Automated Computer-aided Design of Cranial Implants Using a Deep Volumetric Convolutional Denoising Autoencoder

Ana Morais, Jan Egger, Victor Alves

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandForschungBegutachtung

Abstract

Computer-aided Design (CAD) software enables the design of patient-specific cranial implants, but it often requires of a lot of manual user-interactions. This paper proposes a Deep Learning (DL) approach towards the automated CAD of cranial implants, allowing the design process to be less user-dependent and even less time-consuming. The problem of reconstructing a cranial defect, which is essentially filling in a region in a skull, was posed as a 3D shape completion task and, to solve it, a Volumetric Convolutional Denoising Autoencoder was implemented using the open-source DL framework PyTorch. The autoencoder was trained on 3D skull models obtained by processing an open-access dataset of Magnetic Resonance Imaging brain scans. The 3D skull models were represented as binary voxel occupancy grids and experiments were carried out for different voxel resolutions. For each experiment …
Originalspracheenglisch
TitelNew Knowledge in Information Systems and Technologies
UntertitelWorldCIST'19 2019
Redakteure/-innenÁ. Rocha, H. Adeli, L. Reis, S. Costanzo
ErscheinungsortCham
Herausgeber (Verlag)Springer
Seiten151-160
Band1
ISBN (elektronisch)978-3-030-16187-3
ISBN (Print)978-3-030-16186-6
DOIs
PublikationsstatusVeröffentlicht - 2019
Veranstaltung2019 World Conference on Information Systems and Technologies - Galicia, Spanien
Dauer: 16 Apr 201919 Apr 2019

Publikationsreihe

NameAdvances in Intelligent Systems and Computing
Band932

Konferenz

Konferenz2019 World Conference on Information Systems and Technologies
KurztitelWorldCIST 2019
LandSpanien
OrtGalicia
Zeitraum16/04/1919/04/19

Fingerprint

Computer aided design
Brain
Experiments
Defects
Processing
Deep learning
Magnetic Resonance Imaging

Dies zitieren

Morais, A., Egger, J., & Alves, V. (2019). Automated Computer-aided Design of Cranial Implants Using a Deep Volumetric Convolutional Denoising Autoencoder. in Á. Rocha, H. Adeli, L. Reis, & S. Costanzo (Hrsg.), New Knowledge in Information Systems and Technologies: WorldCIST'19 2019 (Band 1, S. 151-160). (Advances in Intelligent Systems and Computing; Band 932). Cham: Springer. https://doi.org/10.1007/978-3-030-16187-3_15

Automated Computer-aided Design of Cranial Implants Using a Deep Volumetric Convolutional Denoising Autoencoder. / Morais, Ana; Egger, Jan; Alves, Victor.

New Knowledge in Information Systems and Technologies: WorldCIST'19 2019. Hrsg. / Á. Rocha; H. Adeli; L. Reis; S. Costanzo. Band 1 Cham : Springer, 2019. S. 151-160 (Advances in Intelligent Systems and Computing; Band 932).

