TY - GEN
T1 - Feature-based characterisation of patient-specific 3d anatomical models
AU - Banerjee, Imon
AU - Paccini, Martina
AU - Ferrari, Enrico
AU - Catalano, Chiara Eva
AU - Biasotti, Silvia
AU - Spagnuolo, Michela
N1 - Publisher Copyright:
© 2019 The Author(s) Eurographics Proceedings © 2019 The Eurographics Association.
PY - 2019
Y1 - 2019
N2 - This paper aims to examine the potential of 3D shape analysis integrated to machine learning techniques in supporting medical investigation. In particular, we introduce an approach specially designed for the characterisation of anatomical landmarks on patient-specific 3D carpal bone models represented as triangular meshes. Furthermore, to identify functional articulation regions, two novel district-based properties are defined. The performance of both state of the art and novel features has been evaluated in a machine learning setting to identify a set of significant anatomical landmarks on patient data. Experiments have been performed on a carpal dataset of 56 patient-specific 3D models that are segmented from T1 weighed magnetic resonance (MR) scans of healthy male subjects. Despite the typical large inter-patient shape variation within the training samples, our framework has achieved promising results.
AB - This paper aims to examine the potential of 3D shape analysis integrated to machine learning techniques in supporting medical investigation. In particular, we introduce an approach specially designed for the characterisation of anatomical landmarks on patient-specific 3D carpal bone models represented as triangular meshes. Furthermore, to identify functional articulation regions, two novel district-based properties are defined. The performance of both state of the art and novel features has been evaluated in a machine learning setting to identify a set of significant anatomical landmarks on patient data. Experiments have been performed on a carpal dataset of 56 patient-specific 3D models that are segmented from T1 weighed magnetic resonance (MR) scans of healthy male subjects. Despite the typical large inter-patient shape variation within the training samples, our framework has achieved promising results.
UR - http://www.scopus.com/inward/record.url?scp=85086728601&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85086728601&partnerID=8YFLogxK
U2 - 10.2312/stag.20191362
DO - 10.2312/stag.20191362
M3 - Conference contribution
AN - SCOPUS:85086728601
T3 - Italian Chapter Conference 2019 - Smart Tools and Apps in computer Graphics, STAG 2019
SP - 41
EP - 50
BT - Italian Chapter Conference 2019 - Smart Tools and Apps in computer Graphics, STAG 2019
A2 - Agus, Marco
A2 - Corsini, Massimiliano
A2 - Pintus, Ruggero
PB - Eurographics Association
T2 - 2019 Italian Chapter Conference - Smart Tools and Apps in Computer Graphics, STAG 2019
Y2 - 14 November 2019 through 15 November 2019
ER -