In Journal of molecular biology ; h5-index 65.0
Micrograph comparison remains useful in bioscience. This technology provides researchers with a quick snapshot of experimental conditions. But sometimes a two- condition comparison relies on researchers'eyes to draw conclusions. Our Bioimage Analysis, Statistic, and Comparison (BASIN) software provides anobjective and reproducible comparison leveraging inferential statistics to bridge image data with other modalities. Users have access to machine learning-based object segmentation. BASIN provides severaldata points such as images' object counts, intensities, andareas. Hypothesis testing may also be performed. To improve BASIN's accessibility,we implemented it using R Shiny and provided both an online and offlineversion. We used BASIN to process 498 image pairs involving five bioscience topics. Our framework supported either direct claims or extrapolations 57% of the time. Analysis results were manually curated to determine BASIN's accuracy which was shown to be 78%. Additionally, each BASIN version's initial release shows an average 82% FAIR compliance score.
Hartman Timothy W, Radichev Evgeni, Munsub Ali Hafiz, Olakunle Alaba Mathew, Hoffman Mariah, Kassa Gideon, Sani Rajesh, Gadhamshetty Venkata, Ragi Shankarachary, Messerli Shanta M, de la Puente Pilar, Sandhurst Eric S, Do Tuyen, Lushbough Carol, Gnimpieba Etienne Z
2022-Dec-01
image comparison, machine learning, microscope imaging, segmentation, statistical analysis
