from tens of gigabytes to exabytes per year in less than a decade. Deeply embedded inside these datasets is detailed information on fashion trends, natural disasters, agricultural output, or looming health risks. The large majority of statistical analysis and data science is performed on numbers either as individuals or sequences. Images, however, do not neatly fit into the standard paradigms and have resulted in “graveyards” of large stagnant image storage systems completely independent of the other standard information collected. In this chapter, we will introduce the basic concepts of quantitative image analysis and show how such work can be used in the biomedical context to link hereditary information (genomic sequences) to the health or quality of bone. Since inheritance studies are much easier to perform if you are able to control breeding, the studies are performed in mice where in-breeding and cross-breeding are possible. Additionally, mice and humans share a large number of genetic and biomechanical similarities, so many of the results are transferable (Ackert-Bicknell et al. Mouse BMD quantitative trait loci show improved concordance with human genome-wide association loci when recalculated on a new, common mouse genetic map. Journal of Bone and Mineral Research 25(8):1808-1820, 2010).
CITATION STYLE
Mader, K. (2019). Image Analysis at Scale for Finding the Links Between Structure and Biology. In Applied Data Science: Lessons Learned for the Data-Driven Business (pp. 425–443). Springer International Publishing. https://doi.org/10.1007/978-3-030-11821-1_23
Mendeley helps you to discover research relevant for your work.