Murphy Lab

The subcellular location pattern represented by a collection of similar images can be described according to a variety of numeric features. These features have been grouped into more than 10 sets known as SLF sets (Subcellular Location Feature sets). In order to demonstrate the usefulness of these features they have been used to train a classifier, which was able to correctly recognize an average of 92% (2D) and 98% (3D) of previously unseen cells showing one of ten patterns. The SLF sets are described as follows:

2D SLF

Name	Parallel DNA image required?	Cell segmentation required?	Number of features	Description	Reference
SLF1	No	Yes	16	Morphological features.	[Boland & Murphy, 2001]
SLF2	Yes	Yes	22	SLF1 plus six features calculated using both the processed protein image and the corresponding DNA image.	[Boland & Murphy, 2001]
SLF3	No	Yes	78	The combination of SLF1 with Zernike and Haralick features that can be calculated from a protein image only.	[Boland & Murphy, 2001]
SLF4	Yes	Yes	84	The combination of SLF2 with Zernike and Haralick features derived from a protein image and a corresponding DNA image.	[Boland & Murphy, 2001]
SLF5	Yes	Yes	37	A subset of features selected from the SLF4 set via stepwise discriminant analysis (SDA).	[Boland & Murphy, 2001]
SLF6	No	Yes	65	The combination of SLF1 with Zernike features.	[Roques & Murphy, 2002]
SLF7	No	Yes	84	Normalized features designed to enable description and classification of images from heterogeneous sources.	[Murphy, Velliste & Porreca, 2002]
SLF8	No	Yes	32	Subset chosen by SDA from SLF7.	[Murphy, Velliste & Porreca, 2002]
SLF12	No	Yes	8	Subset chosen by SDA from SLF7. It is the smallest group to achieve over 80% accuracy on the 2D HeLa dataset.	[Huang, Velliste & Murphy, 2002]
SLF13	Yes	Yes	31	Subset chosen by SDA from SLF7 plus 6 DNA features.	[Murphy, Velliste & Porreca, 2003]
SLF15	No	Yes	44	Subset chosen by SDA from 174 features including 84 SLF7, 60 Gabor texture features and 30 wavelet features.	[Huang & Murphy, 2004b]
SLF16	Yes	Yes	47	Subset chosen by SDA from 180 features including 84 SLF7, 60 Gabor texture features, 30 wavelet features and 6 DNA features.	[Huang & Murphy, 2004b]
SLF21	No	No	26	Subset of rotationally invariant SLF7 features that are also independent of the number of cells in a field. Consists of 13 morphological and 13 texture features.	[Huang & Murphy, 2004a]
SLF25	Yes	No	87	SLF21 plus 1 DNA overlap feature plus Haralick texture features for image downsampled from two through six fold.	[Garcia Osuna, Hua, Bateman, Zhao, Berget & Murphy, 2007]
SLF26	Yes	Yes	9	Parameters of generative model of subcellular distribution.	[Zhao & Murphy, 2007]
SLF27	Yes	Yes	84	SLF7 calculated with more robust background correction.
SLF28	No	Yes	8	Features for estimating image resolution from cell images given just a single channel.	[Coelho & Murphy, 2008]
SLF29	Yes	Yes	16	Features for estimating image resolution from cell images given two channel images (e.g., protein and DNA).	[Coelho & Murphy, 2008]
SLF30	Yes	Yes	90	SLF7 plus DNA features, calculated with more robust background correction.
SLF31	No	No	18	Parameter-free version of Threshold Adjacency Statistics originally described by Hamilton et al., 2007.	[Coelho et al., 2010]
SLF32	Yes	Yes	108	Combination of SLF30 plus SLF31.
SLF33	No	No	161	91 haralick features - original and at 6 different downsamples (SLF3.66-3.78 and SLF33.38-115), 5 object features (SLF1.1-1.5), 5 edge features (SLF1.9-1.13), 5 skeleton features (SLF7.80-7.84), 1 nonobj fluor feature (SLF7.79), 54 pfTAS features - (SLF31.1-18 plus 18 calculated at mean and mean-margin)
SLF34	Yes	No	173	SLF33 plus DNA features (SLF2.21, SLF2.22, 10 new overlap features)
SLF35	Yes	No	23	Features selected by SDA from SLF34 using IC100 images from the RandTag project.
SLF36	Yes	No	22	Features selected by SDA from SLF34 using confocal images from the RandTag project.

3D SLF

• SLF9 - A set of 28 features for describing 3D images derived from SLF2. [Velliste & Murphy, 2002]
• SLF10 - Nine features selected by SDA from SLF9. [Huang & Murphy, 2004b]
• SLF11 - Unselected set containing morphological, edge and texture features. [Chen, Velliste, Weinstein, Jarvik & Murphy, 2003]
• SLF14 - Features in SLF9 that do not require a parallel DNA image. [Huang & Murphy, 2004b]
• SLF17 - 7 Features selected by SDA from SLF11. The texture features are calculated at 0.4 microns and 256 gray levels. [Chen & Murphy, 2004]
• SLF18 - 34 Features selected by SDA from SLF11. The texture features are calculated at 0.5 microns and 64 gray levels. [Chen & Murphy, 2005]
• SLF19 - Defined as the combination of SLF11 and 14 DNA features. The texture features are calculated at 0.09 microns and 256 gray levels. [Nair, Schaub, Huang, Chen, Murphy, Griffith, Geuze, & Rohrer, 2005]
• SLF20 - 52 features selected by SDA from SLF19. [Nair, Schaub, Huang, Chen, Murphy, Griffith, Geuze, & Rohrer, 2005]
• SLF22 - 14 Morphological and 2 edge features calculated after downsampling (if necessary) to a resolution of 0.11 x 0.11 x 0.5 microns. 26 texture features calculated after downsampling to 0.5 microns and 64 gray levels.
• SLF23 - 14 Morphological and 2 edge features calculated after downsampling (if necessary) to a resolution of 0.05 x 0.05 x 0.2 microns. 26 texture features calculated after downsampling to 0.4 microns and 256 gray levels.
• SLF24 - SLF23 plus 14 DNA features calculated after downsampling image to a resolution of 0.05 x 0.05 x 0.2 microns.

Last Updated: 26 Jun 2005

Copyright © 1996-2005 by the Murphy Lab