MIRIAM: A machine and deep learning single-cell segmentation and quantification pipeline for multi-dimensional tissue images.

Increasingly, highly multiplexed tissue imaging methods are used to profile protein expression at the single-cell level. However, a critical limitation is the lack of robust cell segmentation tools for tissue sections. We present Multiplexed Image Resegmentation of Internal Aberrant Membranes (MIRIAM) that combines (a) a pipeline for cell segmentation and quantification that incorporates machine learning-based pixel classification to define cellular compartments, (b) a novel method for extending incomplete cell membranes, and (c) a deep learning-based cell shape descriptor. Using human colonic adenomas as an example, we show that MIRIAM is superior to widely utilized segmentation methods and provides a pipeline that is broadly applicable to different imaging platforms and tissue types.

Validation of Self-Reported Smoking Status Among Orthopedic Hip Surgery Patients.

Purpose The purpose of this study was to determine the accuracy of self-reported non-smoking status in subjects undergoing elective orthopedic surgery as confirmed by serum cotinine levels. Methods Institutional Review Board approval was obtained for this retrospective review of consecutive subjects that underwent elective orthopedic surgery by a single fellowship-trained orthopedic surgeon. All patients provided smoking history (active, former, or non-smoker). Serum cotinine levels defined each subject as "non-smoker", "passive tobacco exposure", or "active smoker". Self-reported non-smokers were eligible for inclusion. Subjects were excluded if they failed to provide smoking history, reported themselves as "smokers", and/or had unavailable serum cotinine levels. Self-reported non-smoking status accuracy was determined by dividing the total number of included subjects by the number of subjects that were defined as "non-smoker" or "passive tobacco exposure" on their serum cotinine test. Results A total of 378 patients (mean age of 42.5 (13-78) years and 68% female) self-reported as non-smokers and were included. A total of 369 subjects had serum cotinine levels consistent with "non-smoking" resulting in a self-reported non-smoking status accuracy of 97.6%. None of the former smokers had cotinine levels consistent with active smoker status. Conclusion Subjects undergoing elective orthopedic surgery self-report as non-smokers with an accuracy of 97.6%. This suggests that routine serum cotinine testing of non-smokers in this patient population may not be necessary.