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandForschungBegutachtung

Morais, A, Egger, J & Alves, V 2019, Automated Computer-aided Design of Cranial Implants Using a Deep Volumetric Convolutional Denoising Autoencoder. in Á Rocha, H Adeli, L Reis & S Costanzo (Hrsg.), New Knowledge in Information Systems and Technologies: WorldCIST'19 2019. Bd. 1, Advances in Intelligent Systems and Computing, Bd. 932, Springer, Cham, S. 151-160, Galicia, Spanien, 16/04/19. https://doi.org/10.1007/978-3-030-16187-3_15
Morais A, Egger J, Alves V. Automated Computer-aided Design of Cranial Implants Using a Deep Volumetric Convolutional Denoising Autoencoder. in Rocha Á, Adeli H, Reis L, Costanzo S, Hrsg., New Knowledge in Information Systems and Technologies: WorldCIST'19 2019. Band 1. Cham: Springer. 2019. S. 151-160. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-030-16187-3_15
Morais, Ana ; Egger, Jan ; Alves, Victor. / Automated Computer-aided Design of Cranial Implants Using a Deep Volumetric Convolutional Denoising Autoencoder. New Knowledge in Information Systems and Technologies: WorldCIST'19 2019. Hrsg. / Á. Rocha ; H. Adeli ; L. Reis ; S. Costanzo. Band 1 Cham : Springer, 2019. S. 151-160 (Advances in Intelligent Systems and Computing).
@inproceedings{eb0eaeb0c7fc4752a5ca62674a69d5b9,
title = "Automated Computer-aided Design of Cranial Implants Using a Deep Volumetric Convolutional Denoising Autoencoder",
abstract = "Computer-aided Design (CAD) software enables the design of patient-specific cranial implants, but it often requires of a lot of manual user-interactions. This paper proposes a Deep Learning (DL) approach towards the automated CAD of cranial implants, allowing the design process to be less user-dependent and even less time-consuming. The problem of reconstructing a cranial defect, which is essentially filling in a region in a skull, was posed as a 3D shape completion task and, to solve it, a Volumetric Convolutional Denoising Autoencoder was implemented using the open-source DL framework PyTorch. The autoencoder was trained on 3D skull models obtained by processing an open-access dataset of Magnetic Resonance Imaging brain scans. The 3D skull models were represented as binary voxel occupancy grids and experiments were carried out for different voxel resolutions. For each experiment …",
author = "Ana Morais and Jan Egger and Victor Alves",
year = "2019",
doi = "10.1007/978-3-030-16187-3_15",
language = "English",
isbn = "978-3-030-16186-6",
volume = "1",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer",
pages = "151--160",
editor = "{\'A}. Rocha and H. Adeli and L. Reis and S. Costanzo",
booktitle = "New Knowledge in Information Systems and Technologies",

}

TY - GEN

T1 - Automated Computer-aided Design of Cranial Implants Using a Deep Volumetric Convolutional Denoising Autoencoder

AU - Morais, Ana

AU - Egger, Jan

AU - Alves, Victor

PY - 2019

Y1 - 2019

N2 - Computer-aided Design (CAD) software enables the design of patient-specific cranial implants, but it often requires of a lot of manual user-interactions. This paper proposes a Deep Learning (DL) approach towards the automated CAD of cranial implants, allowing the design process to be less user-dependent and even less time-consuming. The problem of reconstructing a cranial defect, which is essentially filling in a region in a skull, was posed as a 3D shape completion task and, to solve it, a Volumetric Convolutional Denoising Autoencoder was implemented using the open-source DL framework PyTorch. The autoencoder was trained on 3D skull models obtained by processing an open-access dataset of Magnetic Resonance Imaging brain scans. The 3D skull models were represented as binary voxel occupancy grids and experiments were carried out for different voxel resolutions. For each experiment …

AB - Computer-aided Design (CAD) software enables the design of patient-specific cranial implants, but it often requires of a lot of manual user-interactions. This paper proposes a Deep Learning (DL) approach towards the automated CAD of cranial implants, allowing the design process to be less user-dependent and even less time-consuming. The problem of reconstructing a cranial defect, which is essentially filling in a region in a skull, was posed as a 3D shape completion task and, to solve it, a Volumetric Convolutional Denoising Autoencoder was implemented using the open-source DL framework PyTorch. The autoencoder was trained on 3D skull models obtained by processing an open-access dataset of Magnetic Resonance Imaging brain scans. The 3D skull models were represented as binary voxel occupancy grids and experiments were carried out for different voxel resolutions. For each experiment …

U2 - 10.1007/978-3-030-16187-3_15

DO - 10.1007/978-3-030-16187-3_15

M3 - Conference contribution

SN - 978-3-030-16186-6

VL - 1

T3 - Advances in Intelligent Systems and Computing

SP - 151

EP - 160

BT - New Knowledge in Information Systems and Technologies

A2 - Rocha, Á.

A2 - Adeli, H.

A2 - Reis, L.

A2 - Costanzo, S.

PB - Springer

CY - Cham

ER -