DENTALMAPS: Automatic Dental Delineation for Radiotherapy Planning in Head and Neck Cancer

Juliette Thariat; Liliane Ramus; Philippe Maingon; Guillaume Odin; Vincent Grégoire; Vincent Darcourt; Pierre-Yves Marcy; Nicolas Guevara; Marie-Helene Orlanducci; Serge Marcie; Gilles Poissonnet; Alex Bozec; Olivier Dassonville; François Demard; Laurent Castillo; José Santini; Grégoire Malandain

HAL: inria-00616186, version 1

International Journal of Radiation Oncology*Biology*Physics / International Journal of Radiation Oncology Biology Physics; International Journal of Radiation Oncology Biology & Physics (2011)

DENTALMAPS: Automatic Dental Delineation for Radiotherapy Planning in Head and Neck Cancer

Juliette Thariat ¹, Liliane Ramus (

) ^2, 3, Philippe Maingon ⁴, Guillaume Odin ⁵, Vincent Grégoire ⁶, Vincent Darcourt ⁷, Pierre-Yves Marcy ⁷, Nicolas Guevara ⁵, Marie-Helene Orlanducci ⁵, Serge Marcie ⁷, Gilles Poissonnet ⁷, Alex Bozec ⁷, Olivier Dassonville ⁷, François Demard ⁷, Laurent Castillo ⁵, José Santini ⁷, Grégoire Malandain (

) ²

(2011)

Purpose To propose an automatic atlas-based segmentation framework of the dental structures, called Dentalmaps, and to assess its accuracy and relevance to guide dental care in the context of intensity-modulated radiotherapy. Methods and Materials A multi-atlas-based segmentation, less sensitive to artifacts than previously published head-and-neck segmentation methods, was used. The manual segmentations of a 21-patient database were first deformed onto the query using nonlinear registrations with the training images and then fused to estimate the consensus segmentation of the query. Results The framework was evaluated with a leave-one-out protocol. The maximum doses estimated using manual contours were considered as ground truth and compared with the maximum doses estimated using automatic contours. The dose estimation error was within 2-Gy accuracy in 75% of cases (with a median of 0.9 Gy), whereas it was within 2-Gy accuracy in 30% of cases only with the visual estimation method without any contour, which is the routine practice procedure. Conclusions Dose estimates using this framework were more accurate than visual estimates without dental contour. Dentalmaps represents a useful documentation and communication tool between radiation oncologists and dentists in routine practice. Prospective multicenter assessment is underway on patients extrinsic to the database.

1:	Institute of Developmental Biology and Cancer (IBDC)

	CNRS : UMR6543 – Université Nice Sophia Antipolis [UNS]

2:	ASCLEPIOS (INRIA Sophia Antipolis)

	INRIA

3:	DOSIsoft

	DOSIsoft

4:	Centre Georges-François Leclerc (CGFL)

	CRLCC Georges-François Leclerc

5:	CHU Nice [Cimiez]

	Hôpital Cimiez

6:	Laboratoire des Mécanismes et Transfert en Géologie (LMTG)

	CNRS : UMR5563 – Observatoire Midi-Pyrénées – Université Paul Sabatier [UPS] - Toulouse III – Institut de recherche pour le développement [IRD] : UMR154

7:	Centre Antoine Lacassagne

	CRLCC Antoine Lacassagne

Research team (except Inria): Department of Radiation Oncology
Department of Head-and-Neck Surgery

Domain

Computer Science/Medical Imaging

Computer Science/Modeling and Simulation

Life Sciences/Bioengineering/Imaging

Engineering Sciences/Signal and Image processing

Computer Science/Signal and Image Processing


inria-00616186, version 1
http://hal.inria.fr/inria-00616186
oai:hal.inria.fr:inria-00616186
From: Project-Team Asclepios <>
Submitted for: Gregoire MALANDAIN <>
Submitted on: Friday, 19 August 2011 19:47:28
Updated on: Tuesday, 17 April 2012 15:53:15