ECE2013 Poster Presentations Developmental Endocrinology (14 abstracts)
Optimising strategies for face classification in the detection of acromegaly
Richard Frohner 1 , Robert P Kosilek 1 , Claudia Reinholz 1 , Dilek Gogas 2 , Alexander Lammert 3 , Rolf P Würtz 4 & Harald J Schneider 1
1Medizinische Klinik IV, Munich, Germany; 2School of Medicine, Marmara Universtiy, Istanbul, Turkey; 3University Medicine Mannheim, Mannheim, Germany; 4Institut für Neuroinformatik, Bochum, Germany.
Introduction: It has been shown that face classification software might help distinguishing between subjects with and without acromegaly on regular photographs. In this project, we investigated several aspects that will be necessary and helpful to bring this recognition method closer to clinical application.
Methods: Face classification was based on nodes placed on frontal and side photographs of individuals and analysis the underlying texture and geometric functions. In the first step, we analysed whether omission of nodes considered less relevant would change classification rates in the original database on 57 acromegalics and 60 controls. In a second step, we analysed how a completely new set of nodes (referring to the most common changes in morphological changes in face) will affect the classification rate.
In a third step, we analysed whether classification was improved in an external data set consisting of 82 acromegalics and 141 controls for both steps.
Results: Correct classification rates in the original database were 79% with all nodes 78% if irrelevant points were omitted and 80% using the new set of nodes.
Using the same approach, in the validation set, correct classification rates were 78% with all nodes (80 and 76% of acromegalics and controls, respectively) 86% (85 and 86% of acromegalics and controls, respectively) after omission of irrelevant nodes and 93% (92 and 93% of acromegalics).
Conclusions: Reduction of nodes associated with unwanted noise can improve correct classification rates in the detection of acromegaly by face classification software.
Article tools
My recent searches
My recently viewed abstracts
Authors
Endocrine Abstracts
ISSN 1470-3947 (print) | ISSN 1479-6848 (online)
© Bioscientifica 2024 |
Privacy policy |
Cookie settings
BiosciAbstracts
Bioscientifica Abstracts is the gateway to a series of products that provide a permanent, citable record of abstracts for biomedical and life science conferences.
Find out more