Cargando…

Application of Neural Networks to the Classification of Pancreatic Intraductal Proliferative Lesions

The aim of the study was to test applycability of neural networks to classification of pancreatic intraductal proliferative lesions basing on nuclear features, especially chromatin texture. Material for the study was obtained from patients operated on for pancreatic cancer, chronic pancreatitis and...

Descripción completa

Detalles Bibliográficos
Autores principales: Okoń, Krzysztof, Tomaszewska, Romana, Nowak, Krystyna, Stachura, Jerzy
Formato: Online Artículo Texto
Lenguaje:English
Publicado: IOS Press 2001
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4618009/
https://www.ncbi.nlm.nih.gov/pubmed/12082293
http://dx.doi.org/10.1155/2001/657268
_version_ 1782396874590781440
author Okoń, Krzysztof
Tomaszewska, Romana
Nowak, Krystyna
Stachura, Jerzy
author_facet Okoń, Krzysztof
Tomaszewska, Romana
Nowak, Krystyna
Stachura, Jerzy
author_sort Okoń, Krzysztof
collection PubMed
description The aim of the study was to test applycability of neural networks to classification of pancreatic intraductal proliferative lesions basing on nuclear features, especially chromatin texture. Material for the study was obtained from patients operated on for pancreatic cancer, chronic pancreatitis and other tumours requiring pancreatic resection. Intraductal lesions were classified as low and high grade as previously described. The image analysis system consisted of a microscope, CCD camera combined with a PC and AnalySIS v. 2.11 software. The following texture characteristics were measured: variance of grey levels, features extracted from the grey levels correlation matrix and mean values, variance and standard deviation of the energy obtained from Laws matrices. Furthermore we used moments derived invariants and basic geometric data such as surface area, the minimum and maximum diameter and shape factor. The sets of data were randomly divided into training and testing groups. The training of the network using the back‐propagation algorithm, and the final classification of data was carried out with a neural network simulator SNNS v. 4.1. We studied the efficacy of networks containing from one to three hidden layers. Using the best network, containing three hidden layers, the rate of correct classification of nuclei was 73%, and the rate of misdiagnosis was 3%; in 24% the network response was ambiguous. The present findings may serve as a starting point in search for methods facilitating early diagnosis of ductal pancreatic carcinoma.
format Online
Article
Text
id pubmed-4618009
institution National Center for Biotechnology Information
language English
publishDate 2001
publisher IOS Press
record_format MEDLINE/PubMed
spelling pubmed-46180092016-01-12 Application of Neural Networks to the Classification of Pancreatic Intraductal Proliferative Lesions Okoń, Krzysztof Tomaszewska, Romana Nowak, Krystyna Stachura, Jerzy Anal Cell Pathol Other The aim of the study was to test applycability of neural networks to classification of pancreatic intraductal proliferative lesions basing on nuclear features, especially chromatin texture. Material for the study was obtained from patients operated on for pancreatic cancer, chronic pancreatitis and other tumours requiring pancreatic resection. Intraductal lesions were classified as low and high grade as previously described. The image analysis system consisted of a microscope, CCD camera combined with a PC and AnalySIS v. 2.11 software. The following texture characteristics were measured: variance of grey levels, features extracted from the grey levels correlation matrix and mean values, variance and standard deviation of the energy obtained from Laws matrices. Furthermore we used moments derived invariants and basic geometric data such as surface area, the minimum and maximum diameter and shape factor. The sets of data were randomly divided into training and testing groups. The training of the network using the back‐propagation algorithm, and the final classification of data was carried out with a neural network simulator SNNS v. 4.1. We studied the efficacy of networks containing from one to three hidden layers. Using the best network, containing three hidden layers, the rate of correct classification of nuclei was 73%, and the rate of misdiagnosis was 3%; in 24% the network response was ambiguous. The present findings may serve as a starting point in search for methods facilitating early diagnosis of ductal pancreatic carcinoma. IOS Press 2001 2001-01-01 /pmc/articles/PMC4618009/ /pubmed/12082293 http://dx.doi.org/10.1155/2001/657268 Text en Copyright © 2001 Hindawi Publishing Corporation.
spellingShingle Other
Okoń, Krzysztof
Tomaszewska, Romana
Nowak, Krystyna
Stachura, Jerzy
Application of Neural Networks to the Classification of Pancreatic Intraductal Proliferative Lesions
title Application of Neural Networks to the Classification of Pancreatic Intraductal Proliferative Lesions
title_full Application of Neural Networks to the Classification of Pancreatic Intraductal Proliferative Lesions
title_fullStr Application of Neural Networks to the Classification of Pancreatic Intraductal Proliferative Lesions
title_full_unstemmed Application of Neural Networks to the Classification of Pancreatic Intraductal Proliferative Lesions
title_short Application of Neural Networks to the Classification of Pancreatic Intraductal Proliferative Lesions
title_sort application of neural networks to the classification of pancreatic intraductal proliferative lesions
topic Other
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4618009/
https://www.ncbi.nlm.nih.gov/pubmed/12082293
http://dx.doi.org/10.1155/2001/657268
work_keys_str_mv AT okonkrzysztof applicationofneuralnetworkstotheclassificationofpancreaticintraductalproliferativelesions
AT tomaszewskaromana applicationofneuralnetworkstotheclassificationofpancreaticintraductalproliferativelesions
AT nowakkrystyna applicationofneuralnetworkstotheclassificationofpancreaticintraductalproliferativelesions
AT stachurajerzy applicationofneuralnetworkstotheclassificationofpancreaticintraductalproliferativelesions