eISSN: 1897-4309
ISSN: 1428-2526
Contemporary Oncology/Współczesna Onkologia
Current issue Archive Manuscripts accepted About the journal Supplements Addendum Special Issues Editorial board Reviewers Abstracting and indexing Subscription Contact Instructions for authors Publication charge Ethical standards and procedures
Editorial System
Submit your Manuscript
SCImago Journal & Country Rank
8/2007
vol. 11
 
Share:
Share:
abstract:

An application of artificial neural networks in breast cancer recognition using scintimammography

Dariusz Świetlik
,
Tomasz Bandurski
,
Mariusz Masiuk

Współczesna Onkologia (2007) vol. 11; 8 (385–389)
Online publish date: 2007/11/14
View full text Get citation
 
The aim of the study was to assess the usefulness of artificial neural networks (ANN) application in evaluation of
scintimammography in the context of clinical data in the diagnosis of breast cancer. The results produced by ANN were compared with the diagnosis of two independent observers, nuclear medicine specialists.
Material and methods: The clinical data and the numerical values derived from scintimammograms of 103 patients were the material for the study. The reference method was the result of histopathology study (core biopsy and /or FNB).
Results: The overall sensitivity of physician diagnosis was 78% with specificity of 72%. The ANN produced 71% sensitivity and specificity of 73%. The physicians’ and ANN results were not significantly different (p=0.4619).
Conclusions: Artificial neutral networks are useful tool in clinical diagnosis of breast cancer.
keywords:

artificial neural network, scintimammography, breast cancer

Quick links
© 2024 Termedia Sp. z o.o.
Developed by Bentus.