Images were collected of CHO cells showing five distinct subcellular patterns. Briefly, cells were grown to sub-confluent levels on collagen-coated microscope coverslips, fixed in paraformaldehyde and permeabilized with saponin. The cells were incubated with one of four primary antibodies (chosen to yield qualitatively different patterns), and stained with Hoechst 33258 (to label the nucleus) in parallel with a fluorescently-conjugated secondary antibody. The antibodies used were against giantin (a Golgi protein), LAMP2 (a lysosomal protein), tubulin (a cytoskeletal protein), and NOP4 (an S. cerevisiae nucleolar protein). (The antibody against NOP4 cross-reacted with a CHO protein mainly located in the nucleus but also found in the cytoplasm.) Coverslips were searched for fields containing cells that were well spread and separated from their neighbors. A stack of three images was then taken in which the focus was adjusted by a small amount between each image in the stack. Slides were processed in this way until there were enough digital images available to train and test the classification schemes described below. There were 33 to 97 images available for each class of fluorescence distribution. >>>>
Image stacks were deconvolved to remove out of focus fluorescence, cropped to a rectangular region containing a single cell, corrected for background fluorescence, and thresholded as described in Materials and Methods. Prior to subsequent feature extraction steps, the images were segregated into distinct training and test sets. >>>>
Sample images for each class of pattern are shown in Figure 2.3. These images were chosen to represent their respective classes using a feature-based method for picking a representative image [34]. >>>>
>>>>
![]() |
>>>>