Transcript A Framework for a Fully Automatic Karyotyping System

A Framework for a
Fully Automatic Karyotyping System
E. Poletti, E. Grisan, A. Ruggeri
Department of Information Engineering, University of Padova, Italy
Introduction
 Karyotype analysis is a widespread procedure in cytogenetics to assess the
possible presence of genetics defects. The procedure is lengthy and repetitive,
so that an automatic analysis would greatly help the cytogenetist routine work.
 The segmentation is carried out by means of a space variant thresholding scheme,
which proved to be successful even in presence of hyper- or hypo-fluorescent
regions in the image. Then a greedy approach is used to identify and resolve
touching and overlapping chromosomes, based on geometric evidence and image
information.
 Still, automatic segmentation and classification of chromosomes are open
issues: existing commercial software packages are far from being fully
automatic and their poor performances require human intervention to correct
challenging situations. We propose a framework for a fully automatic
karyotyping procedure.
 The classification step is coupled with a sequence of modules conceived to cope
with routine images in which chromosomes are randomly rotated, possibly blurred
or corrupted by overlapping or by dye stains.
Methods: Segmentation
A cluster is selected
for analysis
Original input image
Push clusters
into the queue
An axis is extracted and
the SCM is evaluated
Pop first cluster
and
evaluate the SCM
Single
chromosome?
Y
Save single
chromosome
N
Identify new
clusters
Single Chromosome Measure (SCM)
• morphological dilation of the axis with a disk
• evaluation of the ratio of the obtained area with that of the original blob.
space variant thresholding:
cluster identification
Dark paths
The quasi-contact area along
adjacent chromosomes.
Geometric analysis
and
Disentanglement
Resolution of the cluster used
as example
Concave points
identification
Overlaps
Each two of lines connecting
disjoint pairs of minima points in
K are considered.
Concave points as cues
The local minima of the curvature of the contour (K) are the points
suggesting the possible presence of touching and overlaps.
Geometrical cuts
Candidate cut lines links two
points in K and lies entirely
inside the cluster.
Space variant threshold
• divide the image into a tessellation of squares
• evaluate the Otsu threshold for each square separately
Concave points are here
identified and used as cues
for cuts and overlaps
 elimination of small, spurious segmented blobs
 identification of nuclei present in the image
Curvature along the contour
Classification
Feature pre-processing
Features extraction
Polarization
The axis estimation is carried out by a robust
modified version of a vessel-tracking algorithm.
Chromosomes are randomly rotated.
Three features are derived from the axis:
 length
 density profile (64 samples)
 contour function (64 samples)
• an uniformed array feature orderliness
• the orientation standard adopted
• different zoom
• different illumination conditions
• chromosomes belonging to slightly
different stages of the prometaphase
 Boosted alternating decision tree:
 standardization needed.
We need to comply with:
Classification via Neural Network
•
•
•
•
3-layer ANN
131, 131, and 24 nodes respectively.
activation functions: log-sigmoid.
training algorithm: scaled conjugate gradient
• training set: 50 karyotypes
• validation set: 20 karyotypes
• testing set::49 karyotypes
Two other geometrical features considered are:
 perimeter
 area
Class Reassigning Algorithm
The human karyotype contains 22 pairs of autosomal chromosomes and
1 pair of sex chromosomes  constrained classification problem.
Linear Programming algorithm:
Decision node: specify a predicate
condition based on a feature.
Axis calculation for the feature extraction
Prediction node: specify a value
to add to the polarization score.
 rearranges the classifier output
 satisfy the above constraints
 maximize the accuracy.
Length distribution for every class,
previous (up) and after (down) rescaling
Results and Discussion
The performance of the proposed methods are better or comparable to the best of
other methods reported in the literature, providing a tool able to automatically
analyze an image, and whose results can be handed over wit minimal human
intervention to a classifier for automatic karyotyping.
119 cells containing a total of 5474 chromosomes was analyzed to test the
segmentation algorithm. 50 of these cells have been used to train the classifier, 20 to
validate the training and 50 to test the classification step.
We have presented an algorithm able to automatically identify chromosomes in
metaphase images, taking care of a first segmentation step and then of the
disentanglement of chromosome clusters by resolving separately adjacencies and
overlaps with a greedy approach, that ensures that at each step only the best split of
a blob is performed. The automatic classification step is able to deal with routine
images in which chromosomes are randomly rotated, blurred, corrupted by
overlapping or by dye stains.
Acknowledgements
Correctly segmented chromosomes
94%
This work has been partially funded by TesiImaging S.r.l., Milan, Italy
Correctly classified chromosomes
96%
Correspondence
Enea Poletti, University of Padova - Dept. of Information Engineering
Via G. Gradenigo 6/a - 35131 Padova - ITALY e-mail: [email protected]