Applying machine learning methods for the analysis of two-dimensional mass spectra.

In a measurement of isomeric yield-ratios in fission, the Phase-Imaging Ion-Cyclotron-Resonance technique, which projects the radial motions of ions in the Penning trap (JYFLTRAP) onto a position-sensitive micro-channel plate detector, has been applied. To obtain the yield ratio, that is the relative population of two states of an isomer pair, a novel analysis procedure has been developed to determine the number of detected ions in each state, as well as corrections for the detector efficiency and decay losses. In order to determine the population of the states in cases where their mass difference is too small to reach full separation, a Bayesian Gaussian Mixture model was implemented. The position-dependent efficiency of the micro-channel plate detector was calibrated by mapping it with 133Cs+ ions, and a Gaussian Process was trained with the position data to construct an efficiency function that could be used to correct the recorded distributions. The obtained numbers of counts of excited and ground-state ions were used to derive the isomeric yield ratio, taking into account decay losses as well as feeding from precursors.

Quantitative chromogenic immunohistochemical image analysis in cellprofiler software.

Visual grading of chromogenically stained immunohistochemical (IHC) samples is subjective, time consuming, and predisposed to considerable inter- and intra-observer variations. The open-source digital analysis software, CellProfiler has been extensively used for fluorescently stained cells/tissues; however, chromogenic IHC staining is routinely used in both pathological and research diagnostics. The current investigation aimed to compare CellProfiler quantitative chromogenic IHC analyses against the gold standard manual counting. Oral mucosal biopsies from patients with chronic graft-versus-host disease were stained for CD4. Digitized images were manually counted and subjected to image analysis in CellProfiler. Inter-observer and inter-platform agreements were assessed by scatterplots with linear regression and Bland-Altman plots. Validation comparisons between the manual counters demonstrated strong intra-observer concordance (r2 = 0.979), particularly when cell numbers were less than 100. Scatterplots and Bland-Altman plots demonstrated strong agreement between the manual counters and CellProfiler, with the number of positively stained cells robustly correlating (r2 = 0.938). Furthermore, CellProfiler allowed the determination of multiple variables simultaneously, such as area stained and masking to remove any nonstained tissue and white gaps, which also demonstrated reliable agreement (r2 = >0.9). CellProfiler demonstrated versatility with the ability to assess large numbers of images and allowed additional parameters to be quantified. CellProfiler allowed rapid high processing capacity of chromogenically stained chronic inflammatory tissue that was reliable, accurate, and reproducible and highlights potential applications in research diagnostics.