chromosome classification:workflow

The work-flow from raw DAPI image to two features scatter plot can be summarised as follow:

Yellow:to be written

Combining five metaphases, with two features (the area of the segmented particles and the ratio between the particle area and the area of convex hull of the particle) yields the following scatter plot where three clusters can be distinguished:

• blue cluster: nuclei
• red cluster: overlapping chromosomes
• green cluster:single chromosomes
• pink cluster:particles resulting from segmentation artefacts, some corresponds to nuclei touching the image border and should have been classified as nuclei.

As seen in the previous post the green and red clusters partially overlap. The graphic was build as follow with pandas (with some help):

import KarIO
import os,csv
import pylab
import pandas
#make a configurator object
config=KarIO.ClassifConf()
#build the the name feature file
##list all the feature files
##répertoire courant : os.listdir(os.getcwd())
featurespath=os.path.join(os.getcwd(),"Results","features")
labelpath=os.path.join(os.getcwd(),"Results","labels")
#print featurespath
##open features csv files
featuresFilesList=os.listdir(featurespath)
labelsFilesList=os.listdir(labelpath)
##
metalist=[0,1,2,3,4]
#metaphase=2
def makeDataShape(meta):
    featfile=config.user+'-'+config.slide+'-'+config.metaphases_list[meta]+'-'+config.counterstain+'.csv'
    labelfile='shapeCateg-'+featfile
    fea=pandas.read_csv(os.path.join(featurespath,featfile),header=None,index_col=None,names=['particle','ratio','area'])
    lab=pandas.read_csv(os.path.join(labelpath,labelfile),header=None,index_col=None,names=['particle','type'])
    del lab['particle']    
    #merge columns:features and label
    data=fea.join(lab)
    data.insert(0,'meta',config.metaphases_list[meta])
    #print data
    return data
bigdata=makeDataShape(0)
for meta in metalist:
    bigdata=bigdata.append(makeDataShape(meta),ignore_index=True)
single=bigdata[bigdata['type']=='single']
touching=bigdata[bigdata['type']=='touching']
nuclei=bigdata[bigdata['type']=='nuclei']
dusts=bigdata[bigdata['type']=='dusts']
##ploting with pylab
#different colors according to the category
fig=pylab.figure()
ax = fig.add_subplot(111)
ax.scatter(single['ratio'],single['area'],c='green',marker='o')
ax.scatter(touching['ratio'],touching['area'],c='red',marker='o')
ax.scatter(nuclei['ratio'],nuclei['area'],c='blue',marker='o')
ax.scatter(dusts['ratio'],dusts['area'],c='pink',marker='o')
pylab.show()