Abstract Summary: Modern scientific investigation is generating increasingly larger datasets, yet analyzing these data with current tools is challenging. DIVE is a software framework intended to facilitate big data analysis and reduce the time to scientific insight. Here, we present features of the framework and demonstrate DIVE’s application to the Dynameomics project, looking specifically at two proteins. Availability and implementation: Binaries and documentation are available at http://www.dynameomics.org/DIVE/DIVESetup.exe. Contact: [email protected] Supplementary information: Supplementary data are available at Bioinformatics online.

This paper proposes a novel approach to improve the segmentation quality of a 3D random walks algorithm using classifiability criteria. We produce a range of potential threshold values by extending the decision function of a random walks algorithm using a likelihood ratio test. Optimal threshold values are quantitatively isolated using two data-driven methods: maximum total accuracy and Bayesian cross validation criteria. The proposed methods are evaluated using a dataset of 28 dental lesions in 3D cone-beam CT scans. Both methods produce viable thresholds, the first corresponding to a conservative segmentation and the second a relaxed segmentation. We qualitatively compare the results to determine the best method.