Abstract
Scientists wishing to communicate the essential characteristics of a pattern (such as an immunofluorescence distribution) currently must make a subjective choice of one or two images to publish. We therefore developed methods for objectively choosing a typical image from a set, with emphasis on images from cell biology. The methods involve calculation of numerical features to describe each image, calculation of similarity between images as a distance in feature space, and ranking of images by distance from the center of the feature distribution. Two types of features were explored image texture measures and Zernike polynomial moments, and various distance measures were utilized. Criteria for evaluating methods for assigning typicality were proposed and applied to sets of images containing more than one pattern. The results indicate the importance of using distance measures that are insensitive to the presence of outliers. For collections of images of the distributions of a lysosomal protein, a Golgi protein, and nuclear DNA, the images chosen as most typical were in good agreement with the conventional understanding of organelle morphologies. The methods described here have been implemented in a web server (http://murphylab.web.cmu.edu/services/TypIC).
| Original language | English (US) |
|---|---|
| Pages (from-to) | 2230-2237 |
| Number of pages | 8 |
| Journal | Biophysical Journal |
| Volume | 76 |
| Issue number | 4 |
| State | Published - 1999 |
| Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- Biophysics
Cite this
Toward objective selection of representative microscope images. / Markey, Mia K.; Boland, Michael; Murphy, Robert F.
In: Biophysical Journal, Vol. 76, No. 4, 1999, p. 2230-2237.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Toward objective selection of representative microscope images
AU - Markey, Mia K.
AU - Boland, Michael
AU - Murphy, Robert F.
PY - 1999
Y1 - 1999
N2 - Scientists wishing to communicate the essential characteristics of a pattern (such as an immunofluorescence distribution) currently must make a subjective choice of one or two images to publish. We therefore developed methods for objectively choosing a typical image from a set, with emphasis on images from cell biology. The methods involve calculation of numerical features to describe each image, calculation of similarity between images as a distance in feature space, and ranking of images by distance from the center of the feature distribution. Two types of features were explored image texture measures and Zernike polynomial moments, and various distance measures were utilized. Criteria for evaluating methods for assigning typicality were proposed and applied to sets of images containing more than one pattern. The results indicate the importance of using distance measures that are insensitive to the presence of outliers. For collections of images of the distributions of a lysosomal protein, a Golgi protein, and nuclear DNA, the images chosen as most typical were in good agreement with the conventional understanding of organelle morphologies. The methods described here have been implemented in a web server (http://murphylab.web.cmu.edu/services/TypIC).
AB - Scientists wishing to communicate the essential characteristics of a pattern (such as an immunofluorescence distribution) currently must make a subjective choice of one or two images to publish. We therefore developed methods for objectively choosing a typical image from a set, with emphasis on images from cell biology. The methods involve calculation of numerical features to describe each image, calculation of similarity between images as a distance in feature space, and ranking of images by distance from the center of the feature distribution. Two types of features were explored image texture measures and Zernike polynomial moments, and various distance measures were utilized. Criteria for evaluating methods for assigning typicality were proposed and applied to sets of images containing more than one pattern. The results indicate the importance of using distance measures that are insensitive to the presence of outliers. For collections of images of the distributions of a lysosomal protein, a Golgi protein, and nuclear DNA, the images chosen as most typical were in good agreement with the conventional understanding of organelle morphologies. The methods described here have been implemented in a web server (http://murphylab.web.cmu.edu/services/TypIC).
UR - http://www.scopus.com/inward/record.url?scp=0033065594&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0033065594&partnerID=8YFLogxK
M3 - Article
C2 - 10096918
AN - SCOPUS:0033065594
VL - 76
SP - 2230
EP - 2237
JO - Biophysical Journal
JF - Biophysical Journal
SN - 0006-3495
IS - 4
ER -