|
|
|
Tissue Counter Analysis of histological imagesby
Marco Wiltgen, Dr.
MED UNI GRAZ
Inst f medizinische
Informatik, Statistik und
dokumentation
| Lecture takes place
on: |
Tuesday the 13th of July |
| Starting at: |
8:30 |
| Duration: |
45 minutes |
|
| Additional Information: |
 Lecture_17.ppt |
|
| Link for ext. Info: |
not
available |
Abstract:
Microscopic
views of histological tissues show structures mostly arranged in a
variety of patterns. Therefore the automatic segmentation of
different structures, like cells, nuclei, cytoplasm, vessels etc.,
is difficult, depending on the concrete tissue and cannot be done in
a general approach. The practical applicability of the analysis of
histological tissues is largely limited by the problem of detecting
structures of interest. This is one reason why compact tissue
structures generally resist a fully automatic analysis.
Nevertheless, automatic discrimination of tissue structures plays an
important task in medical image analysis due to an increasing need
of objectivity and assessment in diagnosis.
We present
tissue counter analysis (TCA) as a method for discrimination of
different histological tissues. TCA is based on the partition of the
image into square elements of equal size where the features,
describing the tissue, are calculated out of each square element.
Because TCA needs no image segmentation, problems related to this
task are avoided. We concentrate our attention on the automatic
analysis of benign common nevi and malignant melanoma lesions and
check the applicability of tissue counter analysis to the diagnostic
discrimination.
The TCA consists of 3 steps: The feature
analysis and extraction, the classification and the relocation. The
features are based on grey level histogram and co-occurrence matrix.
80 cases from microscopic views of benign common nevi and malignant
melanoma were sampled. From this study set 40 cases were randomly
selected as learning set and the remaining 40 cases were used as
test set. The classification was done by CART (Classification and
Regression Trees) analysis. Each image was dissected in 256 square
elements and 51 different features, describing histogram and
co-occurrence matrix, were used. The square elements from the images
of a learning set were classified. To evaluate the recognition rate
the classification results were applied to individual cases of the
test set. The classification results were indicated in the original
image in order to evaluate the performance of the procedure
(relocation).
The results from classification show a
clear-cut difference between common nevi and malignant melanoma.
With the features based on histogram and co-occurrence matrix the
classification correctly classified 92,7% of nevi elements and 92,1%
of melanoma elements in the learning set. In the test set,
discriminant analysis based on the percentage of “malignant
elements” showed a correct classification of all cases (sensitivity
= 100 %, specificity = 100 %).
In conclusion, tissue counter
analysis is a potential diagnostic tool in automatic or semi
automatic analysis of melanocytic skin
tumors.
References
Wiltgen M, Gerger A, Smolle J.
Tissue counter analysis of benign common nevi and malignant
melanoma. International Journal of Medical Informatics 2003;
69/1:17-28
M. Wiltgen, A. Gerger, C. Wagner, P. Bergthaler,
J. Smolle.
Discrimination of benign common nevi and malignant
melanoma lesions by use of features based on spectral properties of
the wavelet transform.
Analytical and Quantitative Cytology and
Histology Volume 25,
Number 5/October 2003: pp 243-253
M.
Wiltgen, A. Gerger, C. Wagner, P. Bergthaler, J.
Smolle
Evaluation of the influence of image compression to the
automatic discrimination of histological images of skin
lesions
Methods Inf Med 2004 43: pp
141-9
| |
SSIP 04 
