%PDF-1.4
%
1 0 obj
<>
endobj
2 0 obj
<>stream
Multilayer perceptron
Support vector machine
Locally constrained watershed transform
Gland unit identification
Histological prostate image
A new approach for the segmentation of gland units in histological images is proposed with the aim of contributing to the improvement of the prostate cancer diagnosis. Clustering methods on several
colour spaces are applied to each sample in order to generate a binary
mask of the different tissue components. From the mask of lumen candidates, the Locally Constrained Watershed Transform (LCWT) is applied
as a novel gland segmentation technique never before used in this type
of images. 500 random gland candidates, both benign and pathological,
are selected to evaluate the LCWT technique providing results of Dice
coefficient of 0.85. Several shape and textural descriptors in combination
with contextual features and a fractal analysis are applied, in a novel
way, on different colour spaces achieving a total of 297 features to discern between artefacts and true glands. The most relevant features are
then selected by an exhaustive statistical analysis in terms of independence between variables and dependence with the class. 3.200 artefacts,
3.195 benign glands and 3.000 pathological glands are obtained, from a
data set of 1468 images at 10x magnification. A careful strategy of data
partition is implemented to robustly address the classification problem
between artefacts and glands. Both linear and non-linear approaches are
considered using machine learning techniques based on Support Vector
Machines (SVM) and feedforward neural networks achieving values of
sensitivity, specificity and accuracy of 0.92, 0.97 and 0.95, respectively
Reserva de todos los derechos
Embargado
http://hdl.handle.net/10251/124077
Springer
Adrián Colomer
Valeriana Naranjo Ornedo
Francisco Peñaranda
María Ángeles Sales
Intelligent Data Engineering and Automated Learning – IDEAL 2018
Inglés
endstream
endobj
3 0 obj
<>/ExtGState<>/Font<>/XObject<>>>/Rotate 0/StructParents 0/Type/Page>>
endobj
21 0 obj
<>
endobj
24 0 obj
<>
endobj
28 0 obj
<>
endobj
32 0 obj
<>
endobj
36 0 obj
<>
endobj
40 0 obj
<>
endobj
43 0 obj
<>
endobj
47 0 obj
<>
endobj
50 0 obj
<>
endobj
8 0 obj
<>
endobj
4 0 obj
<>stream
x+ |
endstream
endobj
5 0 obj
<>stream
HUo0>ƓᩪT:R+,Җm$ºs d%ݽwyjYϞݤ߯$܀)JHpaT%\gOE-@l;2+]=J
Z@JDLe$elMxyYVD%0\
[Lymi]յSǶZ gfxRQ<",5)"ViMe7x00YaѰAl 9)@Dt<"Ǥ)W`A~o*۸&O B7 QÑ CՄp=gYX5S!L7&ӰInʤp}fQ.j^=o-2&5ϨIv@nD
4R\p.{]PDCjY3$B@n-<k"H:R3Pp+&`|;