institute for systems and robotics instituto de medicina molecular automatic pairing of metaphase...
TRANSCRIPT
Institute for Systems and Roboticshttp://www.isr.ist.utl.pt
Instituto de Medicina Molecularhttp://www.imm.ul.pt
Automatic Pairing of Metaphase Chromosomes with Mutual Information for Karyotyping Purposes
Artem Khmelinskii1, Rodrigo Ventura1, Carmo-Fonseca, M.2 and João Sanches1
([email protected]), ([email protected]), ([email protected]), ([email protected])
1Systems and Robotic Institute / Instituto Superior Técnico2Instituto de Medicina Molecular / Faculdade de Medicina de Lisboa
Lisboa , Portugal
Abstract
Clinical cytogenetics plays a key role in the diagnosis of genetic diseases and haematological disorders that involve chromosomal abnormalities. A major technique used in cytogenetics is karyotyping. A karyotype analysis consists of blocking cells in mitosis and staining the chromosomes.The 46 human chromosomes are then paired and visually arranged in decreasing order of size.The pairing procedure aims at to identify all pairs of homologous chromosomes. The pairing criterion is based on dimensional, morphological, and textural features similarity. This process is time consuming when performed manually, and demanding from a technical point of view. An automatic pairing algorithm would thus bring benefits, but it remains an open problem to date.In this work a new strategy for automatic pairing of homologous chromosomes is proposed.Besides the traditional features described in the literature, the Mutual Information (MI) is used to discriminate chromosome textural differences. A supervised non-linear classifier is trained by using manual classifications provided by expert technicians, combining the different features computed from each pair.Simulations using 836 real chromosome images taken from bone marrow samples of patients with haematological disorders, obtained with a Leica Optical Microscope DM 2500, in a leave-one-out cross-validation fashion, were performed for training and testing the algorithm.Furthermore, qualitative comparisons with the results obtained with the Leica CW 4000 Karyo software were also performed. Promising and relevant results were found, despite the poor quality of the original chromosome images, contrasting with state-of-the-art algorithms and datasets found in the literature.
Feature Extraction
1. Size – Area, Perimeter, Bounding Box dimensions, Aspect Ratio
2. Shape – Normalized area (Perimeter/Area)
3. Texture – Mutual Information (pair), Band Profile
Pairs F1 F2 ... FL
P11 d1(1,1) d2(1,1) ... dL(1,1)
P12 d1(1,2) d2(1,2) ... dL(1,2)
...
PNN d1(N,N) d2(N,N) ... dL(N,N)
Data – Feature/Distance Matrix
Pre-processing
1. Metaphase Chromosome extraction
2. Geometrical Compensation
3. Geometrical Scaling
4. Intensity Compensation
pi,j c1 c2 ... cN-1 cN
c1 - 1 ... 0 0
c2 1 - ... 0 0
... ... ... ... ... ...
cN-1 ... 1
cN 0 0 ... 1 -
Classifier Binary Global Optimization
Find a permutation matrix, , where
€
pi, ji=1
N
∑ =1, ∀ i, and pi, jj=1
N
∑ =1, ∀ j
€
P = pi, j{ }
Mutual Information
Without with
Data Set 1 94.4% 94.4%
Data Set 2 93.5% 95.4%
Data Set 3 68.9% 70.1%
Training
1. Distance between two chromosomes p and q:
2. Training -- computing wr
€
d(p,q) = mini
wi(k)dk (p,q)k=1
L
∑
€
wr = argmin d(a,b)(a,b )∈V (r )
∑ − d(a,b)(a,b )∈U (r)
∑
Results
This work was partially supported by FCT (ISR/IST plurianual funding) through the POS_Conhecimento Program that includes FEDER funds.