Fourier-ring descriptor to characterize rare circulating cells from images generated using immunofluorescence microscopy

Tegan Emerson; Michael Kirby; Kelly Bethel; Anand Kolatkar; Madelyn Luttgen; Stephen O'Hara; Paul Newton; Peter Kuhn

doi:10.1016/j.compmedimag.2014.10.003

Fourier-ring descriptor to characterize rare circulating cells from images generated using immunofluorescence microscopy

Comput Med Imaging Graph. 2015 Mar:40:70-87. doi: 10.1016/j.compmedimag.2014.10.003. Epub 2014 Oct 23.

Authors

Tegan Emerson¹, Michael Kirby², Kelly Bethel³, Anand Kolatkar⁴, Madelyn Luttgen⁵, Stephen O'Hara⁶, Paul Newton⁷, Peter Kuhn⁸

Affiliations

¹ Department of Mathematics, Colorado State University, 841 Oval Drive, Fort Collins, CO 80523, United States. Electronic address: emerson@math.colostate.edu.
² Department of Mathematics, Colorado State University, 841 Oval Drive, Fort Collins, CO 80523, United States. Electronic address: kirby@math.colostate.edu.
³ The Scripps Clinic, Department of Pathology, 10666 N Torrey Pines Road, La Jolla, CA 92037, United States. Electronic address: Bethel.Kelly@scrippshealth.org.
⁴ The Scripps Research Institute, The Kuhn Lab, 10550 N Torrey Pines Road, La Jolla, CA 92037, United States. Electronic address: anandk@scripps.edu.
⁵ The Scripps Research Institute, The Kuhn Lab, 10550 N Torrey Pines Road, La Jolla, CA 92037, United States. Electronic address: mluttgen@scripps.edu.
⁶ DigitalGlobe, Image Mining Group, 1601 Dry Creek Drive, Longmont, CO 80503, United States. Electronic address: svohara@ieee.org.
⁷ Department of Aerospace and Mechanical Engineering, University of Southern California Viterbi School of Engineering, Los Angeles, CA 90089, United States. Electronic address: newton@usc.edu.
⁸ The Kuhn Lab, Department of Biological Sciences, University of Southern California, Los Angeles, CA 90089, United States. Electronic address: peter.kuhn@usc.edu.

PMID: 25456146
DOI: 10.1016/j.compmedimag.2014.10.003

Abstract

We address the problem of subclassification of rare circulating cells using data driven feature selection from images of candidate circulating tumor cells from patients diagnosed with breast, prostate, or lung cancer. We determine a set of low level features which can differentiate among candidate cell types. We have implemented an image representation based on concentric Fourier rings (FRDs) which allow us to exploit size variations and morphological differences among cells while being rotationally invariant. We discuss potential clinical use in the context of treatment monitoring for cancer patients with metastatic disease.

Publication types

Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

Algorithms
Artificial Intelligence
Cell Tracking / methods*
Fourier Analysis
Humans
Image Enhancement / methods
Image Interpretation, Computer-Assisted / methods*
Microscopy, Fluorescence / methods*
Neoplastic Cells, Circulating / pathology*
Pattern Recognition, Automated / methods*
Reproducibility of Results
Sensitivity and Specificity
Subtraction Technique*