TY - GEN
T1 - Deep recurrent-convolutional model for automated segmentation of craniomaxillofacial CT scans
AU - Murabito, F.
AU - Palazzo, S.
AU - Salanitri, F. Proietto
AU - Rundo, F.
AU - Bagci, U.
AU - Giordano, D.
AU - Leonardi, R.
AU - Spampinato, C.
N1 - Publisher Copyright:
© 2020 IEEE
PY - 2020
Y1 - 2020
N2 - In this paper we define a deep learning architecture for automated segmentation of anatomical structures in Craniomaxillofacial (CMF) CT scans that leverages the recent success of encoder-decoder models for semantic segmentation of natural images. In particular, we propose a fully convolutional deep network that combines the advantages of recent fully convolutional models, such as Tiramisu, with squeeze-and-excitation blocks for feature recalibration, integrated with convolutional LSTMs to model spatio-temporal correlations between consecutive slices. The proposed segmentation network shows superior performance and generalization capabilities (to different structures and imaging modalities) than state of the art methods on automated segmentation of CMF structures (e.g., mandibles and airways) in several standard benchmarks (e.g., MICCAI datasets) and on new datasets proposed herein, effectively facing shape variability.
AB - In this paper we define a deep learning architecture for automated segmentation of anatomical structures in Craniomaxillofacial (CMF) CT scans that leverages the recent success of encoder-decoder models for semantic segmentation of natural images. In particular, we propose a fully convolutional deep network that combines the advantages of recent fully convolutional models, such as Tiramisu, with squeeze-and-excitation blocks for feature recalibration, integrated with convolutional LSTMs to model spatio-temporal correlations between consecutive slices. The proposed segmentation network shows superior performance and generalization capabilities (to different structures and imaging modalities) than state of the art methods on automated segmentation of CMF structures (e.g., mandibles and airways) in several standard benchmarks (e.g., MICCAI datasets) and on new datasets proposed herein, effectively facing shape variability.
KW - Fully convolutional neural networks
KW - Mandibles
KW - Pharyngeal airways
KW - Squeeze-and-excitation residual layers
UR - http://www.scopus.com/inward/record.url?scp=85110484090&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85110484090&partnerID=8YFLogxK
U2 - 10.1109/ICPR48806.2021.9413084
DO - 10.1109/ICPR48806.2021.9413084
M3 - Conference contribution
AN - SCOPUS:85110484090
T3 - Proceedings - International Conference on Pattern Recognition
SP - 10644
EP - 10649
BT - Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 25th International Conference on Pattern Recognition, ICPR 2020
Y2 - 10 January 2021 through 15 January 2021
ER -