Please use this identifier to cite or link to this item:

TitleAutomatic modeling of pectus excavatum corrective prosthesis using artificial neural networks
Author(s)Rodrigues, Pedro L.
Rodrigues, Nuno F.
Pinho, A. C. Marques de
Fonseca, Jaime C.
Pinto, Jorge Correia
Vilaça, João L.
KeywordsPectus excavatum
Artificial neural networks
Image segmentation
Prosthesis 45 modelling
Prosthesis modelling
Issue date2014
JournalMedical Engineering & Physics
Abstract(s)Pectus excavatum is the most common deformity of the thorax. Pre-operative diagnosis usually includes Computed Tomography (CT) to successfully employ a thoracic prosthesis for anterior chest wall remodeling. Aiming at the elimination of radiation exposure, this paper presents a novel methodology for the replacement of CT by a 3D laser scanner (radiation-free) for prosthesis modeling. The complete elimination of CT is based on an accurate determination of ribs position and prosthesis placement region through skin surface points. The developed solution resorts to a normalized and combined outcome of an artificial neural network (ANN) set. Each ANN model was trained with data vectors from 165 male patients and using soft tissue thicknesses (STT) comprising information from the skin and rib cage (automatically determined by image processing algorithms). Tests revealed that ribs position for prosthesis placement and modeling can be estimated with an average error of 5.0±3.6mm. One also showed that the ANN performance can be improved by introducing a manually determined initial STT value in the ANN normalization procedure (average error of 2.82±0.76mm). Such error range is well below current prosthesis manual modeling (approximately 11mm), which can provide a valuable and radiation-free procedure for prosthesis personalization.
Publisher version
Appears in Collections:ICVS - Artigos em Revistas Internacionais com Referee

Files in This Item:
File Description SizeFormat 
rodrigues pl_med eng phys 2014 prep.pdf840,62 kBAdobe PDFView/Open

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu Currículo DeGóis